feat(workflows): grant codebase-memory MCP tools to code-intel stages

Explicit per-stage grants (least-privilege, invariant #5) for the mounted
codebase-memory MCP side-car:
- role_pipeline: discovery bootstraps the graph (index_repository) + grounds;
  analyst/architect/decomposer/implementer/reviewer get read-only query tools
  (search_code/search_graph/get_architecture/trace_path/get_code_snippet)
  scoped to each role. NOTE: architect flips from pure-reasoning to tool-calling.
- review_loop implement+review and task_planning planner get read-only queries.

Tools are approval-gated at T2 (server default in config.toml [[mcp]]).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

examples/workflows/review_loop.toml

@@ -20,7 +20,12 @@ start = "implement"
 id = "implement"
 prompt = "prompts/implement.md"
 produces = [{ name = "patch", kind = "file_written" }]
-allowed_tools = ["file_write", "task_create", "task_update", "task_context", "task_search"]
+allowed_tools = [
+    "file_write", "task_create", "task_update", "task_context", "task_search",
+    "mcp__codebase-memory__search_code",
+    "mcp__codebase-memory__get_code_snippet",
+    "mcp__codebase-memory__trace_path",
+]
 token_budget = 8192
 max_retries = 3
 
@@ -31,7 +36,11 @@ id = "review"
 prompt = "prompts/review.md"
 needs = ["patch"]
 produces = [{ name = "review_report", kind = "review_report" }]
-allowed_tools = ["task_context", "task_update"]
+allowed_tools = [
+    "task_context", "task_update",
+    "mcp__codebase-memory__search_code",
+    "mcp__codebase-memory__trace_path",
+]
 token_budget = 8192
 max_retries = 3