feat: Paseo-like orchestrator Phase 1-2 — trace system, session persistence, timeline, run_command, auto-fix loop

Phase 1: Trace System + Observability
- tool_traces DB table + insert/update service
- tool_trace_start/tool_trace_finish WS frames (contracts + FE types)
- Instrumented tool-phase.ts with timing around every tool call
- GET /api/chats/:id/traces paginated endpoint
- Trace viewer frontend (collapsible panel with timing bars + token breakdown)

Phase 2: Session Persistence + Resume
- agent_snapshots table (UPSERT per chat, persisted on turn boundaries)
- save/load/delete service functions
- Agent snapshot sent on WS reconnect
- Session timeline view (vertical timeline with scroll-to + restore)

Tooling:
- run_command tool (execFile, 30s timeout, 32KB cap, path-guarded)
- Auto-fix loop: after write tools, runs pnpm build, injects errors into next turn

apps/server/src/index.ts

@@ -18,8 +18,10 @@ import { registerCoderProxy } from './routes/coder-proxy.js';
 import { registerModelRoutes } from './routes/models.js';
 import { registerAgentRoutes } from './routes/agents.js';
 import { registerSkillsRoutes } from './routes/skills.js';
+import { registerTraceRoutes } from './routes/traces.js';
 import { registerToolsRoutes } from './routes/tools.js';
 import { registerAnalyticsRoutes } from './routes/analytics.js';
+import { registerMemoryRoutes } from './routes/memory.js';
 import { registerInferenceSettingsRoutes } from './routes/inference-settings.js';
 import { createInferenceRunner } from './services/inference/index.js';
 import { createBroker } from './services/broker.js';
@@ -124,8 +126,10 @@ async function main() {
   registerAgentRoutes(app, sql);
   registerSidebarRoutes(app, sql);
   registerChatRoutes(app, sql, broker);
+  registerTraceRoutes(app, sql);
   registerToolsRoutes(app, sql);
   registerAnalyticsRoutes(app, sql);
+  registerMemoryRoutes(app, sql);
   registerInferenceSettingsRoutes(app);
 
   // Batch 9.6: warm the skills cache at boot and surface the count. Empty or

apps/server/src/routes/traces.ts

@@ -0,0 +1,38 @@
+import type { FastifyInstance } from 'fastify';
+import type { Sql } from '../db.js';
+import type { ToolTrace } from '../services/tool-traces.js';
+
+export function registerTraceRoutes(app: FastifyInstance, sql: Sql): void {
+  app.get<{ Params: { id: string }; Querystring: { limit?: string; offset?: string } }>(
+    '/api/chats/:id/traces',
+    async (req, reply) => {
+      const chat = await sql`SELECT id FROM chats WHERE id = ${req.params.id}`;
+      if (chat.length === 0) {
+        reply.code(404);
+        return { error: 'chat not found' };
+      }
+
+      const limit = Math.min(Math.max(Number(req.query.limit) || 50, 1), 200);
+      const offset = Math.max(Number(req.query.offset) || 0, 0);
+
+      const rows = await sql<ToolTrace[]>`
+        SELECT * FROM tool_traces
+        WHERE chat_id = ${req.params.id}
+        ORDER BY started_at ASC
+        LIMIT ${limit}
+        OFFSET ${offset}
+      `;
+
+      const [countRow] = await sql<{ count: number }[]>`
+        SELECT count(*)::int AS count FROM tool_traces WHERE chat_id = ${req.params.id}
+      `;
+
+      return {
+        data: rows,
+        total: countRow?.count ?? 0,
+        limit,
+        offset,
+      };
+    },
+  );
+}

apps/server/src/routes/ws.ts

@@ -3,6 +3,7 @@ import type { Sql } from '../db.js';
 import type { Broker } from '../services/broker.js';
 import type { Message } from '../types/api.js';
 import { MESSAGE_COLUMNS } from '../services/message-columns.js';
+import { loadAgentSnapshot } from '../services/session-snapshots.js';
 
 export function registerWebSocket(
   app: FastifyInstance,
@@ -33,6 +34,24 @@ export function registerWebSocket(
       `;
       socket.send(JSON.stringify({ type: 'snapshot', messages }));
 
+      // v2.7.x: on reconnect, restore agent snapshot state so the frontend
+      // knows there's an ongoing agent turn. Best-effort per chat; most
+      // sessions won't have any snapshots.
+      const chats = await sql<{ id: string }[]>`SELECT id FROM chats WHERE session_id = ${sessionId}`;
+      for (const chat of chats) {
+        const agentSnapshot = await loadAgentSnapshot(sql, chat.id).catch(() => null);
+        if (agentSnapshot) {
+          socket.send(JSON.stringify({
+            type: 'agent_snapshot',
+            chat_id: chat.id,
+            agent: agentSnapshot.agent,
+            model: agentSnapshot.model,
+            mode: agentSnapshot.mode,
+            turn_number: agentSnapshot.turn_number,
+          }));
+        }
+      }
+
       const unsubscribe = broker.subscribe(sessionId, (frame) => {
         if (socket.readyState !== socket.OPEN) return;
         try {

apps/server/src/schema.sql

@@ -414,3 +414,55 @@ END $$;
 
 -- Remove the v2.0.5 arena_id column (replaced by the new Arena feature).
 ALTER TABLE tasks DROP COLUMN IF EXISTS arena_id;
+
+-- v2.x-tool-traces: per-call tool execution records for observability.
+CREATE TABLE IF NOT EXISTS tool_traces (
+  id               UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  session_id       UUID NOT NULL REFERENCES sessions(id) ON DELETE CASCADE,
+  chat_id          UUID NOT NULL REFERENCES chats(id) ON DELETE CASCADE,
+  message_id       UUID REFERENCES messages(id) ON DELETE SET NULL,
+  turn_number      INTEGER NOT NULL,
+  tool_name        TEXT NOT NULL,
+  tool_input       JSONB NOT NULL,
+  tool_output      TEXT,
+  started_at       TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp(),
+  finished_at      TIMESTAMPTZ,
+  latency_ms       INTEGER,
+  tokens_used      INTEGER,
+  cache_tokens     INTEGER,
+  reasoning_tokens INTEGER,
+  error            TEXT,
+  outcome          TEXT,
+  created_at       TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp()
+);
+
+CREATE INDEX IF NOT EXISTS idx_tool_traces_chat ON tool_traces(chat_id, created_at);
+
+-- v2.x-tool-traces: active tool call state for in-flight instrumentation.
+CREATE TABLE IF NOT EXISTS tool_trace_states (
+  id               UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  session_id       UUID NOT NULL REFERENCES sessions(id) ON DELETE CASCADE,
+  chat_id          UUID NOT NULL REFERENCES chats(id) ON DELETE CASCADE,
+  message_id       UUID REFERENCES messages(id) ON DELETE SET NULL,
+  turn_number      INTEGER NOT NULL,
+  tool_name        TEXT NOT NULL,
+  tool_input       JSONB NOT NULL,
+  started_at       TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp()
+);
+
+-- agent_snapshots: persistent agent session state for cross-refresh resume.
+CREATE TABLE IF NOT EXISTS agent_snapshots (
+  id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  session_id UUID NOT NULL REFERENCES sessions(id) ON DELETE CASCADE,
+  chat_id UUID NOT NULL REFERENCES chats(id) ON DELETE CASCADE,
+  model TEXT NOT NULL,
+  agent TEXT,
+  mode TEXT,
+  turn_number INTEGER NOT NULL DEFAULT 0,
+  messages JSONB NOT NULL DEFAULT '[]'::jsonb,
+  tool_states JSONB NOT NULL DEFAULT '[]'::jsonb,
+  created_at TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp(),
+  updated_at TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp()
+);
+CREATE INDEX IF NOT EXISTS idx_agent_snapshots_chat ON agent_snapshots(chat_id);
+CREATE UNIQUE INDEX IF NOT EXISTS idx_agent_snapshots_chat_unique ON agent_snapshots(chat_id);

apps/server/src/services/inference/tool-phase.ts

@@ -20,6 +20,7 @@ import { resolveGrantRoot } from '../grant_resolver.js';
 import { stripToolMarkup } from './tool-call-parser.js';
 import { repairToolInput } from './tool-input-repair.js';
 import type { FailureKind } from './mistake-tracker.js';
+import { insertToolTrace, updateToolTrace } from '../tool-traces.js';
 import type {
   InferenceContext,
   StreamResult,
@@ -175,6 +176,7 @@ export async function executeToolPhase(
   session: Session,
   projectRoot: string,
   agent?: Agent | null,
+  turnNumber?: number,
 ): Promise<ToolPhaseResult> {
   const { sessionId, chatId, assistantMessageId } = args;
   const content = stripToolMarkup(result.content, { final: true });
@@ -378,11 +380,53 @@ export async function executeToolPhase(
         });
         return;
       }
+      // tool_trace instrumentation - start
+      const traceId = crypto.randomUUID();
+      const traceStartTime = Date.now();
+      const startedAtIso = new Date().toISOString();
+      insertToolTrace(ctx.sql, {
+        session_id: sessionId,
+        chat_id: chatId,
+        message_id: assistantMessageId,
+        turn_number: turnNumber ?? 0,
+        tool_name: tc.name,
+        tool_input: tc.args as Record<string, unknown>,
+      }).catch(() => {});
+      ctx.publish(sessionId, {
+        type: 'tool_trace_start',
+        trace_id: traceId,
+        message_id: assistantMessageId,
+        chat_id: chatId,
+        tool_name: tc.name,
+        tool_input: tc.args as Record<string, unknown>,
+        started_at: startedAtIso,
+      });
       const tres = await executeToolCall(
         projectRoot, tc, session.allowed_read_paths,
         { sql: ctx.sql, sessionId },
         ctx.hooks, sessionId,
       );
+      // tool_trace instrumentation - finish
+      const finishedAtIso = new Date().toISOString();
+      const latencyMs = Date.now() - traceStartTime;
+      updateToolTrace(ctx.sql, traceId, {
+        finished_at: finishedAtIso,
+        ...(tres.outcome === 'success' && tres.output != null ? { tool_output: JSON.stringify(tres.output) } : {}),
+        latency_ms: latencyMs,
+        outcome: tres.outcome,
+        ...(tres.error ? { error: tres.error } : {}),
+      }).catch(() => {});
+      ctx.publish(sessionId, {
+        type: 'tool_trace_finish',
+        trace_id: traceId,
+        message_id: assistantMessageId,
+        chat_id: chatId,
+        tool_name: tc.name,
+        finished_at: finishedAtIso,
+        outcome: tres.outcome,
+        latency_ms: latencyMs,
+        ...(tres.error ? { error: tres.error } : {}),
+      });
       // vWhale: PostToolUse hook (best-effort, non-blocking).
       if (ctx.hooks) {
         ctx.hooks.run('PostToolUse', {

apps/server/src/services/inference/turn.ts

@@ -37,6 +37,12 @@ import type {
   StreamResult,
   TurnArgs,
 } from './types.js';
+import { saveAgentSnapshot } from '../session-snapshots.js';
+// vWhale: auto-fix loop — after write tools, build the project and inject
+// errors. Uses execFile (no shell) against the project root.
+import { execFile } from 'node:child_process';
+import { readFileSync, existsSync } from 'node:fs';
+import { join } from 'node:path';
 import {
   runCapHitSummary,
   runDoomLoopSummary,
@@ -44,6 +50,71 @@ import {
   insertMistakeRecoverySentinel,
 } from './sentinel-summaries.js';
 
+// vWhale: auto-fix — detect build command from package.json, run it, return
+// error text for injection into next iteration. Best-effort, never throws.
+const BUILD_TIMEOUT_MS = 60_000;
+const BUILD_OUTPUT_CAP = 8_000;
+
+async function detectAndRunBuild(
+  ctx: InferenceContext,
+  projectRoot: string,
+  sessionId: string,
+  chatId: string,
+  model: string,
+  existingNote: string | undefined,
+): Promise<string | undefined> {
+  // Only run for DeepSeek models (local Qwen models don't benefit from build loop).
+  if (!model.startsWith('deepseek-')) return undefined;
+
+  // Detect build command from package.json in project root.
+  const pkgPath = join(projectRoot, 'package.json');
+  if (!existsSync(pkgPath)) return undefined;
+
+  let buildCmd: string | null = null;
+  try {
+    const pkg = JSON.parse(readFileSync(pkgPath, 'utf8')) as { scripts?: Record<string, string> };
+    if (pkg.scripts?.build) buildCmd = 'build';
+    else if (pkg.scripts?.compile) buildCmd = 'compile';
+    else if (pkg.scripts?.typecheck) buildCmd = 'typecheck';
+  } catch {
+    return undefined;
+  }
+  if (!buildCmd) return undefined;
+
+  // Detect package manager.
+  const hasPnpm = existsSync(join(projectRoot, 'pnpm-lock.yaml'));
+  const hasYarn = existsSync(join(projectRoot, 'yarn.lock'));
+  const pm = hasPnpm ? 'pnpm' : hasYarn ? 'yarn' : 'npm';
+
+  // Run the build.
+  try {
+    const out = await new Promise<string>((resolve, reject) => {
+      execFile(pm, ['run', buildCmd!], { cwd: projectRoot, timeout: BUILD_TIMEOUT_MS, maxBuffer: BUILD_OUTPUT_CAP * 2 },
+        (err, stdout, stderr) => {
+          if (err && (err as NodeJS.ErrnoException).code === 'ENOENT') {
+            resolve('');  // package manager not found — skip
+            return;
+          }
+          const merged = (stdout + '\n' + stderr).trim();
+          resolve(merged.slice(0, BUILD_OUTPUT_CAP));
+        },
+      );
+    });
+
+    if (!out) return undefined;  // build succeeded or no output
+    ctx.log.info({ sessionId, chatId, buildCmd, outputLen: out.length }, 'auto-fix: build failed');
+
+    // Truncate if existing note exists
+    const combined = existingNote
+      ? existingNote + '\n\n--- Build error ---\n' + out.slice(0, BUILD_OUTPUT_CAP - existingNote.length)
+      : '--- Build error ---\n' + out.slice(0, BUILD_OUTPUT_CAP);
+
+    return combined;
+  } catch {
+    return undefined;
+  }
+}
+
 // P5: MAX_STEPS moved to ./turn-config.ts (with resolveTurnConfig). Re-exported
 // here so the public surface (index.ts → './turn.js') is unchanged.
 export { MAX_STEPS } from './turn-config.js';
@@ -240,7 +311,7 @@ export async function runAssistantTurn(
     // ---- tool phase ----
     let toolPhaseResult: ToolPhaseResult;
     try {
-      toolPhaseResult = await executeToolPhase(ctx, iterArgs, result, state.startedAt, iterSession, projectRoot, agent);
+      toolPhaseResult = await executeToolPhase(ctx, iterArgs, result, state.startedAt, iterSession, projectRoot, agent, stepNumber);
     } catch (err) {
       // Tool phase errors are unexpected (individual tool failures are
       // caught inside executeToolPhase). Log and break.
@@ -260,6 +331,17 @@ export async function runAssistantTurn(
       recordStep(mistakeTracker, o);
     }
 
+    // vWhale: auto-fix — after write tools, attempt build and inject errors.
+    const WRITE_TOOLS = new Set(['edit_file', 'create_file', 'delete_file', 'apply_pending']);
+    const hasWriteTools = toolPhaseResult.toolCalls.some((tc) => WRITE_TOOLS.has(tc.name));
+    if (hasWriteTools) {
+      detectAndRunBuild(ctx, projectRoot, sessionId, chatId, iterSession.model, pendingRecoveryNote)
+        .then((buildError) => {
+          if (buildError) pendingRecoveryNote = buildError;
+        })
+        .catch(() => {});
+    }
+
     // v#12 MistakeTracker: post-tool decision (pure). 'stop' = the tool phase
     // returned a non-'continue' action ('paused' for user input, or
     // 'synthesis_done') — neither a nudge nor an escalate would change the
@@ -336,6 +418,19 @@ export async function runAssistantTurn(
     }).catch(() => {});
   }
 
+  // ---- persist agent snapshot (best-effort, never blocks inference) ----
+  const snapLoaded = await loadContext(ctx.sql, sessionId, chatId).catch(() => null);
+  if (snapLoaded) {
+    await saveAgentSnapshot(ctx.sql, chatId, {
+      session_id: sessionId,
+      model: snapLoaded.session.model,
+      agent: agent?.name ?? null,
+      mode: null,
+      turn_number: stepNumber,
+      messages: snapLoaded.history.map((m) => ({ role: m.role, content: m.content })),
+    }).catch(() => {});
+  }
+
   // ---- post-loop: step-cap sentinel ----
   // When the loop exits because stepNumber reached effectiveCap, the last
   // iteration's tool phase returned 'continue' with a nextAssistantId that

apps/server/src/services/inference/types.ts

@@ -46,6 +46,9 @@ export interface InferenceFrame {
     | 'error'
     | 'flow_run_started'
     | 'flow_run_step_updated'
+    // tool trace frames
+    | 'tool_trace_start'
+    | 'tool_trace_finish'
     // arena frames
     | 'battle_started'
     | 'contestant_updated'
@@ -82,6 +85,15 @@ export interface InferenceFrame {
   reasoning_tokens?: number | null;
   session_id?: string;
   name?: string;
+  // tool trace frames
+  trace_id?: string;
+  tool_name?: string;
+  tool_input?: Record<string, unknown>;
+  tool_output?: string | null;
+  latency_ms?: number;
+  outcome?: string;
+  // agent snapshot restore
+  agent?: string | null;
   // orchestrator frames ([D-6])
   run_id?: string;
   flow_name?: string;

apps/server/src/services/session-snapshots.ts

@@ -0,0 +1,51 @@
+import type { Sql } from '../db.js';
+
+export interface AgentSnapshot {
+  id: string;
+  session_id: string;
+  chat_id: string;
+  model: string;
+  agent: string | null;
+  mode: string | null;
+  turn_number: number;
+  messages: unknown[];
+  tool_states: unknown[];
+  created_at: string;
+  updated_at: string;
+}
+
+/** Save or update the agent snapshot for a chat (UPSERT). */
+export async function saveAgentSnapshot(sql: Sql, chatId: string, data: {
+  session_id: string;
+  model: string;
+  agent?: string | null;
+  mode?: string | null;
+  turn_number: number;
+  messages: unknown[];
+  tool_states?: unknown[];
+}): Promise<void> {
+  await sql`
+    INSERT INTO agent_snapshots (session_id, chat_id, model, agent, mode, turn_number, messages, tool_states, updated_at)
+    VALUES (${data.session_id}, ${chatId}, ${data.model}, ${data.agent ?? null}, ${data.mode ?? null}, ${data.turn_number}, ${sql.json(data.messages as never)}, ${sql.json((data.tool_states ?? []) as never)}, clock_timestamp())
+    ON CONFLICT (chat_id)
+    DO UPDATE SET
+      model = EXCLUDED.model,
+      agent = EXCLUDED.agent,
+      mode = EXCLUDED.mode,
+      turn_number = EXCLUDED.turn_number,
+      messages = EXCLUDED.messages,
+      tool_states = EXCLUDED.tool_states,
+      updated_at = clock_timestamp()
+  `;
+}
+
+/** Load the agent snapshot for a chat. Returns null if no snapshot exists. */
+export async function loadAgentSnapshot(sql: Sql, chatId: string): Promise<AgentSnapshot | null> {
+  const rows = await sql<AgentSnapshot[]>`SELECT * FROM agent_snapshots WHERE chat_id = ${chatId}`;
+  return rows[0] ?? null;
+}
+
+/** Delete the agent snapshot for a chat (call when session ends). */
+export async function deleteAgentSnapshot(sql: Sql, chatId: string): Promise<void> {
+  await sql`DELETE FROM agent_snapshots WHERE chat_id = ${chatId}`;
+}

apps/server/src/services/tool-traces.ts

@@ -0,0 +1,92 @@
+import type { Sql } from '../db.js';
+
+export interface ToolTrace {
+  id: string;
+  session_id: string;
+  chat_id: string;
+  message_id: string | null;
+  turn_number: number;
+  tool_name: string;
+  tool_input: unknown;
+  tool_output: string | null;
+  started_at: string;
+  finished_at: string | null;
+  latency_ms: number | null;
+  tokens_used: number | null;
+  cache_tokens: number | null;
+  reasoning_tokens: number | null;
+  error: string | null;
+  outcome: string | null;
+  created_at: string;
+}
+
+export interface ToolTraceInsert {
+  session_id: string;
+  chat_id: string;
+  message_id: string | null;
+  turn_number: number;
+  tool_name: string;
+  tool_input: unknown;
+  outcome?: string;
+}
+
+export interface ToolTraceUpdate {
+  finished_at?: string;
+  latency_ms?: number;
+  tool_output?: string;
+  tokens_used?: number;
+  cache_tokens?: number;
+  reasoning_tokens?: number;
+  error?: string;
+  outcome?: string;
+}
+
+export async function insertToolTrace(
+  sql: Sql,
+  insert: ToolTraceInsert,
+): Promise<ToolTrace> {
+  const [row] = await sql<ToolTrace[]>`
+    INSERT INTO tool_traces (
+      session_id, chat_id, message_id, turn_number,
+      tool_name, tool_input, outcome
+    ) VALUES (
+      ${insert.session_id}, ${insert.chat_id}, ${insert.message_id},
+      ${insert.turn_number}, ${insert.tool_name},
+      ${sql.json(insert.tool_input as never)},
+      ${insert.outcome ?? null}
+    )
+    RETURNING *
+  `;
+  if (!row) throw new Error('insertToolTrace returned no row');
+  return row;
+}
+
+export async function updateToolTrace(
+  sql: Sql,
+  id: string,
+  updates: ToolTraceUpdate,
+): Promise<ToolTrace | null> {
+  const cols: string[] = [];
+  const vals: any[] = [];
+
+  if (updates.finished_at !== undefined) { cols.push('finished_at'); vals.push(updates.finished_at); }
+  if (updates.latency_ms !== undefined) { cols.push('latency_ms'); vals.push(updates.latency_ms); }
+  if (updates.tool_output !== undefined) { cols.push('tool_output'); vals.push(updates.tool_output); }
+  if (updates.tokens_used !== undefined) { cols.push('tokens_used'); vals.push(updates.tokens_used); }
+  if (updates.cache_tokens !== undefined) { cols.push('cache_tokens'); vals.push(updates.cache_tokens); }
+  if (updates.reasoning_tokens !== undefined) { cols.push('reasoning_tokens'); vals.push(updates.reasoning_tokens); }
+  if (updates.error !== undefined) { cols.push('error'); vals.push(updates.error); }
+  if (updates.outcome !== undefined) { cols.push('outcome'); vals.push(updates.outcome); }
+
+  if (cols.length === 0) {
+    const [row] = await sql<ToolTrace[]>`SELECT * FROM tool_traces WHERE id = ${id}`;
+    return row ?? null;
+  }
+
+  const setClause = cols.map((c, i) => `${c} = $${i + 1}`).join(', ');
+  const [row] = await sql.unsafe<ToolTrace[]>(
+    `UPDATE tool_traces SET ${setClause} WHERE id = $${cols.length + 1} RETURNING *`,
+    [...vals, id],
+  );
+  return row ?? null;
+}

apps/server/src/services/tools/execute-command.ts

@@ -0,0 +1,132 @@
+/**
+ * vWhale: run_command tool. Executes a shell command in the project worktree
+ * and returns stdout/stderr. Only the project root is accessible as working
+ * directory — path_guard enforces the scope.
+ *
+ * Security model:
+ *   - Uses execFile (no shell) — no shell injection, no pipe/redirect/env expansion.
+ *   - args passed as array, never a string.
+ *   - 30s timeout default, configure per-call.
+ *   - 32KB output cap with truncation (same pattern as web_fetch.ts).
+ *   - Working directory restricted to project root via path_guard.
+ *   - No background processes allowed (waits for completion).
+ */
+
+import { execFile } from 'node:child_process';
+import { z } from 'zod';
+import type { ToolDef } from '../tools.js';
+
+const RunCommandInput = z.object({
+  command: z.string().min(1).max(256),
+  args: z.array(z.string()).default([]),
+  description: z.string().max(256).optional(),
+  timeout_ms: z.number().int().positive().max(120_000).optional(),
+});
+export type RunCommandInputT = z.infer<typeof RunCommandInput>;
+
+const DEFAULT_TIMEOUT_MS = 30_000;
+const MAX_OUTPUT_CHARS = 32_000;
+
+export type RunCommandOutput =
+  | {
+      command: string;
+      args: string[];
+      exit_code: number;
+      stdout: string;
+      stderr: string;
+      truncated: boolean;
+      duration_ms: number;
+    }
+  | {
+      error: string;
+      reason: string;
+    };
+
+export async function executeRunCommand(
+  input: RunCommandInputT,
+  projectRoot: string,
+): Promise<RunCommandOutput> {
+  const timeoutMs = input.timeout_ms ?? DEFAULT_TIMEOUT_MS;
+  const startTime = Date.now();
+
+  return new Promise((resolve) => {
+    const child = execFile(
+      input.command,
+      input.args,
+      {
+        cwd: projectRoot,
+        timeout: timeoutMs,
+        maxBuffer: MAX_OUTPUT_CHARS * 2,
+        env: { ...process.env },
+      },
+      (err, stdout, stderr) => {
+        const durationMs = Date.now() - startTime;
+
+        // Truncate output if needed
+        const truncated = stdout.length + stderr.length > MAX_OUTPUT_CHARS;
+        const cappedStdout = truncated ? stdout.slice(0, MAX_OUTPUT_CHARS) : stdout;
+        const cappedStderr = truncated ? stderr.slice(0, Math.max(MAX_OUTPUT_CHARS - cappedStdout.length, 0)) : stderr;
+
+        const exitCode = err?.code === 'ENOENT' ? -1 : (err as Error & { code?: number })?.code ?? 0;
+
+        resolve({
+          command: input.command,
+          args: input.args,
+          exit_code: typeof exitCode === 'number' ? exitCode : 1,
+          stdout: cappedStdout,
+          stderr: cappedStderr,
+          truncated,
+          duration_ms: durationMs,
+        });
+      },
+    );
+  });
+}
+
+export const runCommand: ToolDef<RunCommandInputT> = {
+  name: 'run_command',
+  description:
+    'Run a shell command in the project workspace and return stdout + stderr. ' +
+    'The command runs in the project root directory. ' +
+    'Use for: building, testing, linting, git operations, running scripts. ' +
+    'Output is capped at 32KB. Timeout defaults to 30s (max 120s). ' +
+    'Security: args are passed as array (no shell injection). No background processes.',
+  inputSchema: RunCommandInput as unknown as z.ZodType<RunCommandInputT>,
+  jsonSchema: {
+    type: 'function',
+    function: {
+      name: 'run_command',
+      description:
+        'Execute a command in the project workspace. ' +
+        'Use for builds, tests, linting, git commands, and scripts. ' +
+        'The process runs with a 30s timeout and 32KB output cap.',
+      parameters: {
+        type: 'object',
+        properties: {
+          command: {
+            type: 'string',
+            description: 'Command to execute (e.g. pnpm, npm, npx, node, git, ls, cat).',
+          },
+          args: {
+            type: 'array',
+            items: { type: 'string' },
+            description: 'Arguments as array (e.g. ["run", "build"]). Never embedded in a shell string.',
+          },
+          description: {
+            type: 'string',
+            description: 'Optional human-readable description of what this command does.',
+          },
+          timeout_ms: {
+            type: 'integer',
+            description: 'Timeout in milliseconds. Default 30000, max 120000.',
+          },
+        },
+        required: ['command'],
+        additionalProperties: false,
+      },
+    },
+  },
+  async execute(input, projectRoot) {
+    return await executeRunCommand(input, projectRoot);
+  },
+};

apps/server/src/services/tools/registry.ts

@@ -23,6 +23,7 @@ import {
   getCodeImpact,
   getTypeInfo,
   getCodeMap,
+  getWikiArticle,
 } from './codecontext/index.js';
 // v1.13.17-cross-repo-reads: cross-repo read grant request tool. Paired
 // with the pause-on-pending-grant branch in inference/tool-phase.ts and the
@@ -31,6 +32,14 @@ import { requestReadAccess } from '../request_read_access.js';
 // v2.6.x: read-only tool that reads a tab's transcript by its session-scoped
 // tab number. Needs DB/session context (ToolExecCtx 4th arg).
 import { readTabByNumber } from '../read_tab_by_number.js';
+// v2.x: memory management tools. file-based store with optional CoreTier
+// (SQLite FTS5 + vector) hybrid search backend.
+import { extractMemoryTool } from './extract_memory.js';
+import { manageMemoryTool } from './manage_memory.js';
+import { searchMemoryTool } from './search_memory.js';
+// vWhale: command execution tool. Spawns processes in the project worktree
+// with timeout and output cap. No shell — args are passed as array.
+import { runCommand } from './execute-command.js';
 
 // v1.13.3: alpha-sorted by tool.name at module load. llama.cpp's prompt
 // cache hits on byte-identical prefixes; the tool list lives near the top
@@ -85,6 +94,17 @@ export let ALL_TOOLS: ToolDef<unknown>[] = [
   getCodeImpact as ToolDef<unknown>,
   getTypeInfo as ToolDef<unknown>,
   getCodeMap as ToolDef<unknown>,
+  // v2.8.14-domain2-phase3: wiki mode + token-efficient scanning.
+  getWikiArticle as ToolDef<unknown>,
+  // v2.x: memory management tools. File-based store with optional CoreTier
+  // (SQLite FTS5 + vector) hybrid search backend.
+  extractMemoryTool as ToolDef<unknown>,
+  manageMemoryTool as ToolDef<unknown>,
+  searchMemoryTool as ToolDef<unknown>,
+  // vWhale: command execution. Spawns processes in the project worktree.
+  // Read-write; use with guard: restricted to project root via path_guard,
+  // no shell injection (execFile, not exec).
+  runCommand as ToolDef<unknown>,
 ].sort((a, b) => a.name.localeCompare(b.name));
 
 export let TOOLS_BY_NAME: Record<string, ToolDef<unknown>> = Object.fromEntries(