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>

.gitignore

@@ -6,3 +6,4 @@ dist
 .vite
 coverage
 secrets/
+data/

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/projects.ts

@@ -9,6 +9,7 @@ import type { Project, AvailableProject } from '../types/api.js';
 import { resolveProjectRoot, PathScopeError } from '../services/path_guard.js';
 import { listDir, viewFile } from '../services/file_ops.js';
 import { getProjectFiles } from '../services/file_index.js';
+import { getGitMeta } from '../services/git_meta.js';
 import {
   bootstrapProject,
   BootstrapNameError,
@@ -381,6 +382,38 @@ export function registerProjectRoutes(
     }
   );
 
+  // GET /api/projects/:id/git
+  // v1.8 mobile-tabs: feeds the header branch indicator and is the same
+  // resolver the model's git_status tool uses. Returns 200 with branch=null
+  // for non-git directories (not 404) so the UI can degrade gracefully.
+  app.get<{ Params: { id: string } }>(
+    '/api/projects/:id/git',
+    async (req, reply) => {
+      const { id } = req.params;
+      const rows = await sql<Project[]>`
+        SELECT id, name, path, added_at, last_session_id, status, gitea_remote
+        FROM projects WHERE id = ${id}
+      `;
+      if (rows.length === 0) {
+        reply.code(404);
+        return { error: 'not found' };
+      }
+      const project = rows[0]!;
+      let projectRoot: string;
+      try {
+        projectRoot = await resolveProjectRoot(project.path);
+      } catch (err) {
+        if (err instanceof PathScopeError) {
+          reply.code(404);
+          return { error: err.message };
+        }
+        throw err;
+      }
+      const meta = await getGitMeta(projectRoot);
+      return meta ?? { branch: null, is_dirty: false, ahead: 0, behind: 0 };
+    }
+  );
+
   // GET /api/projects/:id/files
   app.get<{ Params: { id: string } }>(
     '/api/projects/:id/files',

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

@@ -1,9 +1,17 @@
 import { promises as fs } from 'node:fs';
 import { join } from 'node:path';
-import type { Agent, AgentsResponse } from '../types/api.js';
+import type { Agent, AgentsResponse, AgentParseError } from '../types/api.js';
+
+// v1.8.1: global agents live at /data/AGENTS.md inside the container
+// (./data:/data:ro mount on the host). Per-project AGENTS.md at the project
+// root overrides global by name. In-code builtins are gone — the seed file is
+// the contents of the previous BUILTIN_AGENTS list, copied into /data/AGENTS.md
+// once on first deploy.
+const GLOBAL_AGENTS_PATH = '/data/AGENTS.md';
+const CACHE_TTL_MS = 60_000;
 
 // Tools whitelist universe matches services/tools.ts ALL_TOOLS. Keep in sync.
-const ALL_TOOL_NAMES = ['view_file', 'list_dir', 'grep', 'find_files'] as const;
+const ALL_TOOL_NAMES = ['view_file', 'list_dir', 'grep', 'find_files', 'git_status'] as const;
 const DEFAULT_TOOLS: string[] = [...ALL_TOOL_NAMES];
 const DEFAULT_TEMPERATURE = 0.7;
 
@@ -14,214 +22,6 @@ export function slugify(name: string): string {
     .replace(/^-+|-+$/g, '');
 }
 
-// Six builtin defaults. model is intentionally null — session.model wins.
-// Match AGENTS.md format; system prompts are verbatim.
-const BUILTIN_AGENTS: Agent[] = [
-  {
-    id: 'code-reviewer',
-    name: 'Code Reviewer',
-    description: 'Reviews code for bugs, security issues, and maintainability. Read-only.',
-    temperature: 0.3,
-    tools: [...DEFAULT_TOOLS],
-    model: null,
-    source: 'builtin',
-    system_prompt: `You review code. Find real problems, not style nits.
-
-Process:
-1. Read the file(s) in question with view_file. If a diff is provided, read surrounding context too.
-2. Use grep/find_files to check how changed symbols are used elsewhere.
-3. Cite every finding as file:line.
-
-Prioritize in order:
-1. Bugs and logic errors
-2. Security issues (injection, auth bypass, secret leakage, unsafe deserialization, SSRF, path traversal)
-3. Race conditions, error handling, resource leaks
-4. Performance issues with measurable impact
-5. Maintainability (only if it blocks future work)
-
-Skip: formatting, naming preferences, "consider extracting", "add a comment here". The user has a linter.
-
-Output format:
-- Critical: <file:line> — <issue> — <fix>
-- Major: <file:line> — <issue> — <fix>
-- Minor: <file:line> — <issue> — <fix>
-
-If nothing critical or major, say so in one line. Do not pad.`,
-  },
-  {
-    id: 'debugger',
-    name: 'Debugger',
-    description: 'Diagnoses bugs from error messages, logs, or described symptoms.',
-    temperature: 0.2,
-    tools: [...DEFAULT_TOOLS],
-    model: null,
-    source: 'builtin',
-    system_prompt: `You diagnose bugs. Form a hypothesis, prove it with evidence from the code.
-
-Process:
-1. Restate the symptom in one line. Confirm you understand it.
-2. Read the error/stacktrace. Identify the exact frame where things go wrong.
-3. view_file on that frame. Read 50 lines around it.
-4. grep for callers, related state, recent changes that could explain it.
-5. State the root cause with file:line evidence.
-6. Propose the minimal fix. Note any side effects.
-
-Rules:
-- Never guess. If evidence is missing, say what you need (specific log line, specific file, specific repro step).
-- Distinguish symptom from cause. A null check fixes the symptom; missing init causes it.
-- Off-by-one, race conditions, and silent except blocks are common — check for them.
-- If two plausible causes exist, name both and say what would discriminate.
-
-Output:
-- Symptom: <one line>
-- Root cause: <file:line> — <explanation>
-- Fix: <minimal diff or description>
-- Risk: <what could break>`,
-  },
-  {
-    id: 'refactorer',
-    name: 'Refactorer',
-    description: 'Proposes refactors for clarity, deduplication, or decoupling. Read-only — outputs plans, not edits.',
-    temperature: 0.3,
-    tools: [...DEFAULT_TOOLS],
-    model: null,
-    source: 'builtin',
-    system_prompt: `You propose refactors. You do not apply them. The user applies via OpenCode or Claude Code.
-
-Process:
-1. Read the target file(s).
-2. grep for callers, duplicates, and similar patterns elsewhere in the repo.
-3. Identify the smallest refactor that delivers the goal.
-
-Prioritize:
-1. Deduplication where 3+ sites have near-identical logic
-2. Extracting a function/module when one is doing two unrelated jobs
-3. Decoupling when a change in A forces a change in B unnecessarily
-4. Renaming when a name actively misleads
-
-Reject:
-- Refactors that touch 10+ files for marginal gain
-- "Modernization" with no concrete benefit
-- Abstraction for future flexibility that may never come
-- Style-only changes
-
-Output:
-- Goal: <one line>
-- Scope: <files affected, count of lines roughly>
-- Plan: numbered steps, each one self-contained
-- Risk: <what tests must pass, what could regress>
-- Skip if: <conditions under which this refactor is not worth doing>`,
-  },
-  {
-    id: 'architect',
-    name: 'Architect',
-    description: 'Designs new features, modules, or architectural changes. Outputs a build plan.',
-    temperature: 0.5,
-    tools: [...DEFAULT_TOOLS],
-    model: null,
-    source: 'builtin',
-    system_prompt: `You design. You produce build plans, not code.
-
-Process:
-1. Restate the goal in your own words. Confirm constraints (perf, deploy, deps).
-2. list_dir the relevant areas. Read existing patterns — match them unless there's a reason not to.
-3. Decide: extend existing code or add new module. Justify.
-4. Sketch the data flow: inputs → transforms → outputs → side effects.
-5. Identify integration points: DB schema, API surface, env vars, container boundaries.
-6. List failure modes and how the design handles them.
-
-Rules:
-- Reuse before inventing. If a service/lib in the repo already does this, say so.
-- Prefer boring tech. New deps require justification.
-- Tailscale IPs for internal routing. No 0.0.0.0 binds.
-- Least privilege: separate read/write paths, explicit auth gates.
-- State assumptions inline. Do not ask clarifying questions mid-design unless blocked.
-
-Output:
-- Goal
-- Existing code to reuse: <file paths>
-- New code: <file paths, one-line purpose each>
-- Data model changes: <SQL or schema diff>
-- API surface: <endpoints, request/response shapes>
-- Failure modes: <list>
-- Build order: numbered, each step 30-90 min`,
-  },
-  {
-    id: 'security-auditor',
-    name: 'Security Auditor',
-    description: 'Audits code for security vulnerabilities. Read-only.',
-    temperature: 0.2,
-    tools: [...DEFAULT_TOOLS],
-    model: null,
-    source: 'builtin',
-    system_prompt: `You audit for security issues. Concrete findings only, no generic warnings.
-
-Process:
-1. Identify the trust boundary: where does untrusted input enter? Where does it leave?
-2. Trace input flow with grep. Mark every transformation.
-3. Check each finding against a real attack scenario.
-
-Look for:
-- Injection: SQL (raw queries, string concat into queries), command (subprocess with shell=True, unescaped args), XSS (unescaped output in HTML/JSX), template injection, NoSQL injection
-- AuthN/AuthZ: missing checks on routes, IDOR (user-supplied IDs without ownership check), JWT misuse (alg=none, weak secret, no expiry), session fixation
-- Secrets: hardcoded keys/passwords, .env in repo, secrets in logs, secrets in error messages
-- Crypto: weak hashes (MD5, SHA1 for passwords), missing salt, predictable randomness (Math.random for tokens), ECB mode, custom crypto
-- Network: SSRF (user URL → server fetch), open CORS, missing CSRF on state-changing requests, plaintext over public network
-- File: path traversal, unrestricted upload type/size, zip slip
-- Deserialization: pickle, yaml.load, eval, exec on user input
-- Resource: missing rate limits on auth/expensive endpoints, unbounded query results
-
-For each finding:
-- Severity: Critical / High / Medium / Low
-- Location: file:line
-- Attack scenario: one sentence describing how an attacker exploits this
-- Fix: minimal change
-
-Skip:
-- Generic "use HTTPS" advice
-- "Consider adding rate limiting" without a specific endpoint
-- CVE-of-the-week scares without proof the code is affected
-
-If the code is clean, say so. Do not invent findings.`,
-  },
-  {
-    id: 'prompt-builder',
-    name: 'Prompt Builder',
-    description: 'Builds prompts for OpenCode, Claude Code, or BooCode dispatch.',
-    temperature: 0.4,
-    tools: [...DEFAULT_TOOLS],
-    model: null,
-    source: 'builtin',
-    system_prompt: `You write prompts that another coding agent will execute. Your output is the prompt, not the work.
-
-Process:
-1. Ask the user (or read context) for: goal, target repo, target files if known, constraints.
-2. list_dir and view_file the target area. Confirm files exist and are roughly the shape you think.
-3. Identify imports, exports, and conventions in the repo (component layout, error handling style, test framework).
-4. Write the prompt.
-
-Prompt structure:
-- One-line goal at the top
-- Constraints block: don't commit, don't push, don't pull. Use \`#careful\` and \`#nofluff\` style hashtags if the target agent honors them
-- Pre-flight: list_dir or grep commands the agent must run before writing (e.g. "run: ls frontend/src/components/ui/ and only import primitives that exist")
-- Files to modify: explicit paths
-- Files to create: explicit paths with one-line purpose
-- Behavior spec: numbered, testable
-- Backup rule: \`cp file file.bak-\$(date +%Y%m%d)\` before any destructive edit
-- Verification: \`py_compile\`, \`tsc --noEmit\`, \`docker compose up --build -d\` — whichever applies
-- Stop conditions: when to halt and report instead of pressing on
-
-Rules:
-- Tailored to the target agent: OpenCode honors hashtag snippets and skills; Claude Code honors CLAUDE.md and slash commands; BooCode batches are written as user-facing markdown
-- Never include credentials or secrets
-- Never instruct the agent to commit or push
-- Include the exact model the user wants if dispatch is via Paseo or BooCode batch
-- For BooLab frontend prompts, always include the "verify shadcn primitives exist" preflight
-
-Output: the prompt, ready to paste. Nothing else.`,
-  },
-];
-
 // ---- AGENTS.md parser ------------------------------------------------------
 
 interface ParsedFrontmatter {
@@ -229,6 +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 {
@@ -289,6 +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.
   }
@@ -296,18 +114,14 @@ function parseFrontmatter(yaml: string): { data: ParsedFrontmatter; errors: stri
   return { data, errors };
 }
 
-interface ParseResult {
-  agents: Agent[];
-  error: string | null;
+interface RawSection {
+  name: string;
+  body: string;
 }
 
-export function parseAgentsMd(content: string): ParseResult {
-  const errors: string[] = [];
-  const agents: Agent[] = [];
-
-  // Split into per-agent sections by lines that exactly match "## <name>".
-  // Lines starting with "### " (level-3 headings) are not section boundaries.
-  const sections: { name: string; body: string }[] = [];
+function splitSections(content: string): RawSection[] {
+  // Split by lines matching exactly "## <name>". Level-3+ headings are body content.
+  const sections: RawSection[] = [];
   let currentName: string | null = null;
   let currentLines: string[] = [];
 
@@ -329,74 +143,102 @@ export function parseAgentsMd(content: string): ParseResult {
   if (currentName !== null) {
     sections.push({ name: currentName, body: currentLines.join('\n') });
   }
+  return sections;
+}
 
-  for (const section of sections) {
-    const lines = section.body.split('\n');
-    // Opening "---" fence must be the first non-empty line (blank lines allowed).
-    let openIdx = -1;
-    for (let i = 0; i < lines.length; i++) {
-      const t = lines[i]!.trim();
-      if (t === '') continue;
-      if (t === '---') {
-        openIdx = i;
-      }
+// Throws on malformed section — caller handles per-block error collection.
+function parseAgentSection(section: RawSection): Omit<Agent, 'source'> {
+  const lines = section.body.split('\n');
+
+  // Opening "---" fence must be the first non-empty line.
+  let openIdx = -1;
+  for (let i = 0; i < lines.length; i++) {
+    const t = lines[i]!.trim();
+    if (t === '') continue;
+    if (t === '---') {
+      openIdx = i;
+    }
+    break;
+  }
+  if (openIdx < 0) {
+    throw new Error('missing opening --- fence after heading');
+  }
+  let closeIdx = -1;
+  for (let i = openIdx + 1; i < lines.length; i++) {
+    if (lines[i]!.trim() === '---') {
+      closeIdx = i;
       break;
     }
-    if (openIdx < 0) {
-      errors.push(`agent "${section.name}": missing opening --- fence after heading`);
-      continue;
-    }
-    let closeIdx = -1;
-    for (let i = openIdx + 1; i < lines.length; i++) {
-      if (lines[i]!.trim() === '---') {
-        closeIdx = i;
-        break;
-      }
-    }
-    if (closeIdx < 0) {
-      errors.push(`agent "${section.name}": missing closing --- fence`);
-      continue;
-    }
-    const yamlText = lines.slice(openIdx + 1, closeIdx).join('\n');
-    const systemPrompt = lines.slice(closeIdx + 1).join('\n').trim();
+  }
+  if (closeIdx < 0) {
+    throw new Error('missing closing --- fence');
+  }
+  const yamlText = lines.slice(openIdx + 1, closeIdx).join('\n');
+  const systemPrompt = lines.slice(closeIdx + 1).join('\n').trim();
 
-    const { data: fm, errors: fmErrors } = parseFrontmatter(yamlText);
-    if (fmErrors.length > 0) {
-      errors.push(`agent "${section.name}": ${fmErrors.join('; ')}`);
-      continue;
-    }
-
-    const filteredTools = Array.isArray(fm.tools)
-      ? fm.tools.filter((t): t is string =>
-          (ALL_TOOL_NAMES as readonly string[]).includes(t)
-        )
-      : DEFAULT_TOOLS;
-
-    agents.push({
-      id: slugify(section.name),
-      name: section.name,
-      description: fm.description ?? '',
-      system_prompt: systemPrompt,
-      temperature: typeof fm.temperature === 'number' ? fm.temperature : DEFAULT_TEMPERATURE,
-      tools: filteredTools,
-      model: typeof fm.model === 'string' && fm.model.length > 0 ? fm.model : null,
-      source: 'file',
-    });
+  const { data: fm, errors: fmErrors } = parseFrontmatter(yamlText);
+  if (fmErrors.length > 0) {
+    throw new Error(fmErrors.join('; '));
   }
 
-  return { agents, error: errors.length > 0 ? errors.join('; ') : null };
+  const filteredTools = Array.isArray(fm.tools)
+    ? fm.tools.filter((t): t is string =>
+        (ALL_TOOL_NAMES as readonly string[]).includes(t),
+      )
+    : DEFAULT_TOOLS;
+
+  return {
+    id: slugify(section.name),
+    name: section.name,
+    description: fm.description ?? '',
+    system_prompt: systemPrompt,
+    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,
+  };
+}
+
+interface ParseResult {
+  agents: Omit<Agent, 'source'>[];
+  errors: AgentParseError[];
+}
+
+// v1.8.1: parse each `## Name` block independently. A failure in one block
+// does not abort the rest of the file — we collect a per-agent error and
+// keep parsing. Server logs a console.warn for each skipped agent.
+export function parseAgentsMd(content: string): ParseResult {
+  const sections = splitSections(content);
+  const agents: Omit<Agent, 'source'>[] = [];
+  const errors: AgentParseError[] = [];
+
+  for (const section of sections) {
+    try {
+      agents.push(parseAgentSection(section));
+    } catch (err) {
+      const reason = err instanceof Error ? err.message : String(err);
+      console.warn(`agents: skipped "${section.name}" — ${reason}`);
+      errors.push({ agent_name: section.name, reason });
+    }
+  }
+
+  return { agents, errors };
 }
 
 // ---- mtime-keyed cache + public API ----------------------------------------
 
 interface CacheEntry {
-  mtimeMs: number;
+  globalMtime: number | null;
+  projectMtime: number | null;
+  cachedAt: number;
   result: AgentsResponse;
 }
 
+// Keyed by projectPath ('' is fine — no project case, e.g. tests). Two files
+// participate in the cache key (global + project); editing either bumps the
+// corresponding mtime so the next read sees a miss without a watcher.
 const cache = new Map<string, CacheEntry>();
 
-// Test/admin: force re-parse on next call for a project (or all projects).
 export function invalidateAgentsCache(projectPath?: string): void {
   if (projectPath === undefined) {
     cache.clear();
@@ -405,54 +247,74 @@ export function invalidateAgentsCache(projectPath?: string): void {
   }
 }
 
-export async function getAgentsForProject(projectPath: string): Promise<AgentsResponse> {
-  const agentsPath = join(projectPath, 'AGENTS.md');
-  let mtimeMs: number;
+async function safeStat(path: string): Promise<number | null> {
   try {
-    const s = await fs.stat(agentsPath);
-    mtimeMs = s.mtimeMs;
+    const s = await fs.stat(path);
+    return s.mtimeMs;
   } catch {
-    // No AGENTS.md → builtins, no parse error
-    cache.delete(projectPath);
-    return { agents: BUILTIN_AGENTS, parse_error: null };
+    return null;
   }
+}
 
-  const cached = cache.get(projectPath);
-  if (cached && cached.mtimeMs === mtimeMs) {
+async function safeRead(path: string): Promise<string | null> {
+  try {
+    return await fs.readFile(path, 'utf8');
+  } catch {
+    return null;
+  }
+}
+
+export async function getAgentsForProject(projectPath: string): Promise<AgentsResponse> {
+  const projectAgentsPath = projectPath ? join(projectPath, 'AGENTS.md') : null;
+
+  const [globalMtime, projectMtime] = await Promise.all([
+    safeStat(GLOBAL_AGENTS_PATH),
+    projectAgentsPath ? safeStat(projectAgentsPath) : Promise.resolve(null),
+  ]);
+
+  const cacheKey = projectPath || '__none__';
+  const cached = cache.get(cacheKey);
+  const now = Date.now();
+  if (
+    cached &&
+    cached.globalMtime === globalMtime &&
+    cached.projectMtime === projectMtime &&
+    now - cached.cachedAt < CACHE_TTL_MS
+  ) {
     return cached.result;
   }
 
-  let content: string;
-  try {
-    content = await fs.readFile(agentsPath, 'utf8');
-  } catch {
-    cache.delete(projectPath);
-    return { agents: BUILTIN_AGENTS, parse_error: null };
+  const [globalContent, projectContent] = await Promise.all([
+    globalMtime !== null ? safeRead(GLOBAL_AGENTS_PATH) : Promise.resolve(null),
+    projectAgentsPath && projectMtime !== null ? safeRead(projectAgentsPath) : Promise.resolve(null),
+  ]);
+
+  const errors: AgentParseError[] = [];
+  const byName = new Map<string, Agent>();
+
+  if (globalContent !== null) {
+    const r = parseAgentsMd(globalContent);
+    for (const a of r.agents) byName.set(a.name, { ...a, source: 'global' });
+    errors.push(...r.errors);
+  }
+  if (projectContent !== null) {
+    const r = parseAgentsMd(projectContent);
+    for (const a of r.agents) byName.set(a.name, { ...a, source: 'project' });
+    errors.push(...r.errors);
   }
 
-  const parsed = parseAgentsMd(content);
-  let result: AgentsResponse;
-  if (parsed.error) {
-    // Parse error: surface in API, fall back to builtins
-    result = { agents: BUILTIN_AGENTS, parse_error: parsed.error };
-  } else if (parsed.agents.length === 0) {
-    // Empty / no headings → builtins
-    result = { agents: BUILTIN_AGENTS, parse_error: null };
-  } else {
-    // At least one valid agent → file-defined agents win, builtins hidden
-    result = { agents: parsed.agents, parse_error: null };
-  }
-
-  cache.set(projectPath, { mtimeMs, result });
+  const result: AgentsResponse = {
+    agents: Array.from(byName.values()),
+    errors,
+  };
+  cache.set(cacheKey, { globalMtime, projectMtime, cachedAt: now, result });
   return result;
 }
 
 export async function getAgentById(
   projectPath: string,
-  agentId: string
+  agentId: string,
 ): Promise<Agent | null> {
   const { agents } = await getAgentsForProject(projectPath);
   return agents.find((a) => a.id === agentId) ?? null;
 }
-
-export { BUILTIN_AGENTS };

apps/server/src/services/git_meta.ts

@@ -0,0 +1,92 @@
+import { execFile } from 'node:child_process';
+import { promisify } from 'node:util';
+
+const execFileAsync = promisify(execFile);
+
+const CACHE_TTL_MS = 30_000;
+const GIT_TIMEOUT_MS = 2_000;
+// Cap stdout size so a pathological repo can't blow the buffer. Branch + status
+// porcelain + diverge counts never approach this on a real repo.
+const GIT_MAX_BUFFER = 1024 * 1024;
+
+export interface GitMeta {
+  branch: string | null;
+  is_dirty: boolean;
+  ahead: number;
+  behind: number;
+}
+
+interface CacheEntry {
+  at: number;
+  value: GitMeta | null;
+}
+
+const cache = new Map<string, CacheEntry>();
+
+// Runs a single git invocation with a hard 2s timeout. Returns null on any
+// failure (non-zero exit, timeout, git not installed) so callers can decide
+// how to degrade. Stderr is intentionally swallowed; we don't surface git's
+// error text to the model or UI.
+async function runGit(args: string[], cwd: string): Promise<string | null> {
+  try {
+    const { stdout } = await execFileAsync('git', args, {
+      cwd,
+      timeout: GIT_TIMEOUT_MS,
+      windowsHide: true,
+      maxBuffer: GIT_MAX_BUFFER,
+    });
+    return stdout.toString();
+  } catch {
+    return null;
+  }
+}
+
+export async function getGitMeta(rootPath: string): Promise<GitMeta | null> {
+  const cached = cache.get(rootPath);
+  const now = Date.now();
+  if (cached && now - cached.at < CACHE_TTL_MS) {
+    return cached.value;
+  }
+
+  // Three calls in parallel. rev-parse establishes repo + branch name;
+  // status --porcelain detects dirtiness with no false-positives from formatting;
+  // rev-list --left-right --count compares HEAD to upstream and is allowed to
+  // fail silently (returns null → ahead/behind = 0) when no upstream is set.
+  const [branchOut, statusOut, divergedOut] = await Promise.all([
+    runGit(['rev-parse', '--abbrev-ref', 'HEAD'], rootPath),
+    runGit(['status', '--porcelain'], rootPath),
+    runGit(['rev-list', '--left-right', '--count', 'HEAD...@{upstream}'], rootPath),
+  ]);
+
+  // If rev-parse fails, this isn't a git repo (or git isn't installed). Cache
+  // the null result so the next 30s of requests don't re-probe.
+  if (branchOut === null) {
+    cache.set(rootPath, { at: now, value: null });
+    return null;
+  }
+
+  const branch = branchOut.trim() || null;
+  const is_dirty = statusOut !== null && statusOut.trim().length > 0;
+
+  let ahead = 0;
+  let behind = 0;
+  if (divergedOut !== null) {
+    const match = divergedOut.trim().match(/^(\d+)\s+(\d+)/);
+    if (match) {
+      ahead = Number(match[1]);
+      behind = Number(match[2]);
+    }
+  }
+
+  const value: GitMeta = { branch, is_dirty, ahead, behind };
+  cache.set(rootPath, { at: now, value });
+  return value;
+}
+
+export function invalidateGitMetaCache(rootPath?: string): void {
+  if (rootPath) {
+    cache.delete(rootPath);
+  } else {
+    cache.clear();
+  }
+}

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;
 }
 
@@ -480,20 +545,43 @@ 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}
     RETURNING project_id, name, updated_at
   `;
   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. 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,
@@ -501,12 +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');
   }
@@ -520,7 +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<
@@ -604,7 +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,
   });
 }
@@ -638,6 +736,7 @@ async function finalizeCompletion(
     RETURNING project_id, name, updated_at
   `;
   ctx.publishUser({ type: 'session_updated', session_id: sessionId, project_id: completeSessRow!.project_id, name: completeSessRow!.name, updated_at: completeSessRow!.updated_at });
+  ctx.publishUser({ type: 'chat_status', chat_id: chatId, status: 'idle', at: new Date().toISOString() });
   ctx.publish(sessionId, {
     type: 'message_complete',
     message_id: assistantMessageId,
@@ -667,24 +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',
-    });
-    return;
-  }
+  const { sessionId, chatId } = args;
 
   const loaded = await loadContext(ctx.sql, sessionId, chatId);
   if (!loaded) {
@@ -699,6 +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 };
@@ -725,7 +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 =
@@ -820,6 +1170,9 @@ export function createInferenceRunner(
         ...ctx,
         publishUser: (frame) => publishUserFn(user, frame),
       };
+      // v1.8 mobile-tabs: announce working before the async loop starts so
+      // every device subscribed to the user channel sees the amber dot.
+      callCtx.publishUser({ type: 'chat_status', chat_id: chatId, status: 'working', at: new Date().toISOString() });
       const controller = new AbortController();
       let resolveCompleted!: () => void;
       const completed = new Promise<void>((res) => { resolveCompleted = res; });

apps/server/src/services/tools.ts

@@ -3,6 +3,7 @@ import { resolve, basename, relative } from 'node:path';
 import { z } from 'zod';
 import { pathGuard, PathScopeError } from './path_guard.js';
 import { grep as fileOpsGrep, findFiles as fileOpsFindFiles } from './file_ops.js';
+import { getGitMeta } from './git_meta.js';
 
 const MAX_FILE_BYTES = 5 * 1024 * 1024;
 const DEFAULT_VIEW_LINES = 200;
@@ -266,13 +267,60 @@ export const findFiles: ToolDef<FindFilesInputT> = {
   },
 };
 
+// v1.8 Level 1 branch awareness: gives the model a read-only view of the
+// project's git state. No path input — operates on the inference-resolved
+// project root via getGitMeta. Subprocess runs with a 2s timeout (see git_meta).
+const GitStatusInput = z.object({}).strict();
+type GitStatusInputT = z.infer<typeof GitStatusInput>;
+
+export const gitStatus: ToolDef<GitStatusInputT> = {
+  name: 'git_status',
+  description:
+    "Returns the current git branch, whether the working tree is dirty, and ahead/behind counts vs upstream. Read-only. Use when you need to know which branch the user is currently working on.",
+  inputSchema: GitStatusInput,
+  jsonSchema: {
+    type: 'function',
+    function: {
+      name: 'git_status',
+      description:
+        'Returns the current git branch, dirty flag, and ahead/behind counts vs upstream. Read-only.',
+      parameters: {
+        type: 'object',
+        properties: {},
+        additionalProperties: false,
+      },
+    },
+  },
+  async execute(_input, projectRoot) {
+    const meta = await getGitMeta(projectRoot);
+    if (meta === null) {
+      return { repo: false, branch: null, is_dirty: false, ahead: 0, behind: 0 };
+    }
+    return { repo: true, ...meta };
+  },
+};
+
 export const ALL_TOOLS: ReadonlyArray<ToolDef<unknown>> = [
   viewFile as ToolDef<unknown>,
   listDir as ToolDef<unknown>,
   grep as ToolDef<unknown>,
   findFiles as 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

@@ -31,9 +31,10 @@ export interface Session {
   agent_id: string | null;
 }
 
-// Agent sources: 'builtin' = baked-in default (services/agents.ts),
-// 'file' = parsed from project's AGENTS.md.
-export type AgentSource = 'builtin' | 'file';
+// v1.8.1: agents come from two sources. 'global' = /data/AGENTS.md (always
+// loaded inside the container), 'project' = per-project override at
+// <root>/AGENTS.md. Project entries override global by name (case-sensitive).
+export type AgentSource = 'global' | 'project';
 
 export interface Agent {
   id: string;            // slug of name; stable handle stored in sessions.agent_id
@@ -44,11 +45,23 @@ 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
+// whole file — the loader returns parsed-successfully agents AND the list of
+// skipped ones so the UI can show a non-blocking warning chip.
+export interface AgentParseError {
+  agent_name: string;
+  reason: string;
 }
 
 export interface AgentsResponse {
   agents: Agent[];
-  parse_error: string | null;  // present (non-null) when AGENTS.md exists but failed to parse
+  errors: AgentParseError[];
 }
 
 // KEEP IN SYNC: apps/server/src/schema.sql chats_status_chk
@@ -91,6 +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;
@@ -108,6 +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 {
@@ -246,6 +287,17 @@ export interface ProjectUpdatedFrame {
   project_id: string;
   name: string;
 }
+// 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
   | ProjectDeletedFrame
@@ -261,4 +313,5 @@ export type UserStreamFrame =
   | ChatDeletedFrame
   | ProjectArchivedFrame
   | ProjectUnarchivedFrame
-  | ProjectUpdatedFrame;
+  | ProjectUpdatedFrame
+  | ChatStatusFrame;

apps/web/src/api/client.ts

@@ -9,6 +9,7 @@ import type {
   ListDirResult,
   ViewFileResult,
   AgentsResponse,
+  GitMeta,
 } from './types';
 
 export class ApiError extends Error {
@@ -87,6 +88,8 @@ export const api = {
       request<ViewFileResult>(`/api/projects/${id}/view_file?path=${encodeURIComponent(path)}`),
     files: (id: string) =>
       request<{ files: string[] }>(`/api/projects/${id}/files`),
+    git: (id: string) =>
+      request<GitMeta>(`/api/projects/${id}/git`),
   },
 
   sessions: {
@@ -149,6 +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

@@ -30,7 +30,10 @@ export interface Session {
   agent_id: string | null;
 }
 
-export type AgentSource = 'builtin' | 'file';
+// v1.8.1: 'global' = /data/AGENTS.md (always-on), 'project' = per-project
+// override at <root>/AGENTS.md. In-code builtins were retired; the seed file
+// lives at /data/AGENTS.md.
+export type AgentSource = 'global' | 'project';
 
 export interface Agent {
   id: string;
@@ -41,11 +44,20 @@ 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 {
+  agent_name: string;
+  reason: string;
 }
 
 export interface AgentsResponse {
   agents: Agent[];
-  parse_error: string | null;
+  errors: AgentParseError[];
 }
 
 export const CHAT_STATUSES = ['open', 'archived'] as const;
@@ -81,6 +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;
@@ -98,6 +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 {
@@ -175,6 +216,15 @@ export interface PaneUpdateRequest {
   position?: number;
 }
 
+// v1.8 mobile-tabs: shape returned by GET /api/projects/:id/git. Mirrors
+// services/git_meta.ts on the server. branch=null means "not a git repo".
+export interface GitMeta {
+  branch: string | null;
+  is_dirty: boolean;
+  ahead: number;
+  behind: number;
+}
+
 export type WorkspacePaneKind = 'chat' | 'terminal' | 'agent' | 'empty';
 
 export interface WorkspacePane {
@@ -208,7 +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 };

apps/web/src/components/AgentPicker.tsx

@@ -2,7 +2,7 @@ import { useEffect, useState } from 'react';
 import { Check, ChevronDown } from 'lucide-react';
 import { toast } from 'sonner';
 import { api } from '@/api/client';
-import type { Agent } from '@/api/types';
+import type { Agent, AgentParseError } from '@/api/types';
 import {
   DropdownMenu,
   DropdownMenuContent,
@@ -19,23 +19,28 @@ interface Props {
 
 export function AgentPicker({ projectId, value, onChange }: Props) {
   const [agents, setAgents] = useState<Agent[] | null>(null);
+  const [parseErrors, setParseErrors] = useState<AgentParseError[]>([]);
   const [error, setError] = useState<string | null>(null);
   const [open, setOpen] = useState(false);
 
-  // Load on mount (and on projectId change) so the trigger shows the agent
-  // name immediately, not the raw id. AGENTS.md parse errors surface as a
-  // toast once per load.
+  // v1.8.1: per-agent parse errors are non-blocking. Silent if any agents
+  // loaded successfully; a gray warning toast fires only when EVERY agent
+  // in AGENTS.md failed to parse. Server logs a console.warn either way.
   useEffect(() => {
     let cancelled = false;
     setAgents(null);
+    setParseErrors([]);
     setError(null);
     api.agents
       .list(projectId)
       .then((res) => {
         if (cancelled) return;
         setAgents(res.agents);
-        if (res.parse_error) {
-          toast.error(`AGENTS.md parse error: ${res.parse_error}`);
+        setParseErrors(res.errors);
+        if (res.errors.length > 0 && res.agents.length === 0) {
+          toast.warning(
+            `AGENTS.md: ${res.errors.length} agent${res.errors.length === 1 ? '' : 's'} failed to parse, none loaded`,
+          );
         }
       })
       .catch((err) => {
@@ -100,6 +105,14 @@ export function AgentPicker({ projectId, value, onChange }: Props) {
                 )}
               </DropdownMenuItem>
             ))}
+            {parseErrors.length > 0 && (
+              <div
+                className="px-2 py-1.5 mt-1 text-xs text-amber-500 border-t border-border"
+                title={parseErrors.map((e) => `${e.agent_name}: ${e.reason}`).join('\n')}
+              >
+                {parseErrors.length} agent{parseErrors.length === 1 ? '' : 's'} skipped
+              </div>
+            )}
           </>
         )}
       </DropdownMenuContent>

apps/web/src/components/BottomSheet.tsx

@@ -0,0 +1,92 @@
+import { useEffect, useRef, useState, type ReactNode, type TouchEvent } from 'react';
+import { cn } from '@/lib/utils';
+
+interface Props {
+  open: boolean;
+  onClose: () => void;
+  children: ReactNode;
+  title?: string;
+}
+
+// Past this drag distance, release dismisses the sheet.
+const SWIPE_DISMISS_THRESHOLD_PX = 80;
+
+export function BottomSheet({ open, onClose, children, title }: Props) {
+  const [dragY, setDragY] = useState(0);
+  const startYRef = useRef<number | null>(null);
+
+  useEffect(() => {
+    if (!open) return;
+    const onKey = (e: KeyboardEvent) => {
+      if (e.key === 'Escape') onClose();
+    };
+    window.addEventListener('keydown', onKey);
+    return () => window.removeEventListener('keydown', onKey);
+  }, [open, onClose]);
+
+  useEffect(() => {
+    if (!open) {
+      setDragY(0);
+      startYRef.current = null;
+    }
+  }, [open]);
+
+  function onTouchStart(e: TouchEvent<HTMLDivElement>) {
+    const t = e.touches[0];
+    if (!t) return;
+    startYRef.current = t.clientY;
+  }
+  function onTouchMove(e: TouchEvent<HTMLDivElement>) {
+    const t = e.touches[0];
+    if (!t || startYRef.current === null) return;
+    const dy = t.clientY - startYRef.current;
+    // Clamp to downward drags so the sheet doesn't "rubber-band" up.
+    if (dy > 0) setDragY(dy);
+  }
+  function onTouchEnd() {
+    if (dragY > SWIPE_DISMISS_THRESHOLD_PX) {
+      onClose();
+    } else {
+      setDragY(0);
+    }
+    startYRef.current = null;
+  }
+
+  if (!open) return null;
+
+  return (
+    <>
+      <div
+        className="fixed inset-0 z-40 bg-black/40"
+        onClick={onClose}
+        aria-hidden="true"
+      />
+      <div
+        role="dialog"
+        aria-modal="true"
+        className={cn(
+          'fixed inset-x-0 bottom-0 z-50 rounded-t-2xl border-t border-border bg-popover text-popover-foreground shadow-2xl',
+          'transition-transform duration-150 will-change-transform',
+          'max-h-[70vh] flex flex-col',
+        )}
+        style={{
+          transform: `translateY(${dragY}px)`,
+          paddingBottom: 'env(safe-area-inset-bottom)',
+        }}
+      >
+        <div
+          onTouchStart={onTouchStart}
+          onTouchMove={onTouchMove}
+          onTouchEnd={onTouchEnd}
+          className="flex flex-col items-center pt-2 pb-1 select-none touch-none"
+        >
+          <div className="w-10 h-1 bg-muted-foreground/40 rounded-full" />
+          {title && (
+            <div className="mt-1 text-sm font-medium text-muted-foreground">{title}</div>
+          )}
+        </div>
+        <div className="flex-1 overflow-y-auto">{children}</div>
+      </div>
+    </>
+  );
+}

apps/web/src/components/CapHitSentinel.tsx

@@ -0,0 +1,90 @@
+import { useState } from 'react';
+import { AlertCircle } from 'lucide-react';
+import { toast } from 'sonner';
+import { api } from '@/api/client';
+import type { Message } from '@/api/types';
+import { Button } from '@/components/ui/button';
+
+interface Props {
+  message: Message;
+  // 1-indexed position among cap-hit sentinels in this chat. The first
+  // cap-hit is 1, second is 2, third is 3 (hard ceiling).
+  capHitPosition: number;
+  // Only the most recent sentinel shows the Continue button. Older ones
+  // render text-only — they've already been continued past.
+  isLatest: boolean;
+}
+
+// Hard ceiling = 3 cap-hits per chat ⇒ 2 continues max. Lives here in sync
+// with insertCapHitSentinel's `canContinue = priorCount < 2` rule in
+// services/inference.ts.
+const MAX_CONTINUES = 2;
+
+export function CapHitSentinel({ message, capHitPosition, isLatest }: Props) {
+  const meta = message.metadata;
+  // Defensive parse — if the row is somehow missing metadata we still render
+  // the bare text rather than crashing the chat.
+  const isCapHit =
+    meta !== null && typeof meta === 'object' && meta.kind === 'cap_hit';
+
+  const limit = isCapHit ? meta.limit : null;
+  const canContinue = isCapHit ? meta.can_continue : false;
+  const agentName = isCapHit ? meta.agent_name : null;
+  // `capHitPosition` is 1-indexed; `MAX_CONTINUES - (position - 1)` is the
+  // number of continues remaining including this one. Clamped to ≥0.
+  const remaining = Math.max(0, MAX_CONTINUES - (capHitPosition - 1));
+
+  const [continuing, setContinuing] = useState(false);
+
+  async function handleContinue() {
+    if (continuing || !canContinue || !isLatest) return;
+    setContinuing(true);
+    try {
+      await api.chats.continue(message.chat_id, message.id);
+    } catch (err) {
+      toast.error(err instanceof Error ? err.message : 'continue failed');
+    } finally {
+      setContinuing(false);
+    }
+  }
+
+  // Tooltip wording from the v1.8.2 spec. Disabled state takes precedence —
+  // the spec text "Hard limit reached — start a new chat" matches what the
+  // server returns when canContinue is false.
+  const enabledTooltip = limit
+    ? `Resumes with a fresh budget of ${limit} tool calls. ${remaining} continue${remaining === 1 ? '' : 's'} remaining on this chat.`
+    : undefined;
+  const disabledTooltip = 'Hard limit reached — start a new chat';
+
+  return (
+    <div className="rounded-md border border-amber-500/40 bg-amber-500/10 text-sm">
+      <div className="px-3 py-2 flex items-start gap-2">
+        <AlertCircle className="size-4 text-amber-500 shrink-0 mt-0.5" />
+        <div className="flex-1 min-w-0 space-y-1">
+          <div className="text-xs font-medium text-amber-700 dark:text-amber-300">
+            {isCapHit && limit !== null
+              ? `Reached tool budget (${limit}/${limit})${agentName ? ` — ${agentName}` : ''}.`
+              : 'Reached tool budget.'}
+          </div>
+          <div className="text-xs text-muted-foreground">
+            {message.content}
+          </div>
+          {isLatest && (
+            <div className="pt-1">
+              <Button
+                type="button"
+                size="sm"
+                variant="outline"
+                onClick={() => void handleContinue()}
+                disabled={!canContinue || continuing}
+                title={canContinue ? enabledTooltip : disabledTooltip}
+              >
+                {continuing ? 'Continuing…' : 'Continue'}
+              </Button>
+            </div>
+          )}
+        </div>
+      </div>
+    </div>
+  );
+}

apps/web/src/components/ChatTabBar.tsx

@@ -1,6 +1,7 @@
 import { useState } from 'react';
 import { History, MessageSquare, Plus, X } from 'lucide-react';
 import type { Chat, WorkspacePane } from '@/api/types';
+import { StatusDot } from '@/components/StatusDot';
 import {
   ContextMenu,
   ContextMenuContent,
@@ -66,7 +67,7 @@ export function ChatTabBar({
   }
 
   return (
-    <div className="flex items-center border-b border-border bg-muted/20 h-8 shrink-0 overflow-x-auto">
+    <div className="flex items-center border-b border-border bg-muted/20 h-8 shrink-0 overflow-x-auto max-md:hidden">
       {tabs.map((chat, tabIdx) => {
         const isActive = tabIdx === pane.activeChatIdx;
         const isLast = tabIdx === tabs.length - 1;
@@ -91,6 +92,7 @@ export function ChatTabBar({
                 )}
               >
                 <MessageSquare size={12} className="shrink-0" />
+                <StatusDot chatId={chat.id} />
                 {renamingId === chat.id ? (
                   <input
                     autoFocus

apps/web/src/components/MessageBubble.tsx

@@ -4,10 +4,10 @@ import Markdown from 'react-markdown';
 import remarkGfm from 'remark-gfm';
 import { ChevronDown, ChevronRight, Copy, RefreshCw, Check, Share2, RotateCw, GitFork, Trash2 } from 'lucide-react';
 import { toast } from 'sonner';
-import type { Chat, Message } from '@/api/types';
+import type { Chat, ErrorReason, Message } from '@/api/types';
 import { api } from '@/api/client';
 import { sessionEvents } from '@/hooks/sessionEvents';
-import { ToolCallCard } from './ToolCallCard';
+import { CapHitSentinel } from './CapHitSentinel';
 import { CodeBlock } from './CodeBlock';
 import { Button } from '@/components/ui/button';
 import {
@@ -19,6 +19,15 @@ import {
   DialogTitle,
 } from '@/components/ui/dialog';
 
+// v1.8.2: human labels for the machine-readable error reasons that ride on
+// failed assistant messages via metadata.kind === 'error'. Kept short so the
+// inline render under "message failed" stays a single muted line.
+const ERROR_REASON_LABELS: Record<ErrorReason, string> = {
+  llm_provider_error: 'LLM provider error',
+  tool_execution_failed: 'Tool execution failed',
+  summary_after_cap_failed: 'Summary after tool budget hit failed',
+};
+
 // Match path-shaped substrings ending in `.ext`. Additionally require a `/`
 // in the match to reduce false positives in prose (e.g. plain `foo.ts` won't
 // match, but `src/foo.ts` will). False positives at the edges are accepted
@@ -94,6 +103,9 @@ function linkifyChildren(children: ReactNode, keyPrefix = 'l'): ReactNode {
 interface Props {
   message: Message;
   sessionChats?: Chat[];
+  // v1.8.2: passed by MessageList's render-item pass for cap-hit sentinels.
+  // Only the most recent sentinel shows the Continue button.
+  capHitInfo?: { position: number; isLatest: boolean };
 }
 
 function MarkdownBody({ content }: { content: string }) {
@@ -464,15 +476,34 @@ function CompactCard({ message, sessionChats }: { message: Message; sessionChats
   );
 }
 
-export function MessageBubble({ message, sessionChats }: Props) {
+export function MessageBubble({ message, sessionChats, capHitInfo }: Props) {
   if (message.kind === 'compact') {
     return <CompactCard message={message} sessionChats={sessionChats} />;
   }
 
-  if (message.role === 'tool') {
-    return <ToolCallCard message={message} />;
+  // v1.8.2: cap-hit sentinels render as a distinct system bubble with a
+  // Continue button. MessageList's pre-render pass tags each sentinel with
+  // its position; only the latest gets the actionable button.
+  if (
+    message.role === 'system' &&
+    message.metadata?.kind === 'cap_hit' &&
+    capHitInfo
+  ) {
+    return (
+      <CapHitSentinel
+        message={message}
+        capHitPosition={capHitInfo.position}
+        isLatest={capHitInfo.isLatest}
+      />
+    );
   }
 
+  // v1.8.2: tool messages and assistant tool_calls are now rendered by
+  // MessageList via ToolCallLine / ToolCallGroup. Tool-role messages reach
+  // this point only if MessageList didn't consume them (shouldn't happen,
+  // but guard against it by rendering nothing rather than a stale card).
+  if (message.role === 'tool') return null;
+
   if (message.role === 'user') {
     return (
       <div className="group flex flex-col items-end gap-1">
@@ -487,14 +518,17 @@ export function MessageBubble({ message, sessionChats }: Props) {
   const isStreaming = message.status === 'streaming';
   const failed = message.status === 'failed';
   const hasContent = message.content.length > 0;
-  const hasToolCalls = (message.tool_calls?.length ?? 0) > 0;
+  // v1.8.2: if metadata stamps an error reason, surface it inline under the
+  // generic "message failed" line. Keeps the user's eye where it already is
+  // rather than introducing a separate banner.
+  const errorMeta =
+    message.metadata !== null && message.metadata.kind === 'error'
+      ? message.metadata
+      : null;
 
   return (
     <div className="group flex flex-col gap-2">
-      {message.tool_calls?.map((tc) => (
-        <ToolCallCard key={tc.id} toolCall={tc} />
-      ))}
-      {(hasContent || (!hasToolCalls && isStreaming)) && (
+      {(hasContent || isStreaming) && (
         <div className="max-w-[90%] text-sm leading-relaxed space-y-2 break-words min-w-0">
           {hasContent ? <MarkdownBody content={message.content} /> : null}
           {isStreaming && (
@@ -503,12 +537,18 @@ export function MessageBubble({ message, sessionChats }: Props) {
         </div>
       )}
       {failed && (
-        <div className="text-xs text-destructive">message failed</div>
+        <div className="text-xs text-destructive">
+          message failed
+          {errorMeta && (
+            <span className="block text-muted-foreground mt-0.5">
+              {ERROR_REASON_LABELS[errorMeta.error_reason]}
+              {errorMeta.error_text ? ` — ${errorMeta.error_text}` : ''}
+            </span>
+          )}
+        </div>
       )}
       {!isStreaming && <StatsLine message={message} />}
-      {!isStreaming && (hasContent || hasToolCalls) && (
-        <ActionRow message={message} />
-      )}
+      {!isStreaming && hasContent && <ActionRow message={message} />}
     </div>
   );
 }

apps/web/src/components/MessageList.tsx

@@ -1,15 +1,128 @@
-import { useEffect, useRef } from 'react';
+import { useEffect, useMemo, useRef } from 'react';
 import type { Chat, Message } from '@/api/types';
 import { MessageBubble } from './MessageBubble';
+import { ToolCallGroup } from './ToolCallGroup';
+import { ToolCallLine, type ToolRun } from './ToolCallLine';
 
 interface Props {
   messages: Message[];
   sessionChats?: Chat[];
 }
 
+// v1.8.2: pre-render units. The single linear `messages` array gets walked
+// into a render-time list where each tool_call is a first-class item and
+// tool_result messages are folded onto their matching tool_run by id.
+type RenderItem =
+  | { kind: 'message'; message: Message; capHitInfo?: { position: number; isLatest: boolean } }
+  | { kind: 'tool_run'; run: ToolRun; key: string }
+  | { kind: 'tool_group'; runs: ToolRun[]; key: string };
+
+const GROUP_THRESHOLD = 3;
+
+function isCapHitSentinel(m: Message): boolean {
+  return m.role === 'system' && m.metadata?.kind === 'cap_hit';
+}
+
+// First pass: walk messages chronologically, expanding assistant tool_calls
+// into per-call run items and folding tool_result messages onto their
+// matching runs. Tool messages themselves never produce a render item.
+// Assistant messages produce a text render item only when they have text;
+// pure tool-call messages are "transparent" so consecutive tool runs can
+// still group across them.
+function flatten(messages: Message[]): RenderItem[] {
+  const items: RenderItem[] = [];
+  const runsByCallId = new Map<string, ToolRun>();
+
+  for (const m of messages) {
+    if (m.role === 'tool') {
+      if (m.tool_results) {
+        const run = runsByCallId.get(m.tool_results.tool_call_id);
+        if (run) run.result = m.tool_results;
+      }
+      continue;
+    }
+    const hasToolCalls = m.tool_calls != null && m.tool_calls.length > 0;
+    const hasText = m.content.length > 0;
+    if (m.role === 'assistant' && hasToolCalls) {
+      if (hasText || m.status === 'streaming') {
+        items.push({ kind: 'message', message: m });
+      }
+      for (const tc of m.tool_calls!) {
+        const run: ToolRun = { call: tc, result: null };
+        runsByCallId.set(tc.id, run);
+        items.push({ kind: 'tool_run', run, key: tc.id });
+      }
+      continue;
+    }
+    items.push({ kind: 'message', message: m });
+  }
+
+  return items;
+}
+
+// Second pass: collapse runs of >=GROUP_THRESHOLD consecutive tool_run items
+// of the same tool name into a single tool_group. Any other render item
+// (text bubble, sentinel, user message) breaks the chain.
+function group(items: RenderItem[]): RenderItem[] {
+  const out: RenderItem[] = [];
+  let i = 0;
+  while (i < items.length) {
+    const item = items[i]!;
+    if (item.kind !== 'tool_run') {
+      out.push(item);
+      i += 1;
+      continue;
+    }
+    const name = item.run.call.name;
+    let j = i + 1;
+    while (
+      j < items.length &&
+      items[j]!.kind === 'tool_run' &&
+      (items[j] as { kind: 'tool_run'; run: ToolRun }).run.call.name === name
+    ) {
+      j += 1;
+    }
+    const run = items.slice(i, j) as Array<{ kind: 'tool_run'; run: ToolRun; key: string }>;
+    if (run.length >= GROUP_THRESHOLD) {
+      out.push({
+        kind: 'tool_group',
+        runs: run.map((r) => r.run),
+        key: `group-${run[0]!.key}`,
+      });
+    } else {
+      for (const r of run) out.push(r);
+    }
+    i = j;
+  }
+  return out;
+}
+
+// Third pass: number cap-hit sentinels (1-indexed) and mark the latest.
+// CapHitSentinel uses position to compute the "N continues remaining"
+// tooltip, and isLatest to gate the Continue button (only the most recent
+// sentinel is actionable).
+function stampCapHits(items: RenderItem[]): RenderItem[] {
+  const totalCapHits = items.reduce(
+    (n, it) => n + (it.kind === 'message' && isCapHitSentinel(it.message) ? 1 : 0),
+    0,
+  );
+  if (totalCapHits === 0) return items;
+  let index = 0;
+  return items.map((it) => {
+    if (it.kind !== 'message' || !isCapHitSentinel(it.message)) return it;
+    index += 1;
+    return {
+      ...it,
+      capHitInfo: { position: index, isLatest: index === totalCapHits },
+    };
+  });
+}
+
 export function MessageList({ messages, sessionChats }: Props) {
   const endRef = useRef<HTMLDivElement>(null);
 
+  const renderItems = useMemo(() => stampCapHits(group(flatten(messages))), [messages]);
+
   useEffect(() => {
     endRef.current?.scrollIntoView({ block: 'end' });
   }, [messages]);
@@ -25,9 +138,22 @@ export function MessageList({ messages, sessionChats }: Props) {
   return (
     <div className="flex-1 overflow-y-auto">
       <div className="max-w-[1000px] mx-auto w-full px-6 py-4 space-y-4">
-        {messages.map((m) => (
-          <MessageBubble key={m.id} message={m} sessionChats={sessionChats} />
-        ))}
+        {renderItems.map((item) => {
+          if (item.kind === 'message') {
+            return (
+              <MessageBubble
+                key={item.message.id}
+                message={item.message}
+                sessionChats={sessionChats}
+                capHitInfo={item.capHitInfo}
+              />
+            );
+          }
+          if (item.kind === 'tool_run') {
+            return <ToolCallLine key={item.key} run={item.run} />;
+          }
+          return <ToolCallGroup key={item.key} runs={item.runs} />;
+        })}
         <div ref={endRef} />
       </div>
     </div>

apps/web/src/components/MobileTabSwitcher.tsx

@@ -0,0 +1,207 @@
+import { useState } from 'react';
+import {
+  Bot,
+  ChevronDown,
+  Edit2,
+  MessageSquare,
+  MoreHorizontal,
+  Terminal,
+  X,
+} from 'lucide-react';
+import { toast } from 'sonner';
+import type { Chat, WorkspacePane } from '@/api/types';
+import { BottomSheet } from '@/components/BottomSheet';
+import { StatusDot } from '@/components/StatusDot';
+import {
+  DropdownMenu,
+  DropdownMenuContent,
+  DropdownMenuItem,
+  DropdownMenuTrigger,
+} from '@/components/ui/dropdown-menu';
+import { useLongPress } from '@/hooks/useLongPress';
+import { cn } from '@/lib/utils';
+
+interface Props {
+  panes: WorkspacePane[];
+  activePaneIdx: number;
+  chats: Chat[];
+  onSwitchPane: (idx: number) => void;
+  onRemovePane: (idx: number) => void;
+  onRenameChat: (chatId: string, name: string) => Promise<void>;
+}
+
+function paneIcon(kind: WorkspacePane['kind']) {
+  if (kind === 'terminal') return <Terminal size={14} />;
+  if (kind === 'agent') return <Bot size={14} />;
+  return <MessageSquare size={14} />;
+}
+
+function paneActiveChatId(pane: WorkspacePane | undefined): string | null {
+  if (!pane) return null;
+  if (pane.chatId) return pane.chatId;
+  const idx = pane.activeChatIdx;
+  if (idx < 0 || idx >= pane.chatIds.length) return null;
+  return pane.chatIds[idx] ?? null;
+}
+
+function paneLabel(pane: WorkspacePane, chats: Chat[]): string {
+  const cid = paneActiveChatId(pane);
+  if (cid) {
+    const c = chats.find((x) => x.id === cid);
+    if (c) return c.name ?? 'New chat';
+  }
+  if (pane.kind === 'chat') return 'Chat';
+  if (pane.kind === 'terminal') return 'Terminal';
+  if (pane.kind === 'agent') return 'Agent';
+  return 'Empty';
+}
+
+export function MobileTabSwitcher({
+  panes,
+  activePaneIdx,
+  chats,
+  onSwitchPane,
+  onRemovePane,
+  onRenameChat,
+}: Props) {
+  const [open, setOpen] = useState(false);
+  const [renamingChatId, setRenamingChatId] = useState<string | null>(null);
+  const [renameValue, setRenameValue] = useState('');
+
+  const active = panes[activePaneIdx];
+  const activeLabel = active ? paneLabel(active, chats) : 'Empty';
+  const activeChatId = paneActiveChatId(active);
+
+  // Long-press mirrors ChatTabBar: synthesize a contextmenu event on the row
+  // so the trailing kebab's Radix DropdownMenu opens at the touch point.
+  const longPress = useLongPress(({ clientX, clientY, target }) => {
+    if (!target || !(target instanceof Element)) return;
+    const row = target.closest('[data-pane-id]') as HTMLElement | null;
+    if (!row) return;
+    const trigger = row.querySelector('[data-pane-kebab]') as HTMLElement | null;
+    if (trigger) {
+      trigger.click();
+      return;
+    }
+    row.dispatchEvent(
+      new MouseEvent('contextmenu', { bubbles: true, cancelable: true, clientX, clientY }),
+    );
+  });
+
+  function startRename(chatId: string, currentName: string | null) {
+    setRenamingChatId(chatId);
+    setRenameValue(currentName ?? '');
+  }
+  async function finishRename() {
+    if (renamingChatId && renameValue.trim()) {
+      try {
+        await onRenameChat(renamingChatId, renameValue.trim());
+      } catch (err) {
+        toast.error(err instanceof Error ? err.message : 'rename failed');
+      }
+    }
+    setRenamingChatId(null);
+  }
+
+  function handleSwitchPane(idx: number) {
+    onSwitchPane(idx);
+    setOpen(false);
+  }
+
+  return (
+    <>
+      <button
+        type="button"
+        onClick={() => setOpen(true)}
+        className="flex-1 inline-flex items-center gap-1.5 min-h-[44px] px-3 text-sm rounded-full bg-muted/40 hover:bg-muted/70 text-foreground min-w-0"
+        aria-label="Switch pane"
+      >
+        <span className="shrink-0 text-muted-foreground">{paneIcon(active?.kind ?? 'chat')}</span>
+        <StatusDot chatId={activeChatId} />
+        <span className="truncate flex-1 text-left">{activeLabel}</span>
+        <ChevronDown size={14} className="opacity-60 shrink-0" />
+      </button>
+
+      <BottomSheet open={open} onClose={() => setOpen(false)} title="Panes">
+        <ul className="px-2 py-2 space-y-1">
+          {panes.map((pane, idx) => {
+            const isActive = idx === activePaneIdx;
+            const cid = paneActiveChatId(pane);
+            const chat = cid ? chats.find((c) => c.id === cid) ?? null : null;
+            const label = paneLabel(pane, chats);
+            return (
+              <li
+                key={pane.id}
+                data-pane-id={pane.id}
+                onTouchStart={longPress.onTouchStart}
+                onTouchMove={longPress.onTouchMove}
+                onTouchEnd={longPress.onTouchEnd}
+                onTouchCancel={longPress.onTouchCancel}
+                onClick={() => handleSwitchPane(idx)}
+                style={{ WebkitTouchCallout: 'none' }}
+                className={cn(
+                  'flex items-center gap-2 px-3 py-2 rounded min-h-[48px] cursor-default select-none',
+                  isActive
+                    ? 'bg-accent/40 border-l-2 border-primary'
+                    : 'hover:bg-muted/50',
+                )}
+              >
+                <span className="shrink-0 text-muted-foreground">{paneIcon(pane.kind)}</span>
+                <StatusDot chatId={cid ?? null} />
+                {renamingChatId === cid && cid ? (
+                  <input
+                    autoFocus
+                    value={renameValue}
+                    onChange={(e) => setRenameValue(e.target.value)}
+                    onBlur={() => void finishRename()}
+                    onKeyDown={(e) => {
+                      if (e.key === 'Enter') void finishRename();
+                      if (e.key === 'Escape') setRenamingChatId(null);
+                    }}
+                    onClick={(e) => e.stopPropagation()}
+                    className="bg-transparent border-b border-border text-sm outline-none flex-1 min-w-0"
+                  />
+                ) : (
+                  <span className="truncate flex-1 text-sm">{label}</span>
+                )}
+                {isActive && (
+                  <span aria-hidden="true" className="text-primary text-xs shrink-0">
+                    ✓
+                  </span>
+                )}
+                <DropdownMenu>
+                  <DropdownMenuTrigger asChild>
+                    <button
+                      type="button"
+                      data-pane-kebab
+                      onClick={(e) => e.stopPropagation()}
+                      className="inline-flex items-center justify-center p-1 rounded text-muted-foreground hover:bg-muted hover:text-foreground min-h-[44px] min-w-[44px]"
+                      aria-label="Pane options"
+                    >
+                      <MoreHorizontal size={14} />
+                    </button>
+                  </DropdownMenuTrigger>
+                  <DropdownMenuContent align="end">
+                    {chat && (
+                      <DropdownMenuItem onSelect={() => startRename(chat.id, chat.name)}>
+                        <Edit2 size={14} /> Rename chat
+                      </DropdownMenuItem>
+                    )}
+                    <DropdownMenuItem
+                      disabled={panes.length <= 1}
+                      onSelect={() => onRemovePane(idx)}
+                    >
+                      <X size={14} /> Close pane
+                    </DropdownMenuItem>
+                  </DropdownMenuContent>
+                </DropdownMenu>
+              </li>
+            );
+          })}
+        </ul>
+        {/* v1.8: New-pane button moved out of the sheet to the header row 2
+            (see NewPaneMenu). Sheet is for switching only. */}
+      </BottomSheet>
+    </>
+  );
+}

apps/web/src/components/NewPaneMenu.tsx

@@ -0,0 +1,44 @@
+import { Bot, MessageSquare, Plus, Terminal } from 'lucide-react';
+import {
+  DropdownMenu,
+  DropdownMenuContent,
+  DropdownMenuItem,
+  DropdownMenuTrigger,
+} from '@/components/ui/dropdown-menu';
+
+interface Props {
+  onAddPane: (kind: 'chat' | 'terminal' | 'agent') => void;
+  disabled?: boolean;
+}
+
+// v1.8 row-2 right cluster: mirrors the desktop Workspace.tsx Split dropdown.
+// Terminal and Agent items pass through to addSplitPane which already shows
+// "coming soon" toasts; rendering them here matches the Batch 3 workspace
+// model so the UI is forward-compatible with BooTerm/BooCoder.
+export function NewPaneMenu({ onAddPane, disabled }: Props) {
+  return (
+    <DropdownMenu>
+      <DropdownMenuTrigger asChild>
+        <button
+          type="button"
+          disabled={disabled}
+          className="inline-flex items-center justify-center min-h-[44px] min-w-[44px] rounded-full bg-muted/40 hover:bg-muted/70 text-foreground disabled:opacity-40 disabled:cursor-not-allowed shrink-0"
+          aria-label="New pane"
+        >
+          <Plus size={16} />
+        </button>
+      </DropdownMenuTrigger>
+      <DropdownMenuContent align="end">
+        <DropdownMenuItem onSelect={() => onAddPane('chat')}>
+          <MessageSquare size={14} /> New chat
+        </DropdownMenuItem>
+        <DropdownMenuItem onSelect={() => onAddPane('terminal')}>
+          <Terminal size={14} /> New terminal
+        </DropdownMenuItem>
+        <DropdownMenuItem onSelect={() => onAddPane('agent')}>
+          <Bot size={14} /> New agent
+        </DropdownMenuItem>
+      </DropdownMenuContent>
+    </DropdownMenu>
+  );
+}

apps/web/src/components/StatusDot.tsx

@@ -0,0 +1,36 @@
+import { useChatStatus, type DerivedStatus } from '@/hooks/useChatStatus';
+import { cn } from '@/lib/utils';
+
+interface Props {
+  chatId: string | null | undefined;
+  className?: string;
+}
+
+const STATUS_CLASS: Record<DerivedStatus, string> = {
+  working: 'bg-amber-500 animate-pulse',
+  idle_warm: 'bg-emerald-500',
+  idle_cold: 'bg-muted-foreground/40',
+  error: 'bg-destructive',
+};
+
+const STATUS_LABEL: Record<DerivedStatus, string> = {
+  working: 'working',
+  idle_warm: 'idle',
+  idle_cold: 'idle',
+  error: 'error',
+};
+
+export function StatusDot({ chatId, className }: Props) {
+  const status = useChatStatus(chatId);
+  return (
+    <span
+      aria-label={`Status: ${STATUS_LABEL[status]}`}
+      title={STATUS_LABEL[status]}
+      className={cn(
+        'inline-block w-1.5 h-1.5 rounded-full shrink-0',
+        STATUS_CLASS[status],
+        className,
+      )}
+    />
+  );
+}

apps/web/src/components/ToolCallCard.tsx

@@ -1,102 +0,0 @@
-import { useState } from 'react';
-import type { ReactNode } from 'react';
-import { ChevronRight, Wrench } from 'lucide-react';
-import type { Message, ToolCall } from '@/api/types';
-import { sessionEvents } from '@/hooks/sessionEvents';
-
-interface Props {
-  message?: Message;
-  toolCall?: ToolCall;
-}
-
-// Same regex/heuristic as MessageBubble: paths ending in `.ext` with at
-// least one `/`. Linkifies file paths emitted by tools like grep / find_files
-// so they're clickable.
-const PATH_REGEX = /([a-zA-Z0-9._/-]+\.[a-zA-Z0-9]+)/g;
-
-function linkifyOutput(text: string): ReactNode[] {
-  const out: ReactNode[] = [];
-  let lastIdx = 0;
-  let idx = 0;
-  for (const match of text.matchAll(PATH_REGEX)) {
-    const matchedText = match[0];
-    const start = match.index ?? 0;
-    if (!matchedText.includes('/')) continue;
-    if (start > lastIdx) out.push(text.slice(lastIdx, start));
-    out.push(
-      <button
-        key={idx}
-        type="button"
-        onClick={() =>
-          sessionEvents.emit({
-            type: 'open_file_in_browser',
-            path: matchedText,
-          })
-        }
-        className="text-primary underline cursor-pointer hover:text-primary/80"
-      >
-        {matchedText}
-      </button>
-    );
-    lastIdx = start + matchedText.length;
-    idx += 1;
-  }
-  if (lastIdx < text.length) out.push(text.slice(lastIdx));
-  return out.length > 0 ? out : [text];
-}
-
-export function ToolCallCard({ message, toolCall }: Props) {
-  const [open, setOpen] = useState(false);
-  const tc = toolCall ?? message?.tool_calls?.[0];
-  const result = message?.tool_results;
-
-  const name = tc?.name ?? 'tool';
-  const args = tc?.args ?? {};
-  const error = result?.error;
-  const output = result?.output;
-  const truncated = result?.truncated;
-
-  return (
-    <div className="rounded-md border border-border bg-muted/30 text-sm overflow-hidden">
-      <button
-        type="button"
-        onClick={() => setOpen((v) => !v)}
-        className="w-full flex items-center gap-2 px-2.5 py-1.5 hover:bg-muted/60 text-left"
-      >
-        <ChevronRight
-          className={`size-3.5 transition-transform ${open ? 'rotate-90' : ''}`}
-        />
-        <Wrench className="size-3.5 opacity-70" />
-        <span className="font-mono font-medium">{name}</span>
-        <span className="font-mono text-xs text-muted-foreground truncate min-w-0 flex-1">
-          {JSON.stringify(args)}
-        </span>
-        {error && (
-          <span className="text-xs text-destructive font-medium ml-2">error</span>
-        )}
-        {truncated && (
-          <span className="text-xs text-muted-foreground ml-2">truncated</span>
-        )}
-      </button>
-      {open && (
-        <div className="px-2.5 py-2 border-t bg-background/40">
-          {error ? (
-            <pre className="text-xs text-destructive font-mono whitespace-pre-wrap">
-              {error}
-            </pre>
-          ) : output !== undefined ? (
-            <pre className="text-xs font-mono whitespace-pre-wrap overflow-x-auto max-h-72 overflow-y-auto">
-              {linkifyOutput(
-                typeof output === 'string'
-                  ? output
-                  : JSON.stringify(output, null, 2)
-              )}
-            </pre>
-          ) : (
-            <div className="text-xs text-muted-foreground">no result yet</div>
-          )}
-        </div>
-      )}
-    </div>
-  );
-}

apps/web/src/components/ToolCallGroup.tsx

@@ -0,0 +1,64 @@
+import { useState } from 'react';
+import { ChevronRight } from 'lucide-react';
+import { ToolCallLine, runStatus, type ToolRun } from './ToolCallLine';
+
+interface Props {
+  // All runs must share the same tool name. Caller (MessageList grouping
+  // pass) enforces that invariant.
+  runs: ToolRun[];
+}
+
+export function ToolCallGroup({ runs }: Props) {
+  const [open, setOpen] = useState(false);
+  if (runs.length === 0) return null;
+  const toolName = runs[0]!.call.name;
+  const count = runs.length;
+
+  // Group-level status: pending if any are still running, error if any
+  // finished with an error, otherwise success. Matches the visual the user
+  // gets when scanning a long run of greps / view_files.
+  let pending = 0;
+  let errored = 0;
+  for (const r of runs) {
+    const s = runStatus(r);
+    if (s === 'pending') pending += 1;
+    else if (s === 'error') errored += 1;
+  }
+  const summaryParts: string[] = [];
+  if (pending > 0) summaryParts.push(`${pending} running`);
+  if (errored > 0) summaryParts.push(`${errored} failed`);
+  const summary = summaryParts.length > 0 ? ` (${summaryParts.join(', ')})` : '';
+
+  return (
+    <div className="rounded border border-border/60 bg-muted/20 text-xs">
+      <button
+        type="button"
+        onClick={() => setOpen((v) => !v)}
+        className="w-full flex items-center gap-1.5 px-2 py-1 hover:bg-muted/40 text-left"
+      >
+        <ChevronRight
+          className={`size-3 text-muted-foreground/60 shrink-0 transition-transform ${open ? 'rotate-90' : ''}`}
+        />
+        <span className="text-muted-foreground/60 select-none shrink-0">⊞</span>
+        <span className="font-mono text-foreground/90">
+          {count} {toolName} call{count === 1 ? '' : 's'}
+        </span>
+        {summary && (
+          <span className="text-muted-foreground truncate">{summary}</span>
+        )}
+        <span className="ml-auto text-muted-foreground/60 shrink-0">tap</span>
+      </button>
+      {open && (
+        <div className="border-t border-border/40 px-2 py-1 space-y-0.5">
+          {runs.map((run, i) => (
+            <ToolCallLine
+              key={`${run.call.id}-${i}`}
+              run={run}
+              insideGroup
+            />
+          ))}
+        </div>
+      )}
+    </div>
+  );
+}

apps/web/src/components/ToolCallLine.tsx

@@ -0,0 +1,167 @@
+import { useState } from 'react';
+import type { ReactNode } from 'react';
+import { Check, ChevronRight, Loader2, X } from 'lucide-react';
+import type { ToolCall, ToolResult } from '@/api/types';
+import { sessionEvents } from '@/hooks/sessionEvents';
+
+// v1.8.2: cap on the inline arg-summary length. Expanded view shows full
+// args + full result, so this is purely a single-line render budget.
+const ARG_SUMMARY_MAX = 60;
+
+export interface ToolRun {
+  call: ToolCall;
+  // null while the call is in flight or the matching tool result hasn't
+  // arrived yet on the WS stream.
+  result: ToolResult | null;
+}
+
+function truncate(s: string, n: number): string {
+  return s.length > n ? s.slice(0, n - 1) + '…' : s;
+}
+
+// Per-tool argument summary mapping from the v1.8.2 spec. Goal is a single
+// scannable line that surfaces the *what* (path / pattern) without
+// overwhelming the chat with full JSON.
+export function formatToolArgs(name: string, args: Record<string, unknown>): string {
+  if (name === 'view_file') {
+    const path = String(args.path ?? '');
+    const start = args.start_line;
+    const end = args.end_line;
+    if (typeof start === 'number' && typeof end === 'number') {
+      return truncate(`${path}:${start}-${end}`, ARG_SUMMARY_MAX);
+    }
+    if (typeof start === 'number') {
+      return truncate(`${path}:${start}`, ARG_SUMMARY_MAX);
+    }
+    return truncate(path, ARG_SUMMARY_MAX);
+  }
+  if (name === 'list_dir') {
+    return truncate(String(args.path ?? '.'), ARG_SUMMARY_MAX);
+  }
+  if (name === 'grep') {
+    const pattern = String(args.pattern ?? '');
+    const path = args.path ? ` ${String(args.path)}` : '';
+    return truncate(`"${pattern}"${path}`, ARG_SUMMARY_MAX);
+  }
+  if (name === 'find_files') {
+    return truncate(String(args.pattern ?? ''), ARG_SUMMARY_MAX);
+  }
+  if (name === 'git_status') {
+    return '';
+  }
+  // Unknown tool — surface first arg value or the literal {} so the user can
+  // see something happened. Forward-compatible with future tools.
+  const keys = Object.keys(args);
+  if (keys.length === 0) return '{}';
+  const first = keys[0]!;
+  return truncate(`${first}: ${String(args[first])}`, ARG_SUMMARY_MAX);
+}
+
+export function runStatus(run: ToolRun): 'pending' | 'success' | 'error' {
+  if (run.result === null) return 'pending';
+  if (run.result.error) return 'error';
+  return 'success';
+}
+
+// Path-shaped paths in tool output text get a click handler so users can
+// jump to the file. Same heuristic as MessageBubble.linkifyPaths.
+const PATH_REGEX = /([a-zA-Z0-9._/-]+\.[a-zA-Z0-9]+)/g;
+function linkifyOutput(text: string): ReactNode[] {
+  const out: ReactNode[] = [];
+  let lastIdx = 0;
+  let idx = 0;
+  for (const match of text.matchAll(PATH_REGEX)) {
+    const matchedText = match[0];
+    const start = match.index ?? 0;
+    if (!matchedText.includes('/')) continue;
+    if (start > lastIdx) out.push(text.slice(lastIdx, start));
+    out.push(
+      <button
+        key={idx}
+        type="button"
+        onClick={() =>
+          sessionEvents.emit({ type: 'open_file_in_browser', path: matchedText })
+        }
+        className="text-primary underline cursor-pointer hover:text-primary/80"
+      >
+        {matchedText}
+      </button>
+    );
+    lastIdx = start + matchedText.length;
+    idx += 1;
+  }
+  if (lastIdx < text.length) out.push(text.slice(lastIdx));
+  return out.length > 0 ? out : [text];
+}
+
+interface Props {
+  run: ToolRun;
+  // When rendered inside a ToolCallGroup the line is already nested under a
+  // shared header, so the leading arrow is dropped to avoid double indent.
+  insideGroup?: boolean;
+}
+
+export function ToolCallLine({ run, insideGroup }: Props) {
+  const [open, setOpen] = useState(false);
+  const status = runStatus(run);
+  const args = run.call.args ?? {};
+  const summary = formatToolArgs(run.call.name, args);
+
+  return (
+    <div className="text-xs">
+      <button
+        type="button"
+        onClick={() => setOpen((v) => !v)}
+        className="flex items-center gap-1.5 w-full text-left hover:bg-muted/40 rounded px-1 py-0.5 -mx-1"
+      >
+        {!insideGroup && (
+          <span className="text-muted-foreground/60 select-none shrink-0">↳</span>
+        )}
+        <ChevronRight
+          className={`size-3 text-muted-foreground/60 shrink-0 transition-transform ${open ? 'rotate-90' : ''}`}
+        />
+        <span className="font-mono text-foreground/90 shrink-0">{run.call.name}</span>
+        {summary && (
+          <span className="font-mono text-muted-foreground truncate min-w-0 flex-1">
+            {summary}
+          </span>
+        )}
+        {!summary && <span className="flex-1" />}
+        <span className="shrink-0 ml-1">
+          {status === 'pending' && (
+            <Loader2 className="size-3 text-muted-foreground animate-spin" aria-label="running" />
+          )}
+          {status === 'success' && (
+            <Check className="size-3 text-emerald-500" aria-label="success" />
+          )}
+          {status === 'error' && (
+            <X className="size-3 text-destructive" aria-label="error" />
+          )}
+        </span>
+      </button>
+      {open && (
+        <div className="ml-5 mt-1 mb-1 space-y-1">
+          <pre className="text-[10px] text-muted-foreground font-mono whitespace-pre-wrap break-all bg-muted/30 rounded px-2 py-1">
+            {JSON.stringify(args, null, 2)}
+          </pre>
+          {run.result && (
+            <pre className="text-[11px] font-mono whitespace-pre-wrap bg-muted/30 rounded px-2 py-1 max-h-72 overflow-y-auto">
+              {run.result.error ? (
+                <span className="text-destructive">{run.result.error}</span>
+              ) : (
+                linkifyOutput(
+                  typeof run.result.output === 'string'
+                    ? run.result.output
+                    : JSON.stringify(run.result.output, null, 2)
+                )
+              )}
+              {run.result.truncated && (
+                <div className="text-muted-foreground/60 mt-1">— output truncated —</div>
+              )}
+            </pre>
+          )}
+        </div>
+      )}
+    </div>
+  );
+}

apps/web/src/components/Workspace.tsx

@@ -1,14 +1,11 @@
-import { useCallback, useEffect } from 'react';
-import { useLocation, useNavigate, useSearchParams } from 'react-router-dom';
 import { PanelRight, MessageSquare, Terminal, Bot } from 'lucide-react';
 import type { Chat, WorkspacePane } from '@/api/types';
-import { useWorkspacePanes, MAX_PANES } from '@/hooks/useWorkspacePanes';
-import { useSessionChats } from '@/hooks/useSessionChats';
+import { MAX_PANES, type UseWorkspacePanesResult } from '@/hooks/useWorkspacePanes';
+import type { UseSessionChatsResult } from '@/hooks/useSessionChats';
 import { useViewport } from '@/hooks/useViewport';
 import { ChatPane } from '@/components/panes/ChatPane';
 import { ChatTabBar } from '@/components/ChatTabBar';
 import { SessionLandingPage } from '@/components/SessionLandingPage';
-import { SwipeablePaneTab } from '@/components/SwipeablePaneTab';
 import {
   DropdownMenu,
   DropdownMenuContent,
@@ -23,14 +20,24 @@ interface Props {
   // Batch 9: threaded down to ChatPane → ChatInput → AgentPicker.
   agentId?: string | null;
   onAgentChange?: (agentId: string | null) => void | Promise<void>;
+  // v1.8: panes + chats hoisted into Session.tsx so the mobile header pill
+  // (MobileTabSwitcher) can share state with the pane grid.
+  panesHook: UseWorkspacePanesResult;
+  chatsHook: UseSessionChatsResult;
 }
 
-export function Workspace({ sessionId, projectId, agentId, onAgentChange }: Props) {
+export function Workspace({
+  sessionId,
+  projectId,
+  agentId,
+  onAgentChange,
+  panesHook,
+  chatsHook,
+}: Props) {
   const {
     panes,
     activePaneIdx,
     setActivePaneIdx,
-    activePaneIdxRef,
     openChatInPane,
     switchTab,
     removeTab,
@@ -40,8 +47,6 @@ export function Workspace({ sessionId, projectId, agentId, onAgentChange }: Prop
     showLandingPage,
     addSplitPane,
     removePane,
-    removeChatFromPanes,
-    initializeFirstChatIfEmpty,
     handlePaneDragStart,
     handlePaneDragOver,
     handlePaneDragLeave,
@@ -49,15 +54,7 @@ export function Workspace({ sessionId, projectId, agentId, onAgentChange }: Prop
     handlePaneDragEnd,
     dragOverIdx,
     draggingIdxRef,
-  } = useWorkspacePanes(sessionId);
-
-  // Thin wrapper so useSessionChats can route open_chat_in_active_pane events
-  // without knowing about pane indexing.
-  const openChatInActivePane = useCallback(
-    (chatId: string) => openChatInPane(activePaneIdxRef.current, chatId),
-    [openChatInPane, activePaneIdxRef],
-  );
-
+  } = panesHook;
   const {
     chats,
     createChat,
@@ -66,47 +63,9 @@ export function Workspace({ sessionId, projectId, agentId, onAgentChange }: Prop
     deleteChat,
     renameChat,
     handleLandingSend,
-  } = useSessionChats(sessionId, {
-    removeChatFromPanes,
-    openChatInPane,
-    openChatInActivePane,
-    initializeFirstChatIfEmpty,
-  });
+  } = chatsHook;
 
   const { isMobile } = useViewport();
-  const [searchParams] = useSearchParams();
-  const navigate = useNavigate();
-  const location = useLocation();
-
-  // URL -> state (mobile only). Handles deep-link arrival and Back button
-  // history pops. On a bare URL (no ?pane), reset to first pane so Back
-  // from a ?pane URL returns the user to a sensible default.
-  useEffect(() => {
-    if (!isMobile || panes.length === 0) return;
-    const paneId = searchParams.get('pane');
-    if (!paneId) {
-      if (activePaneIdx !== 0) setActivePaneIdx(0);
-      return;
-    }
-    const idx = panes.findIndex((p) => p.id === paneId);
-    if (idx >= 0 && idx !== activePaneIdx) setActivePaneIdx(idx);
-  }, [isMobile, searchParams, panes, activePaneIdx, setActivePaneIdx]);
-
-  // Switch active pane and push URL (mobile only). User-initiated only;
-  // never called from URL-sync effect.
-  const switchActivePane = useCallback(
-    (idx: number) => {
-      setActivePaneIdx(idx);
-      if (isMobile) {
-        const pane = panes[idx];
-        if (!pane) return;
-        const params = new URLSearchParams(location.search);
-        params.set('pane', pane.id);
-        navigate(`${location.pathname}?${params.toString()}`);
-      }
-    },
-    [setActivePaneIdx, isMobile, panes, navigate, location.pathname, location.search],
-  );
 
   function chatsForPane(pane: WorkspacePane): Chat[] {
     return pane.chatIds
@@ -114,18 +73,6 @@ export function Workspace({ sessionId, projectId, agentId, onAgentChange }: Prop
       .filter((c): c is Chat => c !== undefined);
   }
 
-  function paneLabel(pane: WorkspacePane): string {
-    const activeChatId = pane.chatId;
-    if (activeChatId) {
-      const chat = chats.find((c) => c.id === activeChatId);
-      if (chat) return chat.name ?? 'New chat';
-    }
-    if (pane.kind === 'chat') return 'Chat';
-    if (pane.kind === 'terminal') return 'Terminal';
-    if (pane.kind === 'agent') return 'Agent';
-    return 'Empty';
-  }
-
   return (
     <div className="flex flex-col h-full min-h-0">
       {!isMobile && (
@@ -159,20 +106,8 @@ export function Workspace({ sessionId, projectId, agentId, onAgentChange }: Prop
         </div>
       )}
 
-      {isMobile && panes.length > 1 && (
-        <div className="flex items-center gap-1 overflow-x-auto border-b border-border bg-muted/10 px-2 py-1 shrink-0">
-          {panes.map((pane, idx) => (
-            <SwipeablePaneTab
-              key={pane.id}
-              label={paneLabel(pane)}
-              isActive={idx === activePaneIdx}
-              onTap={() => switchActivePane(idx)}
-              onClose={() => removePane(idx)}
-              canClose={panes.length > 1}
-            />
-          ))}
-        </div>
-      )}
+      {/* v1.8: mobile multi-pane SwipeablePaneTab strip removed; the header
+          pill (MobileTabSwitcher) is the mobile pane switcher. */}
 
       <div
         className={cn('flex-1 min-h-0', isMobile ? 'flex' : 'grid')}
@@ -205,19 +140,24 @@ export function Workspace({ sessionId, projectId, agentId, onAgentChange }: Prop
               onDragStart={!isMobile && panes.length > 1 ? handlePaneDragStart(idx) : undefined}
               onDragEnd={!isMobile && panes.length > 1 ? handlePaneDragEnd : undefined}
             >
-              <ChatTabBar
-                pane={pane}
-                tabs={chatsForPane(pane)}
-                onSwitchTab={(tabIdx) => switchTab(idx, tabIdx)}
-                onRemoveTab={(chatId) => removeTab(idx, chatId)}
-                onCloseOthers={(chatId) => closeOtherTabs(idx, chatId)}
-                onCloseToRight={(chatId) => closeTabsToRight(idx, chatId)}
-                onCloseAll={() => closeAllTabs(idx)}
-                onNewChat={() => void createChat(idx)}
-                onShowHistory={() => showLandingPage(idx)}
-                onRename={renameChat}
-                onRemovePane={panes.length > 1 ? () => removePane(idx) : undefined}
-              />
+              {/* Hidden on mobile per v1.8: chat-within-pane navigation
+                  is not exposed on small screens; users switch panes via
+                  the header pill instead. */}
+              {!isMobile && (
+                <ChatTabBar
+                  pane={pane}
+                  tabs={chatsForPane(pane)}
+                  onSwitchTab={(tabIdx) => switchTab(idx, tabIdx)}
+                  onRemoveTab={(chatId) => removeTab(idx, chatId)}
+                  onCloseOthers={(chatId) => closeOtherTabs(idx, chatId)}
+                  onCloseToRight={(chatId) => closeTabsToRight(idx, chatId)}
+                  onCloseAll={() => closeAllTabs(idx)}
+                  onNewChat={() => void createChat(idx)}
+                  onShowHistory={() => showLandingPage(idx)}
+                  onRename={renameChat}
+                  onRemovePane={panes.length > 1 ? () => removePane(idx) : undefined}
+                />
+              )}
             </div>
 
             <div className="flex-1 min-h-0 overflow-hidden">

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 {
@@ -115,6 +115,19 @@ export interface ProjectUpdatedEvent {
   name: string;
 }
 
+// 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 =
   | SessionRenamedEvent
   | ProjectCreatedEvent
@@ -134,7 +147,8 @@ export type SessionEvent =
   | ChatDeletedEvent
   | ProjectArchivedEvent
   | ProjectUnarchivedEvent
-  | ProjectUpdatedEvent;
+  | ProjectUpdatedEvent
+  | ChatStatusEvent;
 type Listener = (event: SessionEvent) => void;
 
 const listeners = new Set<Listener>();

apps/web/src/hooks/useChatStatus.ts

@@ -0,0 +1,71 @@
+import { useEffect, useState } from 'react';
+import { sessionEvents } from './sessionEvents';
+
+export type RawStatus = 'working' | 'idle' | 'error';
+export type DerivedStatus = 'working' | 'idle_warm' | 'idle_cold' | 'error';
+
+// Window during which an idle dot stays green; after this, it fades to gray.
+const WARM_WINDOW_MS = 30_000;
+const TICK_MS = 5_000;
+
+interface Entry {
+  status: RawStatus;
+  at: string;
+}
+
+// Module-scope shared state so every StatusDot in the app shares one map
+// (mirrors useSidebar's singleton pattern). The map is ephemeral — cleared on
+// page reload; WS reconnect repopulates as new frames arrive.
+const statuses = new Map<string, Entry>();
+const subscribers = new Set<() => void>();
+
+function notify(): void {
+  for (const s of subscribers) {
+    try { s(); } catch { /* swallow */ }
+  }
+}
+
+// Guard against duplicate listeners during Vite HMR.
+const G = globalThis as Record<string, unknown>;
+if (!G.__boocode_chat_status_subscribed) {
+  G.__boocode_chat_status_subscribed = true;
+  sessionEvents.subscribe((ev) => {
+    if (ev.type !== 'chat_status') return;
+    statuses.set(ev.chat_id, { status: ev.status, at: ev.at });
+    notify();
+  });
+  // Single shared ticker: re-notify so any green dot whose 30s window just
+  // expired re-renders as gray. We only notify if there's something warm —
+  // avoids waking sleeping components for nothing.
+  setInterval(() => {
+    const now = Date.now();
+    for (const entry of statuses.values()) {
+      if (entry.status === 'idle') {
+        const age = now - new Date(entry.at).getTime();
+        if (age < WARM_WINDOW_MS + TICK_MS) {
+          notify();
+          return;
+        }
+      }
+    }
+  }, TICK_MS);
+}
+
+function derive(entry: Entry | undefined): DerivedStatus {
+  if (!entry) return 'idle_cold';
+  if (entry.status === 'working') return 'working';
+  if (entry.status === 'error') return 'error';
+  const age = Date.now() - new Date(entry.at).getTime();
+  return age < WARM_WINDOW_MS ? 'idle_warm' : 'idle_cold';
+}
+
+export function useChatStatus(chatId: string | null | undefined): DerivedStatus {
+  const [, force] = useState({});
+  useEffect(() => {
+    const sub = () => force({});
+    subscribers.add(sub);
+    return () => { subscribers.delete(sub); };
+  }, []);
+  if (!chatId) return 'idle_cold';
+  return derive(statuses.get(chatId));
+}

apps/web/src/hooks/useProjectGit.ts

@@ -0,0 +1,41 @@
+import { useEffect, useState } from 'react';
+import { api } from '@/api/client';
+import type { GitMeta } from '@/api/types';
+
+const POLL_INTERVAL_MS = 30_000;
+
+// Live-ish git meta for the project header indicator. Backed by the server's
+// 30s cache, so a 30s client poll plus the cache TTL bounds total staleness
+// to ~60s in the worst case. Returns null while the first fetch is in flight
+// or if the request failed.
+export function useProjectGit(projectId: string | null | undefined): GitMeta | null {
+  const [meta, setMeta] = useState<GitMeta | null>(null);
+
+  useEffect(() => {
+    if (!projectId) {
+      setMeta(null);
+      return;
+    }
+    let cancelled = false;
+
+    const fetchOnce = () => {
+      api.projects
+        .git(projectId)
+        .then((m) => {
+          if (!cancelled) setMeta(m);
+        })
+        .catch(() => {
+          if (!cancelled) setMeta(null);
+        });
+    };
+
+    fetchOnce();
+    const t = setInterval(fetchOnce, POLL_INTERVAL_MS);
+    return () => {
+      cancelled = true;
+      clearInterval(t);
+    };
+  }, [projectId]);
+
+  return meta;
+}

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 };
@@ -143,6 +164,11 @@ function applyFrame(state: State, frame: WsFrame): State {
   }
 }
 
+// Matches useUserEvents — exponential backoff with the same ceiling so the
+// two channels reconnect on the same cadence after a network handoff.
+const RECONNECT_INITIAL_MS = 1000;
+const RECONNECT_MAX_MS = 30_000;
+
 export function useSessionStream(sessionId: string | undefined) {
   const [state, setState] = useState<State>({ messages: [], connected: false, error: null });
   const wsRef = useRef<WebSocket | null>(null);
@@ -152,32 +178,52 @@ export function useSessionStream(sessionId: string | undefined) {
 
     setState({ messages: [], connected: false, error: null });
 
-    const proto = window.location.protocol === 'https:' ? 'wss' : 'ws';
-    const url = `${proto}://${window.location.host}/api/ws/sessions/${sessionId}`;
-    const ws = new WebSocket(url);
-    wsRef.current = ws;
+    let unmounted = false;
+    let reconnectTimer: ReturnType<typeof setTimeout> | null = null;
+    let reconnectDelay = RECONNECT_INITIAL_MS;
 
-    ws.onopen = () => {
-      setState((s) => ({ ...s, connected: true, error: null }));
-    };
-    ws.onmessage = (ev) => {
-      try {
-        const frame = JSON.parse(typeof ev.data === 'string' ? ev.data : '') as WsFrame;
-        setState((s) => applyFrame(s, frame));
-      } catch (err) {
-        console.warn('bad ws frame', err);
-      }
-    };
-    ws.onerror = () => {
-      setState((s) => ({ ...s, error: 'websocket error' }));
-    };
-    ws.onclose = () => {
-      setState((s) => ({ ...s, connected: false }));
+    const connect = () => {
+      if (unmounted) return;
+      const proto = window.location.protocol === 'https:' ? 'wss' : 'ws';
+      const url = `${proto}://${window.location.host}/api/ws/sessions/${sessionId}`;
+      const ws = new WebSocket(url);
+      wsRef.current = ws;
+
+      ws.onopen = () => {
+        reconnectDelay = RECONNECT_INITIAL_MS;
+        setState((s) => ({ ...s, connected: true, error: null }));
+      };
+      ws.onmessage = (ev) => {
+        try {
+          const frame = JSON.parse(typeof ev.data === 'string' ? ev.data : '') as WsFrame;
+          setState((s) => applyFrame(s, frame));
+        } catch (err) {
+          console.warn('bad ws frame', err);
+        }
+      };
+      // v1.8.1: WS errors no longer surface as user-facing toasts here. The
+      // user-channel hook (useUserEvents) owns the debounced "reconnecting…"
+      // UI; this channel just reconnects silently on the same backoff.
+      ws.onerror = () => {
+        try { ws.close(); } catch {}
+      };
+      ws.onclose = () => {
+        if (unmounted) return;
+        setState((s) => ({ ...s, connected: false }));
+        const delay = reconnectDelay;
+        reconnectDelay = Math.min(reconnectDelay * 2, RECONNECT_MAX_MS);
+        reconnectTimer = setTimeout(connect, delay);
+      };
     };
 
+    connect();
+
     return () => {
+      unmounted = true;
+      if (reconnectTimer) clearTimeout(reconnectTimer);
+      const ws = wsRef.current;
       wsRef.current = null;
-      ws.close();
+      if (ws) try { ws.close(); } catch {}
     };
   }, [sessionId]);
 

apps/web/src/hooks/useSidebar.ts

@@ -171,6 +171,7 @@ function applyEvent(prev: SidebarResponse, event: import('./sessionEvents').Sess
     case 'chat_archived':
     case 'chat_unarchived':
     case 'chat_deleted':
+    case 'chat_status':
       return prev;
     case 'project_archived': {
       const next = prev.projects.filter((p) => p.id !== event.project_id);

apps/web/src/hooks/useUserEvents.ts

@@ -1,5 +1,6 @@
 import { useEffect } from 'react';
 import { sessionEvents } from './sessionEvents';
+import { createWsReconnectToast } from './wsReconnectToast';
 
 const RECONNECT_INITIAL_MS = 1000;
 const RECONNECT_MAX_MS = 30000;
@@ -11,6 +12,20 @@ export function useUserEvents(): void {
     let reconnectDelay = RECONNECT_INITIAL_MS;
     let unmounted = false;
 
+    // v1.8.1: silent on the first disconnect; gray "reconnecting…" after 3
+    // fails / 15 s; red "connection lost" with a Retry Now action after 60 s.
+    const reconnectToast = createWsReconnectToast({
+      label: 'Live updates',
+      onRetryNow: () => {
+        if (reconnectTimer) {
+          clearTimeout(reconnectTimer);
+          reconnectTimer = null;
+          reconnectDelay = RECONNECT_INITIAL_MS;
+          connect();
+        }
+      },
+    });
+
     const connect = () => {
       if (unmounted) return;
       const url = new URL('/api/ws/user', window.location.href);
@@ -19,6 +34,7 @@ export function useUserEvents(): void {
 
       ws.onopen = () => {
         reconnectDelay = RECONNECT_INITIAL_MS;
+        reconnectToast.onConnected();
       };
 
       ws.onmessage = (ev) => {
@@ -34,6 +50,7 @@ export function useUserEvents(): void {
 
       ws.onclose = () => {
         if (unmounted) return;
+        reconnectToast.onFailure();
         const delay = reconnectDelay;
         reconnectDelay = Math.min(reconnectDelay * 2, RECONNECT_MAX_MS);
         reconnectTimer = setTimeout(connect, delay);
@@ -50,8 +67,8 @@ export function useUserEvents(): void {
 
     return () => {
       unmounted = true;
+      reconnectToast.dispose();
       if (reconnectTimer) clearTimeout(reconnectTimer);
-      // best-effort cleanup; ignore failure because the socket may already be closed
       if (ws) try { ws.close(); } catch {}
     };
   }, []);

apps/web/src/hooks/wsReconnectToast.ts

@@ -0,0 +1,95 @@
+import { toast } from 'sonner';
+
+// v1.8.1 thresholds. First disconnect is silent — mobile Authelia idle timeouts
+// and tab suspensions trip reconnects constantly and the old red "websocket
+// error" toast made the app feel broken. Only escalate once the failure is
+// sustained.
+const TOAST_AFTER_FAILS = 3;
+const TOAST_AFTER_MS = 15_000;
+const PERSISTENT_AFTER_MS = 60_000;
+
+export interface WsReconnectToast {
+  onFailure(): void;
+  onConnected(): void;
+  dispose(): void;
+}
+
+interface Options {
+  label: string;            // shown in the toast (e.g. "Live updates")
+  onRetryNow: () => void;   // user clicked the "Retry now" action
+}
+
+// Per-connection toast wrapper. Caller drives it from the WS lifecycle:
+//   onFailure   — after each failed connection attempt
+//   onConnected — after a successful onopen
+//   dispose     — on hook unmount
+// The wrapper itself runs no timers and does not change the caller's reconnect
+// cadence; it only decides when to show / dismiss the toast.
+export function createWsReconnectToast(opts: Options): WsReconnectToast {
+  let firstFailureAt: number | null = null;
+  let failureCount = 0;
+  let reconnectingId: string | number | null = null;
+  let persistentId: string | number | null = null;
+
+  function dismissReconnecting(): void {
+    if (reconnectingId !== null) {
+      toast.dismiss(reconnectingId);
+      reconnectingId = null;
+    }
+  }
+  function dismissPersistent(): void {
+    if (persistentId !== null) {
+      toast.dismiss(persistentId);
+      persistentId = null;
+    }
+  }
+
+  return {
+    onFailure() {
+      if (firstFailureAt === null) firstFailureAt = Date.now();
+      failureCount += 1;
+      const elapsed = Date.now() - firstFailureAt;
+
+      // Escalate to red error + Retry button after PERSISTENT_AFTER_MS. Replaces
+      // the gray toast if it's still showing.
+      if (persistentId === null && elapsed >= PERSISTENT_AFTER_MS) {
+        dismissReconnecting();
+        persistentId = toast.error(`${opts.label}: connection lost`, {
+          duration: Infinity,
+          action: {
+            label: 'Retry now',
+            onClick: () => {
+              dismissReconnecting();
+              dismissPersistent();
+              opts.onRetryNow();
+            },
+          },
+        });
+        return;
+      }
+
+      // Gray "reconnecting…" toast once we've crossed either threshold.
+      if (
+        reconnectingId === null &&
+        persistentId === null &&
+        (failureCount >= TOAST_AFTER_FAILS || elapsed >= TOAST_AFTER_MS)
+      ) {
+        reconnectingId = toast.warning(`${opts.label}: reconnecting…`, {
+          duration: Infinity,
+        });
+      }
+    },
+    onConnected() {
+      firstFailureAt = null;
+      failureCount = 0;
+      dismissReconnecting();
+      dismissPersistent();
+    },
+    dispose() {
+      firstFailureAt = null;
+      failureCount = 0;
+      dismissReconnecting();
+      dismissPersistent();
+    },
+  };
+}

apps/web/src/pages/Session.tsx

@@ -1,5 +1,11 @@
-import { useEffect, useState } from 'react';
-import { Link, useNavigate, useParams } from 'react-router-dom';
+import { useCallback, useEffect, useState } from 'react';
+import {
+  Link,
+  useLocation,
+  useNavigate,
+  useParams,
+  useSearchParams,
+} from 'react-router-dom';
 import { ChevronRight, FolderTree, Menu } from 'lucide-react';
 import { api } from '@/api/client';
 import type { Project, Session as SessionType } from '@/api/types';
@@ -8,12 +14,28 @@ import { useActivePane } from '@/hooks/useActivePane';
 import { useSidebarDrawer } from '@/hooks/useSidebarDrawer';
 import { useRightRailDrawer } from '@/hooks/useRightRailDrawer';
 import { useViewport } from '@/hooks/useViewport';
+import { useWorkspacePanes, MAX_PANES } from '@/hooks/useWorkspacePanes';
+import { useSessionChats } from '@/hooks/useSessionChats';
+import { useProjectGit } from '@/hooks/useProjectGit';
 import { Workspace } from '@/components/Workspace';
 import { ModelPicker } from '@/components/ModelPicker';
+import { MobileTabSwitcher } from '@/components/MobileTabSwitcher';
+import { NewPaneMenu } from '@/components/NewPaneMenu';
+import { cn } from '@/lib/utils';
 
 export function Session() {
   const { id } = useParams<{ id: string }>();
+  if (!id) return null;
+  // v1.8: key on id so route navigation remounts SessionInner — the hoisted
+  // useWorkspacePanes + useSessionChats then reinitialize cleanly from the
+  // new sessionId instead of carrying stale state across sessions.
+  return <SessionInner key={id} sessionId={id} />;
+}
+
+function SessionInner({ sessionId }: { sessionId: string }) {
   const navigate = useNavigate();
+  const location = useLocation();
+  const [searchParams] = useSearchParams();
   const [session, setSession] = useState<SessionType | null>(null);
   const [project, setProject] = useState<Project | null>(null);
   const [name, setName] = useState('');
@@ -23,23 +45,53 @@ export function Session() {
   const { toggle: toggleRightRail } = useRightRailDrawer();
   const { isMobile } = useViewport();
 
+  // v1.8: pane + chat state hoisted into Session so the mobile header pill
+  // (MobileTabSwitcher) shares one source of truth with the pane grid below.
+  const panesHook = useWorkspacePanes(sessionId);
+  const {
+    panes,
+    activePaneIdx,
+    setActivePaneIdx,
+    openChatInPane,
+    activePaneIdxRef,
+    addSplitPane,
+    removePane,
+    removeChatFromPanes,
+    initializeFirstChatIfEmpty,
+  } = panesHook;
+
+  const openChatInActivePane = useCallback(
+    (chatId: string) => openChatInPane(activePaneIdxRef.current, chatId),
+    [openChatInPane, activePaneIdxRef],
+  );
+  const chatsHook = useSessionChats(sessionId, {
+    removeChatFromPanes,
+    openChatInPane,
+    openChatInActivePane,
+    initializeFirstChatIfEmpty,
+  });
+  const { chats, renameChat } = chatsHook;
+
+  // v1.8 Level 1: branch indicator. Polls every 30s; server caches the same
+  // span so back-to-back loads are cheap. Returns null until the first fetch
+  // resolves or if the project isn't a git repo.
+  const git = useProjectGit(project?.id);
+
   useEffect(() => {
-    if (!id) return;
     setSession(null);
     setProject(null);
     let cancelled = false;
     api.sessions
-      .get(id)
+      .get(sessionId)
       .then((s) => {
         if (cancelled) return;
         setSession(s);
         setName(s.name);
         sessionEvents.emit({
           type: 'session_loaded',
-          session_id: id,
+          session_id: sessionId,
           project_id: s.project_id,
         });
-        // Load project for breadcrumb. Listing is fine — small N, cached by client.
         api.projects.list().then((projects) => {
           if (cancelled) return;
           const p = projects.find((x) => x.id === s.project_id);
@@ -50,34 +102,61 @@ export function Session() {
     return () => {
       cancelled = true;
     };
-  }, [id]);
+  }, [sessionId]);
 
   useEffect(() => {
-    if (!id) return;
     return sessionEvents.subscribe((event) => {
-      if (event.type === 'session_renamed' && event.session_id === id) {
+      if (event.type === 'session_renamed' && event.session_id === sessionId) {
         setSession((prev) => (prev ? { ...prev, name: event.name } : prev));
         setName((prev) => (editingName ? prev : event.name));
         return;
       }
       if (
         (event.type === 'session_deleted' || event.type === 'session_archived') &&
-        event.session_id === id
+        event.session_id === sessionId
       ) {
         navigate(`/project/${event.project_id}`);
       }
     });
-  }, [id, editingName, navigate]);
+  }, [sessionId, editingName, navigate]);
+
+  // v1.8: URL ?pane= sync (mobile only). Lifted from Workspace.tsx so
+  // MobileTabSwitcher's onSwitchPane can push the same URL state and the
+  // browser Back button continues to walk pane history on mobile.
+  useEffect(() => {
+    if (!isMobile || panes.length === 0) return;
+    const paneId = searchParams.get('pane');
+    if (!paneId) {
+      if (activePaneIdx !== 0) setActivePaneIdx(0);
+      return;
+    }
+    const idx = panes.findIndex((p) => p.id === paneId);
+    if (idx >= 0 && idx !== activePaneIdx) setActivePaneIdx(idx);
+  }, [isMobile, searchParams, panes, activePaneIdx, setActivePaneIdx]);
+
+  const switchActivePane = useCallback(
+    (idx: number) => {
+      setActivePaneIdx(idx);
+      if (isMobile) {
+        const pane = panes[idx];
+        if (!pane) return;
+        const params = new URLSearchParams(location.search);
+        params.set('pane', pane.id);
+        navigate(`${location.pathname}?${params.toString()}`);
+      }
+    },
+    [setActivePaneIdx, isMobile, panes, navigate, location.pathname, location.search],
+  );
 
   async function saveName() {
-    if (!id || !session) return;
+    if (!session) return;
     const trimmed = name.trim();
     if (!trimmed || trimmed === session.name) {
       setName(session.name);
       setEditingName(false);
       return;
     }
-    const updated = await api.sessions.update(id, { name: trimmed });
+    const updated = await api.sessions.update(sessionId, { name: trimmed });
     setSession(updated);
     setEditingName(false);
     // Server publishes session_renamed via broker.publishUser; no local emit needed.
@@ -85,122 +164,179 @@ export function Session() {
 
   // Workspace only sets activeFile for file-browser panes; checking it alone
   // suffices and is forward-compatible with future pane kinds.
-  const showActiveFile = active.sessionId === id && !!active.activeFile;
+  const showActiveFile = active.sessionId === sessionId && !!active.activeFile;
 
   return (
     <div className="flex-1 flex flex-col min-h-0">
       <header
-        className="border-b px-3 sm:px-4 py-2 flex items-center gap-1.5 shrink-0 text-sm"
+        className={cn(
+          'border-b shrink-0 text-sm',
+          isMobile
+            ? 'flex flex-col gap-1.5 px-3 py-2'
+            : 'flex items-center gap-1.5 px-3 sm:px-4 py-2',
+        )}
         style={{ paddingTop: 'max(0.5rem, env(safe-area-inset-top))' }}
       >
-        {isMobile && (
-          <button
-            type="button"
-            onClick={() => setDrawerOpen(true)}
-            className="inline-flex items-center justify-center -ml-1 min-w-[44px] min-h-[44px] rounded text-muted-foreground hover:bg-muted hover:text-foreground shrink-0"
-            aria-label="Open sidebar"
-          >
-            <Menu className="size-5" />
-          </button>
-        )}
-
-        {/* Breadcrumb — desktop only */}
-        <div className="hidden sm:flex items-center gap-1.5 min-w-0">
-          <Link to="/" className="text-muted-foreground hover:text-foreground shrink-0 text-xs">
-            Projects
-          </Link>
-          <ChevronRight className="size-3 text-muted-foreground/60 shrink-0" />
-          {project ? (
-            <Link
-              to={`/project/${project.id}`}
-              className="text-muted-foreground hover:text-foreground truncate max-w-[200px]"
-              title={project.name}
-            >
-              {project.name}
-            </Link>
-          ) : (
-            <span className="text-muted-foreground/60">…</span>
-          )}
-          <ChevronRight className="size-3 text-muted-foreground/60 shrink-0" />
-        </div>
-
-        {/* Session name — always visible, truncated, editable */}
-        {editingName ? (
-          <input
-            autoFocus
-            value={name}
-            onChange={(e) => setName(e.target.value)}
-            onBlur={() => void saveName()}
-            onKeyDown={(e) => {
-              if (e.key === 'Enter') void saveName();
-              if (e.key === 'Escape') {
-                setName(session?.name ?? '');
-                setEditingName(false);
-              }
-            }}
-            className="bg-transparent border-b border-border px-1 py-0.5 text-sm font-medium outline-none focus:border-ring min-w-0"
-          />
-        ) : (
-          <button
-            type="button"
-            className="text-sm font-medium hover:underline truncate max-w-[140px] sm:max-w-[280px] min-w-0"
-            onClick={() => setEditingName(true)}
-            title={session?.name ?? ''}
-          >
-            {session?.name ?? '…'}
-          </button>
-        )}
-
-        {/* Active file — desktop only */}
-        {showActiveFile && active.activeFile && (
+        {isMobile ? (
           <>
-            <span className="text-muted-foreground/40 mx-1 hidden sm:inline">·</span>
-            <span
-              className="text-xs font-mono text-muted-foreground truncate max-w-[200px] hidden sm:inline"
-              title={active.activeFile}
-            >
-              {active.activeFile}
-            </span>
-          </>
-        )}
+            {/* v1.8 mobile row 1: hamburger | repo+branch | ModelPicker | FolderTree.
+                Gear/kebab cluster lands in Batch 7; ModelPicker stays here until
+                then so mobile users keep model-switching access. */}
+            <div className="flex items-center gap-1.5">
+              <button
+                type="button"
+                onClick={() => setDrawerOpen(true)}
+                className="inline-flex items-center justify-center -ml-1 min-w-[44px] min-h-[44px] rounded text-muted-foreground hover:bg-muted hover:text-foreground shrink-0"
+                aria-label="Open sidebar"
+              >
+                <Menu className="size-5" />
+              </button>
 
-        {/* Model picker — right-aligned */}
-        <div className="ml-auto shrink-0">
-          {session && (
-            <div className="inline-flex items-center rounded-full bg-muted/40 hover:bg-muted/70 px-1">
-              <ModelPicker
-                value={session.model}
-                onChange={async (model) => {
-                  const updated = await api.sessions.update(session.id, { model });
-                  setSession(updated);
-                }}
+              <div className="flex-1 min-w-0 flex items-center justify-center gap-1.5">
+                {project ? (
+                  <span className="text-sm font-medium truncate" title={project.name}>
+                    {project.name}
+                  </span>
+                ) : (
+                  <span className="text-muted-foreground/60">…</span>
+                )}
+                {git?.branch && (
+                  <span
+                    className="text-muted-foreground/80 text-xs truncate"
+                    title={`branch: ${git.branch}${git.is_dirty ? ' (dirty)' : ''}`}
+                  >
+                    · {git.branch}
+                  </span>
+                )}
+              </div>
+
+              {session && (
+                <div className="inline-flex items-center rounded-full bg-muted/40 hover:bg-muted/70 px-1 shrink-0">
+                  <ModelPicker
+                    value={session.model}
+                    onChange={async (model) => {
+                      const updated = await api.sessions.update(session.id, { model });
+                      setSession(updated);
+                    }}
+                  />
+                </div>
+              )}
+
+              <button
+                type="button"
+                onClick={toggleRightRail}
+                className="inline-flex items-center justify-center -mr-1 min-w-[44px] min-h-[44px] rounded text-muted-foreground hover:bg-muted hover:text-foreground shrink-0"
+                aria-label="Toggle file browser"
+              >
+                <FolderTree className="size-5" />
+              </button>
+            </div>
+
+            {/* v1.8 mobile row 2: pane-switcher pill + new-pane menu. Pill
+                expands; NewPaneMenu is the trailing 44x44 trigger. */}
+            <div className="flex items-center gap-1.5">
+              <MobileTabSwitcher
+                panes={panes}
+                activePaneIdx={activePaneIdx}
+                chats={chats}
+                onSwitchPane={switchActivePane}
+                onRemovePane={removePane}
+                onRenameChat={renameChat}
+              />
+              <NewPaneMenu
+                onAddPane={addSplitPane}
+                disabled={panes.length >= MAX_PANES}
               />
             </div>
-          )}
-        </div>
+          </>
+        ) : (
+          <>
+            {/* Desktop: unchanged single-row header. */}
+            <div className="hidden sm:flex items-center gap-1.5 min-w-0">
+              <Link to="/" className="text-muted-foreground hover:text-foreground shrink-0 text-xs">
+                Projects
+              </Link>
+              <ChevronRight className="size-3 text-muted-foreground/60 shrink-0" />
+              {project ? (
+                <Link
+                  to={`/project/${project.id}`}
+                  className="text-muted-foreground hover:text-foreground truncate max-w-[200px]"
+                  title={project.name}
+                >
+                  {project.name}
+                </Link>
+              ) : (
+                <span className="text-muted-foreground/60">…</span>
+              )}
+              <ChevronRight className="size-3 text-muted-foreground/60 shrink-0" />
+            </div>
 
-        {/* File browser toggle — mobile only */}
-        {isMobile && (
-          <button
-            type="button"
-            onClick={toggleRightRail}
-            className="inline-flex items-center justify-center -mr-1 min-w-[44px] min-h-[44px] rounded text-muted-foreground hover:bg-muted hover:text-foreground shrink-0"
-            aria-label="Toggle file browser"
-          >
-            <FolderTree className="size-5" />
-          </button>
+            {editingName ? (
+              <input
+                autoFocus
+                value={name}
+                onChange={(e) => setName(e.target.value)}
+                onBlur={() => void saveName()}
+                onKeyDown={(e) => {
+                  if (e.key === 'Enter') void saveName();
+                  if (e.key === 'Escape') {
+                    setName(session?.name ?? '');
+                    setEditingName(false);
+                  }
+                }}
+                className="bg-transparent border-b border-border px-1 py-0.5 text-sm font-medium outline-none focus:border-ring min-w-0"
+              />
+            ) : (
+              <button
+                type="button"
+                className="text-sm font-medium hover:underline truncate max-w-[280px] min-w-0"
+                onClick={() => setEditingName(true)}
+                title={session?.name ?? ''}
+              >
+                {session?.name ?? '…'}
+              </button>
+            )}
+
+            {showActiveFile && active.activeFile && (
+              <>
+                <span className="text-muted-foreground/40 mx-1">·</span>
+                <span
+                  className="text-xs font-mono text-muted-foreground truncate max-w-[200px]"
+                  title={active.activeFile}
+                >
+                  {active.activeFile}
+                </span>
+              </>
+            )}
+
+            <div className="ml-auto shrink-0">
+              {session && (
+                <div className="inline-flex items-center rounded-full bg-muted/40 hover:bg-muted/70 px-1">
+                  <ModelPicker
+                    value={session.model}
+                    onChange={async (model) => {
+                      const updated = await api.sessions.update(session.id, { model });
+                      setSession(updated);
+                    }}
+                  />
+                </div>
+              )}
+            </div>
+          </>
         )}
       </header>
 
-      {id && session && (
+      {session && (
         <Workspace
-          sessionId={id}
+          sessionId={sessionId}
           projectId={session.project_id}
           agentId={session.agent_id}
           onAgentChange={async (agent_id) => {
             const updated = await api.sessions.update(session.id, { agent_id });
             setSession(updated);
           }}
+          panesHook={panesHook}
+          chatsHook={chatsHook}
         />
       )}
     </div>

boocode_roadmap.md

@@ -4,512 +4,341 @@ Last updated: 2026-05-16
 
 ## Overview
 
-BooCode is a standalone code-chat tool at `/opt/boocode/`. Read-only by design in v1.x — pick a project, chat with a local LLM that has file-inspection tools, get streaming responses over WebSocket. Built May 2026 after the in-boolab BooCode mode stalled.
-
-v1 shipped in a single Claude Code session. v1.1 onwards is a batched build-out. Original Batch 1–10 plan was reordered mid-stream — chats-inside-sessions, archive, and fork/delete work was prioritized over the mobile pass.
+BooCode is a standalone code-chat tool at `/opt/boocode/`. Read-only by design — pick a project, chat with a local LLM that has file-inspection tools, get streaming responses over WebSocket.
 
 Live at `https://code.indifferentketchup.com` (Caddy → Authelia → Tailscale → `100.114.205.53:9500`).
 
------
+**Architectural commitments:**
 
-## Version summary
+- No embeddings. The model uses file-view tools (`view_file`, `list_dir`, `grep`, `find_files`) + sidecar analyzers (codecontext, codesight). Walked away from the RAG pipeline May 2026.
+- Read-only in v1.x. Write tools land in BooCoder (separate container, post-v1.x).
+- One Postgres (`boocode_db`), one frontend SPA, container-per-service for new capabilities.
 
-|Version         |Theme                                                                                                                                  |Status                           |Notes                                    |
-|----------------|---------------------------------------------------------------------------------------------------------------------------------------|---------------------------------|-----------------------------------------|
-|v1.0            |Initial scaffold, read-only tools, WS streaming                                                                                        |✅ Done                           |Shipped in one Claude Code session       |
-|v1.1-batch1     |Markdown, Copy + Regen, tok/s + ctx, AI chat naming                                                                                    |✅ Merged                         |—                                        |
-|v1.1-batch2     |Sidebar restructure: projects → sessions, max 5 + “view all”                                                                           |✅ Merged                         |—                                        |
-|v1.1-batch3     |Pane system, FileBrowserPane + Shiki, chat→file click, cross-tab                                                                       |✅ Merged                         |—                                        |
-|v1.1-batch3.5   |Chip infrastructure, `@file` picker, line-select-attach                                                                                |✅ Merged                         |—                                        |
-|v1.2            |Chats inside sessions refactor, right-rail, `/compact`, archive, force-send                                                            |✅ Merged                         |Replaced original “Batch 4 = mobile” plan|
-|v1.2-project-ux |Project archive UX, sidebar context menu, full-bootstrap, Gitea API                                                                    |✅ Merged                         |—                                        |
-|v1.3            |Tab-close + chat-archive                                                                                                               |✅ Merged                         |—                                        |
-|v1.4            |Fork from message + delete message + header polish + housekeeping                                                                      |✅ Merged                         |Was original “Batch 5”                   |
-|v1.5            |Refactor splits, vitest harness (23 tests), error-log surfacing, `/opt:ro` + `BOOTSTRAP_ROOT`, persistent context-window tracker       |✅ Merged                         |—                                        |
-|v1.5.1          |Bootstrap hotfix: git in container, SSH keypair, known_hosts, SSH URL rewrite, /opt/projects label                                     |✅ Merged                         |`4a9f207`                                |
-|v1.6-mobile-pass|Mobile pass: drawer, pane stacking, long-press, swipe-to-close, pull-to-refresh, IME safety, safe-area, tap targets + H1 path-guard fix|✅ Merged                         |`57c883b..943ae7d` (6 commits)           |
-|v1.6.1-cleanup  |Mostly audit-only; one fix shipped: RightRail `max-md:hidden` wrapper. Audit reports for secrets, stale code, panes, mount scope, hand-rolled patterns deferred to follow-ups |✅ Merged                         |`6a9fe18`                                |
-|v1.6.2-mobile-ui-fixes|Mobile UI polish from device testing: kill single-pane navigator chrome, header rework, “New chat” in long-press menu, RightRail as mobile drawer (reverts v1.6.1 wrapper) |🔄 Hand-back received, uncommitted|—                                        |
-|v1.7            |Drag-drop + paste-as-attachment (chip infra extension)                                                                                 |Planned                          |Was Batch 6                              |
-|v1.8            |Settings drawer (system prompt per project + session, web search toggle)                                                               |Planned                          |Was Batch 7                              |
-|v1.9            |Web search backend: SearXNG `web_search` + `web_fetch` tools                                                                           |Planned                          |Was Batch 8                              |
-|v1.10           |Agents (Tier 2): `AGENTS.md`, per-agent model/temp/tools, picker                                                                       |Planned                          |Was Batch 9                              |
-|v1.11           |BooTerm: separate container, xterm.js + node-pty + tmux, terminal pane                                                                 |Planned                          |Was Batch 10                             |
+External code lifted from / referenced in: see `boocode_code_review.md` for full inventory.
 
 -----
 
-## Version details
+## Batch summary
 
-### v1.1-batch1 — Message polish ✅
+|Batch                                     |Theme                                                                              |Status     |Branch / Notes                         |
+|------------------------------------------|-----------------------------------------------------------------------------------|-----------|---------------------------------------|
+|1                                         |Markdown, Copy + Regen, tok/s + ctx, AI naming                                     |✅ Done     |`v1.1-batch1` merged                   |
+|2                                         |Sidebar restructure                                                                |✅ Done     |`v1.1-batch2` merged                   |
+|3                                         |Pane system, FileBrowserPane + Shiki, cross-tab                                    |✅ Done     |`v1.1-batch3` merged                   |
+|3.5                                       |Chip infrastructure, `@file`, line-select                                          |✅ Done     |merged                                 |
+|4 (v1.2)                                  |Chats inside sessions, right-rail, `/compact`, archive, force-send                 |✅ Done     |merged                                 |
+|4.1–4.4                                   |Project archive, sidebar context, Gitea API, bootstrap                             |✅ Done     |merged                                 |
+|v1.5 cleanup                              |resolveProjectPath, BOOTSTRAP_ROOT, vitest pin                                     |✅ Done     |merged                                 |
+|v1.6 mobile                               |Drawer, single-pane, long-press, IME-safe, pull-to-refresh, swipe-close            |✅ Done     |merged                                 |
+|v1.6.1                                    |RightRail mobile wrapper fix                                                       |✅ Done     |merged                                 |
+|Tool-loop bump                            |MAX_TOOL_LOOP_DEPTH 5→15                                                           |✅ Done     |merged                                 |
+|v1.6.2                                    |Workspace + Session+Project headers + ChatTabBar new-chat + RightRail mobile drawer|🔄 In flight|`v1.6.2-mobile-ui-fixes`               |
+|**v1.8 mobile tabs**                      |**Bottom-sheet pane switcher + cross-tab `pane_status` WS sync + StatusDot on tabs**|**Next up**|`v1.8-mobile-tabs`; hand-rolled sheet  |
+|9 (REORDERED, DECOUPLED)                  |Agents (Tier 2): `AGENTS.md`, per-agent temp/tools, picker in ChatInput toolbar    |✅ Implemented, uncommitted|six builtins; on `main` awaiting commit|
+|5                                         |Fork message, delete message, header polish                                        |Planned    |                                       |
+|6                                         |Drag-drop file + paste-as-attachment                                               |Planned    |thin extension of 3.5 chips            |
+|7                                         |Settings drawer: system prompt, web search toggle, agent entry                     |Planned    |adds SettingsDrawer agent entry (Batch 9 deferred half) |
+|8                                         |Web search backend: SearXNG `web_search` + `web_fetch`                             |Planned    |                                       |
+|10                                        |BooTerm: separate container, xterm.js + node-pty + tmux                            |Planned    |                                       |
+|11 — Architect: codebase map              |codecontext sidecar + MCP tool wiring                                              |Planned    |from nmakod/codecontext                |
+|11b — Architect: repo health              |call graph, circular deps, dead code                                               |Planned    |from spirituslab/codesight             |
+|12 — Tool approval + plan/act mode        |Read-only invariant, per-tool gating                                               |Planned    |from cline                             |
+|13 — Append-only event log                |Replace messages-table semantics                                                   |Planned    |from OpenHands V1                      |
+|14 — BooCoder: pending changes            |Sandboxed edit queue, atomic apply                                                 |Post-v1.x  |from plandex                           |
+|15 — BooCoder runtime isolation           |Per-session Docker sandbox                                                         |Post-v1.x  |from OpenHands                         |
+|16 — Multi-provider LLM                   |Optional litellm-style abstraction                                                 |Optional   |from pi-ai                             |
+|17 — Workflow graphs                      |Multi-agent coordination                                                           |Far future |from microsoft/agent-framework concepts|
 
-Markdown (`react-markdown` + `remark-gfm`), Copy + Regenerate, tok/s + context counter, AI session naming.
+**Old Batch 12 (codebase indexer w/ Harrier embeddings) — REMOVED.** Replaced by Batch 11/11b sidecar approach. See `boocode_code_review.md` decisions log.
 
-**Key decisions:**
-
-- `sessions.name` (not `title`).
-- `enable_thinking: false` + `max_tokens: 30` for Qwen3 utility calls.
-- `messages_deleted` WS frame added for multi-tab regen.
-- In-app event bus (`sessionEvents.ts`, module-scope `Set<Listener>`).
-
-**Schema:** `messages.tokens_used`, `messages.ctx_used`, `messages.ctx_max`, `messages.started_at`, `messages.finished_at`.
+**Batch 9 reordered ahead of 5–8, 10.** Picker mounts in `ChatInput.tsx` toolbar only. SettingsDrawer agent entry rolled into Batch 7 when it lands. No UI dependency on Batches 5/6/7, so it can ship anytime after v1.6.2.
 
 -----
 
-### v1.1-batch2 — Sidebar restructure ✅
+## Batch details (planned / new)
 
-Projects as expandable groups, up to 5 recent sessions per project, “View all (N)”, `GET /api/sidebar`, `useSidebar` singleton hook.
+### Batch 9 — Agents (Tier 2, DECOUPLED)
 
-**Key decisions:**
+**Spec:** `boocode_batch9.md` with the deltas below.
 
-- `useSidebar` module-scope singleton.
-- `localStorage['boocode.sidebar.expanded']`.
-- `session_renamed` payload `{session_id, name}`.
+**Status:** Next up after v1.6.2 merges. Decoupled from Batch 7.
+
+**Deltas from `boocode_batch9.md`:**
+
+1. Builtin defaults in `agents.ts` OMIT the `model` field. Resolution order makes `session.model` win when `agent.model` is null. Spec line 30 example is misleading — do not hardcode any model in builtins.
+2. Builtin defaults are the six agents shipped in `/opt/boocode/AGENTS.md`: **Code Reviewer, Debugger, Refactorer, Architect, Security Auditor, Prompt Builder.** If project root `AGENTS.md` exists, only its agents show. If absent, show the six builtins.
+3. AgentPicker mounts in `ChatInput.tsx` toolbar between ModelPicker and the `+` button. **No `SettingsDrawer.tsx` or `Header.tsx` changes in this batch.**
+4. SettingsDrawer agent entry + Header active-agent badge moved to Batch 7.
+
+**Files to create:**
+
+- `apps/server/src/services/agents.ts` — parser, six builtin defaults, mtime-keyed cache.
+- `apps/server/src/routes/agents.ts` — `GET /api/projects/:id/agents`.
+- `apps/web/src/components/AgentPicker.tsx` — dropdown, matches ModelPicker pattern.
+
+**Files to modify:**
+
+- `apps/server/src/schema.sql` — `ALTER TABLE sessions ADD COLUMN IF NOT EXISTS agent_id TEXT;`
+- `apps/server/src/services/inference.ts` — resolution order: `effective_system_prompt`, `effective_model`, `effective_temperature`, `effective_tools` from session + agent + project. Filter tools array against agent whitelist before sending to llama-swap.
+- `apps/server/src/routes/sessions.ts` — PATCH accepts `agent_id`.
+- `apps/server/src/types/api.ts` — Agent type, extend Session with `agent_id`.
+- `apps/web/src/api/client.ts`, `apps/web/src/api/types.ts` — Agent type, `api.agents.list(projectId)`.
+- `apps/web/src/components/ChatInput.tsx` — mount AgentPicker.
+
+**Testing plan (manual, before locking temps):**
+
+- Drop `/opt/boocode/AGENTS.md` (six agents, no `model` field on any).
+- For each of the 7 keeper models, switch session model and run the same target prompt against each agent. Log tok/s, instruction-following quality.
+- Adjust per-agent temperature in `AGENTS.md` based on results.
+- A/B candidates: qwen3.6-35b-a3b-mxfp4 (daily), qwopus3.6-35b-a3b-q4 (reasoning), qwopus3.5-27b-q4, qwen3.6-27b-ud-q4-xl, nemotron-3-nano-30b, gemma-4-26b-a4b-mxfp4, qwen3-coder-30b-apex.
+
+**Dependencies:** v1.6.2 merged.
 
 -----
 
-### v1.1-batch3 — Pane system ✅
+### Batch 11 — Architect: codebase map (REVISED)
 
-`session_panes` table, pane CRUD with transactional position-shift, Workspace + tab strip + drag-to-reorder (native HTML5), ChatPane (extracted), FileBrowserPane (tree + Shiki + filter), chat→file click, PaneTab context menu, `file_ops` + `file_index` shared services, broker user channel + `/ws/user`, `session_updated`, `session_loaded`, idempotent default-Chat-pane backfill.
+**Inspiration / lift:** `nmakod/codecontext` (MIT, Go binary).
 
-**Schema:** `session_panes` (id, session_id, position, kind CHECK, state JSONB).
+**What it gives BooCode:** an architect-grade codebase overview without embeddings. Codecontext parses the repo with tree-sitter, extracts symbols, builds import/dependency relationships, and exposes the result via an MCP server with 8 tools. The model gets a structural map of any codebase on demand.
+
+**Why this replaces the original Batch 11 (aider PageRank port):** codecontext is a finished binary in our stack language (Go), with watch mode, incremental updates, framework detection, and git-co-change-based semantic neighborhoods (no embeddings). The aider port would be reimplementing what codecontext already ships.
+
+**Scope:**
+
+- Add `codecontext` sidecar container to `docker-compose.yml`. Mount the project root read-only. One sidecar per BooCode instance — projects are addressed by absolute path.
+- Wire each codecontext MCP tool into BooCode’s `inference/tools.ts` as a native tool the model can call:
+ - `repo_overview(project_id)` → codecontext `get_codebase_overview`
+ - `repo_file_analysis(project_id, path)` → `get_file_analysis`
+ - `repo_symbol_info(project_id, symbol)` → `get_symbol_info`
+ - `repo_search_symbols(project_id, query)` → `search_symbols`
+ - `repo_dependencies(project_id, path)` → `get_dependencies`
+ - `repo_semantic_neighborhoods(project_id, path)` → `get_semantic_neighborhoods` (git co-change)
+ - `repo_framework_analysis(project_id)` → `get_framework_analysis`
+- `path_guard.ts` extension: incorporate `continuedev/continue` `DEFAULT_SECURITY_IGNORE_FILETYPES` so codecontext can’t surface `.env`, `.pem`, keys, etc.
+- Fallback grammars: drop `Aider-AI/aider`‘s `aider/queries/tree-sitter-*.scm` files for any language codecontext doesn’t cover. Use them via an in-process tree-sitter wrapper *only if* a project needs an unsupported language. Defer wrapper build until that’s an actual gap.
+
+**Where it goes:** new `apps/server/src/architect/` directory. No new tables — codecontext maintains its own state on disk. New env: `CODECONTEXT_URL=http://codecontext:8765` (MCP endpoint).
+
+**Decisions to make at recon time:**
+
+- Bundle the binary directly in the BooCode Dockerfile, or run codecontext as its own service? Sidecar is cleaner. Bundle is one less container.
+- How does the model discover codecontext tools — register them statically in the tools registry, or proxy MCP `tools/list` at startup?
+
+**Dependencies:** none. Can ship before Batches 5–10.
 
 -----
 
-### v1.1-batch3.5 — Chips + @file + line-select ✅
+### Batch 11b — Architect: repo health (NEW)
 
-`Attachment` type + `flattenToMessage` + LANG_MAP, `AttachmentChip`, `AttachmentPreviewModal`, ChatInput chip-row, hand-rolled `@file` mention popover, line-select-attach in FileBrowserPane via local `FileViewer`, FileBrowserPane filter upgrade (empty=tree, non-empty=flat).
+**Inspiration / lift:** `spirituslab/codesight` (MIT-ish, TS/Node).
 
------
+**What it gives BooCode:** complement to Batch 11. Where codecontext answers “what is this codebase,” repo health answers “what’s wrong with this codebase.” Call graph, circular dependency detection, dead code flagging.
 
-### v1.2 — Chats inside sessions ✅
+**Scope:**
 
-Originally planned as the mobile pass. Reshuffled: structural refactor — chats inside sessions, right-rail, `/compact` (chat’s own model summarizes via `kind='compact'` system message), force-send.
-
-**Schema:** `chats` table, `sessions.status`, `messages.chat_id`, `messages.kind` (regular | compact).
-
------
-
-### v1.2-project-ux ✅
-
-Full new-project bootstrap (mkdir + git init + .gitignore + first commit + Gitea remote + push), sidebar context menu (Rename / Archive / Open in Gitea), project landing page archived-list, Gitea API integration. Option B taken: `BOOTSTRAP_ROOT` env var, `/opt` stays read-only mount, `/opt/projects` writable.
-
-**Schema:** `projects.status`, `projects.archived_at`.
-
-**Key decisions:**
-
-- `execFile` only, no `exec` shell strings.
-- DB INSERT last in bootstrap sequence.
-- Soft-fail on Gitea steps.
-- Project Delete endpoint exists but stays unexposed (re-add INSERTs fresh row → FK cascade nukes history; archive is the safe pattern).
-
------
-
-### v1.3 — Tab close + chat archive ✅
-
-Tab close UX cleanup, chat-level archive (separate from session archive).
-
------
-
-### v1.4 — Fork + delete + header polish ✅
-
-Was originally planned as Batch 5.
-
-**Shipped:** `POST /api/sessions/:id/fork` (deep copy messages up to target, new session in same project), `DELETE /api/sessions/:id/messages/:id` (cascading via `messages_deleted` frame), header breadcrumb (Projects → Project → Session), inline-editable session name, file path shown when File Browser pane is active, `useActivePane` hook.
-
------
-
-### v1.5 — Refactor + tests + security scoping + context tracker ✅
-
-5-commit sequence:
-
-1. **Refactor:** FileBrowserPane (865 → split with FileViewer extracted), Workspace, inference split.
-1. **Vitest harness:** 23 tests covering routes + resolveProjectPath. Pinned to v3 (Vite 5 / vitest 4 incompatibility).
-1. **Error-log surfacing:** dead-code removal from earlier H1/H2 audit items, structured error logs to client.
-1. **Mount scoping:** `/opt:/opt:ro` + `BOOTSTRAP_ROOT` writable subdir. Container loses write to `/opt` proper.
-1. **Persistent context-window tracker:** floating popover above chat input right edge, source = latest `message_complete` frame’s `ctx_used` / `ctx_max`, color-coded (neutral <60%, amber 60–85%, red 85%+), hides when `ctx_max` null.
-
-**Carried bug:** `resolveProjectPath` whitelist-root bypass — discovered, asserted as “BEHAVIOR GAP” rather than silently patched. Fix landed in v1.6 (H1).
-
------
-
-### v1.5.1 — Bootstrap hotfix ✅ (`4a9f207`)
-
-Dockerfile (git installed in container), docker-compose.yml, project_bootstrap.ts (SSH keypair, known_hosts, SSH URL Tailscale rewrite), CreateProjectModal.tsx, .gitignore. /opt/projects label clarified.
-
-**Known issue carried forward:** dispatch used the in-repo `secrets/boocode_gitea` SSH key because the agent key was rejected. Key exposure flagged. Audit + rotation tracked in v1.6.1 below.
-
------
-
-### v1.6-mobile-pass ✅
-
-**Merged via 6 commits `57c883b..943ae7d`** (5 functional + 1 docs):
-
-1. `57c883b chore: fix resolveProjectPath whitelist-root bypass` (H1 — dropped `real !== whitelistReal` short-circuit; flipped the v1.5 BEHAVIOR GAP test; 23/23 pass).
-1. `a643b5f feat(mobile): viewport hook + sidebar drawer + hamburger headers` (M1 + M2 + M6-header).
-1. `cd897d6 feat(mobile): single-pane stack + long-press tab menu + swipe-to-close` (M3 + M4 + A2).
-1. `273eeac feat(mobile): chat input keybinds + safe-area + tap targets + overflow safety` (M5 + M6-bottom + M7 + M8).
-1. `4b5b9b2 feat(mobile): pull-to-refresh sidebar list` (A1).
-1. `943ae7d docs: add v1.x roadmap snapshot` (this file).
+- Port codesight’s `analyze.mjs` analyzer core into `apps/server/src/architect/repo_health.ts`. Drop the VS Code extension shell. Keep:
+ - Symbol extraction (already overlaps codecontext — call codecontext where possible, only redo what’s needed for graph edges).
+ - Call graph builder (function-to-function edges).
+ - Circular dependency detector.
+ - Dead code detector (exported symbols never imported or called).
+- New tool: `repo_health(project_id)` returning `{ circular_dependencies: [...], dead_code: [...] }`. Output respects codesight’s documented false-positive caveats (customElements.define, framework entry points, dynamic imports) — surface those in the tool description so the model doesn’t trust dead-code flags blindly.
+- Cache results in `boocode_db` keyed by `(project_id, file_hashes)`. Invalidate on file change via file-index hash check.
 
 **Decisions:**
 
-- H2 (roadmap update) handled in this file rather than by Claude Code.
-- M5: mobile = button-only send, Enter inserts newline. Desktop unchanged. `isComposing` guard for CJK IME.
-- M6: kept `max-w-[1000px]` (mobile naturally full-width below cap).
-- URL state: `?pane=<paneId>`. Bare URL resets activePaneIdx to 0.
-- Long-press dispatches synthetic `contextmenu` on `[data-tab-id]`, opening Radix ContextMenuTrigger at touch coords. iOS callout suppressed.
-- `SwipeablePaneTab`: 60px threshold, bails if vertical >30px, opacity 1→0.4.
-- A2 bundled with M3 in Commit 3 (structural coupling).
-- Home.tsx no hamburger.
+- Build it in-process (Node) vs spawn a CLI? In-process is simpler. Spawn matches codecontext sidecar pattern but adds latency.
 
-**Deferred from v1.6 → rolled into v1.6.1-cleanup:**
-
-- RightRail still renders on mobile (~32px column).
-- Secrets hygiene audit.
-- `ProjectSidebar.tsx` and `ChatTabBar.tsx` share content from two commits each — use `git add -p`.
+**Dependencies:** Batch 11 merged (so we can reuse codecontext’s parse output where possible). Can be deferred until after Batches 5–10.
 
 -----
 
-### v1.6.1-cleanup ✅ (`6a9fe18`)
+### Batch 12 — Tool approval gating + plan/act mode
 
-**Shipped:** RightRail wrapped in `<div className="max-md:hidden contents">` so it's hidden entirely below the md breakpoint on mobile. (Note: v1.6.2 reverses this and replaces with a proper mobile drawer — see below.)
+**Inspiration / lift:** `cline/cline` (Apache-2.0).
 
-**Audited but not shipped (queued for follow-ups):**
-
-- **Secrets hygiene:** `secrets/boocode_gitea` is NOT tracked; never committed to any branch; `.gitignore` already covers `secrets/`. Rotation is a Gitea-side action, no repo change needed.
-- **`.bak` files:** 3 leftover from v1.5.1 (`docker-compose.yml.bak-20260516`, `Dockerfile.bak-20260516`, `apps/web/src/components/CreateProjectModal.tsx.bak-20260516`). Git-invisible via global `~/.gitignore_global` (`*.bak*`). Decide per file.
-- **Unused exports:** neither `knip` nor `ts-prune` installed. Proposal pending.
-- **Dead WS frames:** `session_renamed` HAS a server publisher (`routes/sessions.ts:140`, added in v1.4) — the roadmap's "no server publisher" open item is **STALE**, crossed off. The `InferenceFrame` union still declares `session_renamed` as a type variant but no code publishes it on the per-session channel; trivial 1-line cleanup deferred.
-- **Unused imports:** web `tsc --noUnusedLocals --noUnusedParameters` returns 0 warnings.
-- **`useSessionStream` refcount:** opportunity confirmed (~90 lines diff to apply the `useSidebar`-style module-scope singleton pattern). Risk LOW. Queued for v1.6.2 or later.
-- **PATCH `/api/panes/:id` ownership:** **MOOT** — endpoint does not exist (the pane REST API was never re-introduced after pane state moved to client-side localStorage in v1.2). Crossed off open items.
-- **Hand-rolled patterns vs library:** 5 hand-rolled hooks/components total 336 lines. None duplicates anything in existing deps; library swap (`@use-gesture`, `react-pull-to-refresh`) not worth the dep cost yet.
-- **`/opt:/opt:ro` mount tightening:** Two-option plan documented for v1.6.2 — Option A (per-project bind-mounts) or Option B (deny `.env` pattern in `pathGuard`). Option B is the simpler short-term fix.
-
------
-
-### v1.6.2-mobile-ui-fixes 🔄
-
-**Hand-back received, uncommitted on `v1.6.2-mobile-ui-fixes`.** 4-commit sequence proposed:
-
-1. `fix(mobile): hide Split button + single-pane navigator chrome` (G1 — wrap the Workspace Split row in `!isMobile`).
-1. `feat(mobile): rework Session and Project headers for narrow viewports` (G2 — breadcrumb `hidden sm:flex`, session name cap `max-w-[140px] sm:max-w-[280px]`, project page heading `text-base sm:text-lg`, “New session” icon-only on mobile).
-1. `feat(mobile): add "New chat" to tab long-press context menu` (G3 — top of menu, separator, then existing items).
-1. `feat(mobile): right-rail as drawer on mobile, header toggle button` (G4 option b — new `useRightRailDrawer` Context hook, `RightRail` renders as fixed `w-[85vw] max-w-sm` drawer on mobile, FolderTree button in Session header, **reverts v1.6.1's `max-md:hidden` wrapper**).
-
-**Decisions:**
-
-- G4 option b chosen: mobile file browsing IS useful; drawer pattern mirrors `useSidebarDrawer`.
-- G2 single-row session-name+model layout (model picker right-aligned), per spec example.
-- G3 "New chat" at top, separator, then Rename.
-- G2 "New session" button: icon-only on mobile via `<span className="hidden sm:inline">New session</span>`.
-
-**Adjacent uncommitted change (not part of v1.6.2):** `MAX_TOOL_LOOP_DEPTH 5 → 15` in `apps/server/src/services/inference.ts`. Sam-authored, sitting in working tree on `v1.6.2-mobile-ui-fixes`. **NOT on main as of this update.** Commit separately.
-
------
-
-### v1.7 — Drag-drop + paste (planned, was Batch 6)
-
-**Depends on:** v1.6.1 merged.
-
-**Scope (trimmed — chip infra exists from v1.1-batch3.5):**
-
-- Drag-drop files onto ChatInput → chip via `addAttachment({kind: 'file', source: 'drop'})`.
-- Paste >8 lines → chip via `addAttachment({kind: 'paste', source: 'paste'})`. ≤8 lines inline.
-- Drop overlay (dashed border + “Drop to attach”).
-- Client-side 5 MB cap + binary detection (null-byte check in first 8KB).
-- Max 10 attachments shared cap.
-- Folder drop rejected. Image paste rejected. Binary files rejected with toast.
-
-**Frontend only.**
-
------
-
-### v1.8 — Settings drawer (planned, was Batch 7)
-
-**Depends on:** header gear (already in v1.4).
+**What it gives BooCode:** per-session control over which tools the model can call. Lays the groundwork for BooCoder by building the gating mechanism before there are any write tools to gate.
 
 **Scope:**
 
-- Right-side drawer (hand-rolled, no shadcn Sheet). Tabbed: Session + Project.
-- Session tab: system prompt, web search toggle, model picker, session name.
-- Project tab: default system prompt, default web search, project name, root path (read-only), delete project (consider whether to expose given the cascade concern).
-- Resolution: `session.system_prompt OR project.default_system_prompt OR ""`.
-- Project defaults applied at session create (copied), not retroactively.
-- Web search toggle persistent per session (`sessions.web_search_enabled`).
+- New column `sessions.tool_approval_mode TEXT` — values: `read_only` (v1.x default), `plan`, `act_auto`, `act_approve`.
+- New column `sessions.approved_tools JSONB` — per-session whitelist for `act_approve` mode.
+- Tool registry refactor: tools tagged `read_only` or `write`. In `read_only` mode (v1.x), write tools never appear in the model’s tools array. In `plan` mode, same — write tools hidden, model produces a plan only. `act_*` modes unlock writes (post-v1.x).
+- UI: mode picker in SettingsDrawer (Batch 7 dependency). Inline indicator in chat header.
 
-**Schema:** `sessions.web_search_enabled`, `projects.default_system_prompt`, `projects.default_web_search`.
+**Dependencies:** Batch 7 (SettingsDrawer).
 
 -----
 
-### v1.9 — Web search backend (planned, was Batch 8)
+### Batch 13 — Append-only event log
 
-**Depends on:** v1.8.
+**Inspiration / lift:** `OpenHands/OpenHands` V1 (MIT).
+
+**What it gives BooCode:** replaces the ad-hoc `messages` table semantics with a typed event stream. Unlocks rewind, time-travel, and clean handoff semantics for multi-agent flows.
 
 **Scope:**
 
-- `web_search` tool → SearXNG at `http://100.114.205.53:8888/search?format=json`, top-N `{title, url, snippet}`.
-- `web_fetch` tool, regex HTML strip (no cheerio), 50KB cap.
-- Tools conditionally included based on `session.web_search_enabled`.
-- `ToolCallCard.tsx` renders results as clickable URL list, web_fetch as text preview.
-- Env: `SEARXNG_URL`, `WEB_FETCH_TIMEOUT_MS`, `WEB_FETCH_MAX_BYTES`.
+- New `session_events` table: `(id, session_id, ts, kind, payload JSONB, parent_id)`. Event kinds: `user_message`, `assistant_message`, `tool_call`, `tool_result`, `pane_action`, `mode_change`, `system`.
+- Existing `messages` table becomes a derived view over `session_events` for backward compatibility, then deprecated over a release.
+- Inference loop emits events instead of mutating message rows.
+- Frontend `useSessionStream` reducer rewritten to consume events.
+
+**Migration is non-trivial.** Plan in a dedicated batch with explicit cutover window.
+
+**Dependencies:** Batches 5 (fork/delete) and 7 (settings) merged. Must not be in flight with other backend work.
 
 -----
 
-### v1.10 — Agents (planned, was Batch 9)
+### Batch 14 — BooCoder: pending changes
 
-**Depends on:** v1.8.
+**Inspiration / lift:** `plandex-ai/plandex` (MIT).
+
+**What it gives BooCode:** safe write tools. Edits queue in a virtual layer; nothing touches the filesystem until explicit `/apply`.
 
 **Scope:**
 
-- Tier 2 agents: system prompt + model + temperature + tools whitelist per agent.
-- `AGENTS.md` (OpenCode-compatible): `## Agent Name` blocks with YAML frontmatter.
-- Three builtin defaults (Investigator, Architect, Reviewer) when no `AGENTS.md`.
-- If `AGENTS.md` exists, only its agents shown.
-- Agent picker in ChatInput toolbar + SettingsDrawer.
-- Tools whitelist enforced at inference layer. BooChat agents read-only.
-- File parsed on demand with mtime cache.
-- Mid-conversation agent switch allowed; old messages retain their tool history.
+- New container `boocoder` at `100.114.205.53:9502`. Owns write tools (`edit_file`, `create_file`, `delete_file`, `apply_pending`, `rewind`).
+- New table `pending_changes (id, session_id, file_path, diff TEXT, status, created_at)`. Status: `pending`, `applied`, `rejected`.
+- Tools execute against the pending-changes layer, not the filesystem. `apply_pending` is the only path that touches disk. `rewind` rolls back a `pending`-id back to disk state.
+- BooCode chat container stays read-only (`/opt:/opt:ro`). BooCoder mounts `/opt/repos:/opt/repos:rw` and uses git worktree pattern from paseo for isolation.
+- Frontend: new pane kind `pending_diff` shows the queued diff inline with Approve/Reject per chunk.
 
-**Schema:** `sessions.agent_id TEXT`.
+**Dependencies:** Batches 12 (gating) + 13 (events). Don’t start until both are live.
 
 -----
 
-### v1.11 — BooTerm (planned, was Batch 10)
+### Batch 15 — BooCoder runtime isolation
 
-**Depends on:** v1.1-batch3 (pane system), v1.8 (settings drawer pattern).
+**Inspiration / lift:** `OpenHands/OpenHands` (MIT).
+
+**What it gives BooCode:** per-session Docker sandbox for BooCoder writes. Closes the `/opt:ro` mount risk identified in v1.x open items.
 
 **Scope:**
 
-- New container `booterm` at `100.114.205.53:9501`. Fastify + node-pty + tmux.
-- Caddy path-based routing: `/api/term/*` + `/ws/term/*` → booterm.
-- Shared `boocode_db`.
-- Per-session tmux (`bc-<session_id>`), per-pane tmux window (`term-<pane_id>`).
-- xterm.js terminal pane. New `kind = 'terminal'` in `session_panes` CHECK.
-- PTY over binary WebSocket. Resize via `tmux resize-window`.
-- Workspace mount: `/opt/repos:/opt/repos:rw`. BooCode chat container keeps `/opt:/opt:ro`.
-- Send-to-terminal from chat: select text → right-click → “Send to terminal”.
-- tmux persistence across WS reconnects, page refreshes, container restarts.
-- No chroot/namespace isolation. Acceptable single-user homelab.
+- Per-session container spawned by BooCoder on first write. Container has only the project’s path mounted, not `/opt`.
+- Container lifecycle: spawn on first write call, idle-timeout after 30 min, recreate on resume.
+- Action execution server pattern: HTTP API inside the container, BooCoder calls in. Standard OpenHands runtime contract.
 
-**New app:** `apps/booterm/`.
+**Dependencies:** Batch 14.
 
 -----
 
-## Architecture
+### Batch 16 — Multi-provider LLM abstraction
 
-### Containers (current + planned)
+**Inspiration / lift:** `earendil-works/pi` `pi-ai` (MIT).
 
-|Container   |Port                 |Mount                              |Purpose                     |Status   |
-|------------|---------------------|-----------------------------------|----------------------------|---------|
-|`boocode`   |`100.114.205.53:9500`|`/opt:/opt:ro` + `/opt/projects:rw`|Chat + read-only tools + SPA|Live     |
-|`boocode_db`|`127.0.0.1:5500`     |`boocode_pgdata`                   |Postgres 16-alpine (shared) |Live     |
-|`booterm`   |`100.114.205.53:9501`|`/opt/repos:/opt/repos:rw`         |Terminal sessions           |v1.11    |
-|`boocoder`  |TBD                  |`/opt/repos:/opt/repos:rw`         |Write tools                 |Post-v1.x|
+**What it gives BooCode:** optional non-llama-swap inference paths (Anthropic, OpenAI, Mistral direct). Currently we have one provider (llama-swap) and the existing `streamCompletion` is hardcoded to OpenAI-compatible at that endpoint.
 
-### URL routing (target state after v1.11)
+**Scope:**
 
-```
-code.indifferentketchup.com
-├── /                           → boocode (SPA)
-├── /api/chat/*, /ws/chat/*     → boocode :9500
-├── /api/term/*, /ws/term/*     → booterm :9501
-├── /api/coder/*, /ws/coder/*   → boocoder (future)
-└── /ws/user                    → boocode :9500
-```
+- Provider abstraction: `interface LLMProvider { stream(req): AsyncIterator<Frame> }`.
+- Built-in: llama-swap (current), Anthropic, OpenAI (Codex-style).
+- Per-session `provider_id` column.
 
-### Database
-
-Single Postgres `boocode_db`. All containers share. Projects shared. Sessions container-specific.
-
-Current schema (post v1.5.1):
-
-```
-projects
-├── id UUID PK
-├── name TEXT
-├── root_path TEXT
-├── status TEXT                  (v1.2-project-ux: active | archived)
-├── archived_at TIMESTAMPTZ      (v1.2-project-ux)
-├── default_system_prompt TEXT   (v1.8)
-├── default_web_search BOOLEAN   (v1.8)
-└── created_at TIMESTAMPTZ
-
-sessions
-├── id UUID PK
-├── project_id UUID FK → projects
-├── name TEXT
-├── model TEXT
-├── system_prompt TEXT
-├── status TEXT                  (v1.2: active | archived)
-├── web_search_enabled BOOLEAN   (v1.8)
-├── agent_id TEXT                (v1.10)
-├── created_at TIMESTAMPTZ
-└── updated_at TIMESTAMPTZ
-
-chats                            (v1.2)
-├── id UUID PK
-├── session_id UUID FK → sessions
-├── name TEXT
-├── status TEXT
-├── created_at TIMESTAMPTZ
-└── updated_at TIMESTAMPTZ
-
-messages
-├── id UUID PK
-├── session_id UUID FK → sessions
-├── chat_id UUID FK → chats      (v1.2)
-├── kind TEXT                    (v1.2: regular | compact)
-├── role TEXT
-├── content TEXT
-├── tool_calls JSONB
-├── tool_results JSONB
-├── status TEXT
-├── last_seq INTEGER
-├── tokens_used INTEGER          (v1.1-batch1)
-├── ctx_used INTEGER             (v1.1-batch1)
-├── ctx_max INTEGER              (v1.1-batch1)
-├── started_at TIMESTAMPTZ       (v1.1-batch1)
-├── finished_at TIMESTAMPTZ      (v1.1-batch1)
-└── created_at TIMESTAMPTZ
-
-session_panes                    (v1.1-batch3)
-├── id UUID PK
-├── session_id UUID FK → sessions (CASCADE)
-├── position INTEGER
-├── kind TEXT CHECK (chat | file_browser | terminal)
-├── state JSONB
-└── created_at TIMESTAMPTZ
-
-settings
-├── k TEXT PK
-└── v TEXT
-```
-
-### Reusable patterns
-
-|Pattern                     |Where                                   |Used by                                                  |
-|----------------------------|----------------------------------------|---------------------------------------------------------|
-|In-app event bus            |`sessionEvents.ts`                      |All batches. Module-scope `Set<Listener>`.               |
-|Singleton hooks             |`useSidebar.ts`                         |Module-scope shared state.                               |
-|User-channel WS broker      |`broker.ts` + `useUserEvents.ts`        |Cross-tab lifecycle. One WS per tab.                     |
-|`clock_timestamp()`         |All INSERT/UPDATE                       |Never `NOW()` in new code.                               |
-|Additive schema only        |`schema.sql`                            |`ADD COLUMN IF NOT EXISTS`, `CREATE TABLE IF NOT EXISTS`.|
-|Idempotent backfills        |`schema.sql`                            |`INSERT ... WHERE NOT EXISTS`.                           |
-|`enable_thinking: false`    |`auto_name.ts`                          |Required for Qwen3 utility calls.                        |
-|`pathGuard`                 |`tools/*`, `file_ops.ts`                |Realpath + project root enforcement.                     |
-|Shared `file_ops.ts`        |`tools.ts`, `routes/projects.ts`        |Same core for inference tools and UI.                    |
-|File index (`file_index.ts`)|`routes/projects.ts`                    |`rg --files` + mtime cache.                              |
-|`useViewport`               |`hooks/useViewport.ts` (v1.6)           |matchMedia, SSR-safe.                                    |
-|`useSidebarDrawer`          |`hooks/useSidebarDrawer.tsx` (v1.6)     |Context + auto-close on route change.                    |
-|Hand-rolled long-press      |`hooks/useLongPress.ts` (v1.6)          |500ms touchstart timer, dispatches synthetic contextmenu.|
-|Hand-rolled pull-to-refresh |`hooks/usePullToRefresh.ts` (v1.6)      |80px threshold, 600ms min hold.                          |
-|Hand-rolled swipe           |`components/SwipeablePaneTab.tsx` (v1.6)|60px threshold, vertical bail at 30px.                   |
+**Status:** **Optional. Skip unless a concrete need surfaces.** llama-swap covers daily driver work.
 
 -----
 
-## Tech stack
+### Batch 17 — Workflow graphs
 
-|Layer           |Tech                                                                      |
-|----------------|--------------------------------------------------------------------------|
-|Backend         |Node 20 + Fastify + `@fastify/websocket` + `@fastify/static` + zod + `pg` |
-|Frontend        |React + Vite + Tailwind v4 + shadcn nova preset                           |
-|Inference       |llama-swap `http://100.101.41.16:8401` (OpenAI-compatible)                |
-|Search          |SearXNG `http://100.114.205.53:8888` (v1.9)                               |
-|Syntax          |Shiki (`github-dark`)                                                     |
-|Terminal        |xterm.js + node-pty + tmux (v1.11)                                        |
-|Auth            |`Remote-User` from Authelia via Caddy `forward_auth`                      |
-|Containerization|Docker Compose, Node 20-alpine, multi-stage, ripgrep apk, git apk (v1.5.1)|
-|DB              |Postgres 16-alpine, loopback `127.0.0.1:5500`                             |
-|Networking      |Tailscale mesh, Caddy (DO droplet), Authelia SSO                          |
-|Code hosting    |Gitea `git.indifferentketchup.com`                                        |
-|Tests           |vitest v3 (pinned, Vite 5 / vitest 4 incompatible)                        |
+**Inspiration / lift:** `microsoft/agent-framework` (MIT) — concepts only.
+
+**What it gives BooCode:** multi-agent coordination. Architect → Coder → Reviewer → Verifier handoffs orchestrated by a YAML-defined workflow.
+
+**Status:** **Far future.** Read agent-framework’s `docs/decisions/` ADRs. Don’t port code — Azure/.NET-heavy.
+
+**Dependencies:** Batches 12 (modes), 13 (events). Realistically a v2.x topic.
 
 -----
 
-## Known open items
+## Order of operations
 
-- **`useSessionStream` refcount.** Two ChatPanes = two WS. Apply singleton pattern. Audited in v1.6.1, queued.
-- **`/opt:/opt:ro` mount exposes all `.env` files.** Whitelist scope before BooCoder. Two-option plan documented in v1.6.1 audit; ship in v1.6.2 or v1.7.
-- **`secrets/boocode_gitea` in repo working tree.** Never committed (git-invisible via global ignore). Rotate the Gitea-side key when convenient; no repo action required.
-- **Dormant in-boolab BooCode mode.** Reference only.
-- **BooCoder container.** Post-v1.x.
+Two tracks. Pick one to drive next.
 
-**Closed since last update:**
+**Track A — Finish v1.x mobile + polish then agents:**
 
-- ~~`session_renamed` no server WS publisher~~ — server publishes via `broker.publishUser` from `routes/sessions.ts:140` (added in v1.4). Confirmed in v1.6.1 audit.
-- ~~PATCH `/api/panes/:id` lacks session-ownership check~~ — endpoint does not exist; the pane REST API was never re-introduced after v1.2 moved pane state to localStorage.
+- v1.6.2 ships (in flight)
+- **Batch 9 (agents)** — decoupled, can land next; no UI dependency on 5/6/7
+- Batches 5, 6, 7, 8 in order. Each is small, frontend-heavy, no architecture risk. Batch 7 absorbs SettingsDrawer agent entry.
+
+**Track B — Begin architect capabilities in parallel:**
+
+- Batch 11 (codecontext sidecar) — biggest single capability jump. Frontend stays the same; new tools appear to the model.
+- Batch 11b (repo health) — follow-up.
+- Batch 12 (gating) — sets up everything post-v1.x.
+
+Recommendation: ship v1.6.2, then **Batch 9 (agents)** next so the test bed exists before Track A continues. Then Track A through Batch 7. Batch 11 can run in parallel with Batches 8–10 since 11 has no UI dependency.
 
 -----
 
-## Dependency graph
+## Architecture target state
 
-```
-v1.0 (initial)
-  │
-  ▼
-v1.1-batch1 (markdown)
-  │
-  ▼
-v1.1-batch2 (sidebar)
-  │
-  ▼
-v1.1-batch3 (panes) ────────────────────────┐
-  │                                          │
-  ▼                                          │
-v1.1-batch3.5 (chips) ──────┐                │
-  │                          │                │
-  ▼                          │                │
-v1.2 (chats-in-sessions)     │                │
-  │                          │                │
-  ▼                          │                │
-v1.2-project-ux              │                │
-  │                          │                │
-  ▼                          │                │
-v1.3 (tab-close)             │                │
-  │                          │                │
-  ▼                          │                │
-v1.4 (fork+delete+header) ◄──┼────────────────┘
-  │                          │
-  ▼                          │
-v1.5 (refactor+tests+ctx)    │
-  │                          │
-  ▼                          │
-v1.5.1 (bootstrap hotfix)    │
-  │                          │
-  ▼                          │
-v1.6-mobile-pass             │
-  │                          │
-  ▼                          │
-v1.6.1-cleanup               │
-  │                          │
-  ▼                          │
-v1.6.2-mobile-ui-fixes ◄─────┘
-  │
-  ▼
-v1.7 (drag-drop) ◄── v1.1-batch3.5
-  │
-  ▼
-v1.8 (settings)
-  │
-  ├──▶ v1.9 (web search)
-  │
-  ├──▶ v1.10 (agents)
-  │
-  └──▶ v1.11 (BooTerm) ◄── v1.1-batch3
-```
+### Containers
+
+|Container    |Port                            |Mount                     |Purpose                       |Status  |
+|-------------|--------------------------------|--------------------------|------------------------------|--------|
+|`boocode`    |`100.114.205.53:9500`           |`/opt:/opt:ro`            |Chat + read-only tools + SPA  |Live    |
+|`boocode_db` |`127.0.0.1:5500`                |`boocode_pgdata` volume   |Postgres 16-alpine            |Live    |
+|`codecontext`|`100.114.205.53:8765` (internal)|project root :ro          |MCP server for architect tools|Batch 11|
+|`booterm`    |`100.114.205.53:9501`           |`/opt/repos:/opt/repos:rw`|Terminals (tmux + node-pty)   |Batch 10|
+|`boocoder`   |`100.114.205.53:9502`           |per-session sandbox       |Write tools                   |Batch 14|
+
+### Schema additions
+
+**Batch 9:** `sessions.agent_id TEXT` (nullable; references AGENTS.md by slug).
+**Batch 11:** none (codecontext stateless on disk).
+**Batch 11b:** `repo_health_cache (project_id, file_hashes_sig, payload JSONB, created_at)`.
+**Batch 12:** `sessions.tool_approval_mode`, `sessions.approved_tools`.
+**Batch 13:** `session_events`; deprecate `messages` long-tail.
+**Batch 14:** `pending_changes`.
+
+-----
+
+## Lift sources (summary)
+
+Full inventory in `boocode_code_review.md`. Headline items:
+
+|Source                                |Used for                                |Where                |
+|--------------------------------------|----------------------------------------|---------------------|
+|nmakod/codecontext (MIT, Go)          |Architect: codebase map sidecar         |Batch 11             |
+|spirituslab/codesight (MIT-ish, TS)   |Architect: repo health analyzer         |Batch 11b            |
+|Aider-AI/aider (Apache-2.0)           |Fallback `.scm` grammars (60+ languages)|Batch 11 (fallback)  |
+|continuedev/continue (Apache-2.0)     |DEFAULT_SECURITY_IGNORE_FILETYPES       |Batch 11 prep        |
+|cline/cline (Apache-2.0)              |Plan/Act mode pattern                   |Batch 12             |
+|plandex-ai/plandex (MIT)              |Pending-changes data model              |Batch 14             |
+|OpenHands/OpenHands (MIT)             |Event log + sandbox runtime             |Batches 13, 15       |
+|aimasteracc/tree-sitter-analyzer (MIT)|Outline-first response patterns         |Reference            |
+|earendil-works/pi (MIT)               |Multi-provider LLM                      |Batch 16 (optional)  |
+|rshah515/claude-code-subagents (MIT)  |Reference for builtin agent prompts     |Batch 9 (six builtins)|
+|microsoft/agent-framework (MIT)       |Workflow concepts                       |Batch 17 (far future)|
+
+-----
+
+## Decisions log
+
+- **Embeddings dropped from BooCode.** Replaced RAG with file-view tools + sidecar analyzers.
+- **Original Batch 11 (aider PageRank port) replaced** by codecontext sidecar approach.
+- **Original Batch 12 (codebase indexer w/ Harrier) removed** entirely. No embedding infrastructure in BooCode v1.x.
+- **Globstar parked** — not an architect tool, future verify-before-commit candidate only.
+- **codeprysm rejected** — embedding-based; node/edge taxonomy noted as reference if we ever build our own graph.
+- **Batch 9 decoupled from Batch 7 (2026-05-16).** AgentPicker mounts in `ChatInput.tsx` toolbar only. SettingsDrawer agent entry and Header active-agent badge moved to Batch 7. Builtin defaults shipped: six agents (Code Reviewer, Debugger, Refactorer, Architect, Security Auditor, Prompt Builder) with no `model` field — session model wins by default.
+
+## Follow-ups (post-ship docs / cleanup)
+
+- **After v1.8.2 ships:** Add explicit `max_tool_calls: 30` to all 6 agents in `/data/AGENTS.md` and `/opt/boocode/AGENTS.md`. Purely for documentation/discoverability — defaults handle behavior identically (all 6 agents use only read-only tools, default is already 30).
 
 -----
 
 ## Workflow
 
-1. Verify previous version merged to `main`.
-1. Dispatch prompt via Paseo (Claude Code runs at `/opt/boocode`).
-1. Claude Code recon → blocking questions → implement → hand back.
-1. Review hand-back in separate Claude chat (spec compliance, code quality, drift, stale code).
-1. Deploy: `docker compose up --build -d`.
-1. Smoke test per the hand-back’s plan.
-1. Sam commits manually, pushes to Gitea, merges to `main`.
-1. Next version.
+Each batch:
+
+1. Verify previous batch merged.
+2. Dispatch via Paseo to Claude Code at `/opt/boocode`.
+3. Claude Code recon → blocking questions → implement → hand back.
+4. Compliance review in separate Claude chat.
+5. Deploy: `docker compose up --build -d`.
+6. Smoke test.
+7. Sam commits and pushes.
 
 Sam reviews all diffs. Sam commits. Never git pull/push/commit on his behalf.

docker-compose.yml

@@ -15,6 +15,9 @@ services:
       # Host must `mkdir -p /opt/projects` before container start.
       - /opt/projects:/opt/projects:rw
       - ./secrets/boocode_gitea:/root/.ssh/id_ed25519:ro
+      # v1.8.1: global agents file. Host seeds it once before deploy:
+      # cp /opt/boocode/AGENTS.md /opt/boocode/data/AGENTS.md
+      - ./data:/data:ro
     depends_on:
       - boocode_db
     networks: