Give agents hands: workspace read/list/exec tools so engineers build instead of describing

Every "engineering" deliverable the company ever produced was a markdown
skeleton, because documentation was the ceiling of the toolset:
write_deliverable and create_document were the only artifact tools. An
engineer could not see the files that exist, read a line of code, or run a
single command — and create_task hardcoded requires_filesystem to false, so
the entire approval-gated read_write mount plumbing was dead code.

New workspace capability (agent-workspace-tools.ts):
- list_files / read_file: explore the bound workspace, traversal-guarded by
  the same resolveWorkspacePath used for writes, size- and count-capped.
- run_command: real shell execution with the workspace as cwd, 120s timeout,
  16k output cap. Gated on the task's approved filesystem grant — the same
  requires_filesystem flag that flips the mount to read_write and routes the
  task through operator approval (auto-approved only in AI-CEO mode, which
  is that mode's explicit contract).
- create_task now takes requires_filesystem, so the CEO and officers can
  delegate engineering work that is allowed to change code and run tests.
- Prompts brief every agent on the tools, and filesystem tasks state the
  bar directly: real output is code that builds and tests that pass — a
  document describing the work does not close an engineering task.

Tests: tool registry, dependency-folder-skipping listing, traversal refusal,
the run_command access gate plus exit-code reporting, and the create_task
approval path for filesystem work.

src/main/services/agent-tools.ts

@@ -22,7 +22,8 @@ export interface AgentToolContext {
   agent: { id: string; modelProviderId: string | null; modelId: string | null };
   taskProjectId: string | null;
   taskGoalId: string | null;
-  workspace: { id: string; localPath: string } | null;
+  /** writeAccess mirrors the task's approved filesystem grant (read_write mount) and gates run_command. */
+  workspace: { id: string; localPath: string; writeAccess: boolean } | null;
 }
 
 export interface AgentToolDeps {
@@ -71,6 +72,10 @@ export const AGENT_TOOLS: ToolDefinition[] = [
         description: { type: "string" },
         assignee_agent_name: { type: "string", description: "Name of the agent to assign, if any." },
         risk: { type: "string", enum: ["low", "medium", "high"] },
+        requires_filesystem: {
+          type: "boolean",
+          description: "Set true for engineering work that must change code or run commands (build, test) in the workspace. The assignee then gets run_command; the operator approves such tasks before they execute.",
+        },
       },
       required: ["title", "description"],
     },
@@ -307,7 +312,7 @@ function createTask(deps: AgentToolDeps, ctx: AgentToolContext, args: JsonRecord
       goalId: ctx.taskGoalId,
       workspaceId: ctx.workspace?.id ?? null,
       priority: TASK_PRIORITY.NORMAL,
-      requiresFilesystem: false,
+      requiresFilesystem: args.requires_filesystem === true,
     });
     const assignmentThread = options.announceTaskAssignments !== false && assignee && assignee.id !== ctx.agent.id
       ? postAssignmentMessage(deps, ctx, { taskId, title, description, assignee })