refactor: optimize token usage, deduplicate code, fix bugs across agents

Token reduction (~40% per session, ~2.3M fewer tokens per 200-feature project):
- Agent-type-specific tool lists: coding 9, testing 5, init 5 (was 19 for all)
- Right-sized max_turns: coding 300, testing 100 (was 1000 for all)
- Trimmed coding prompt template (~150 lines removed)
- Streamlined testing prompt with batch support
- YOLO mode now strips browser testing instructions from prompt
- Added Grep, WebFetch, WebSearch to expand project session

Performance improvements:
- Rate limit retries start at ~15s with jitter (was fixed 60s)
- Post-spawn delay reduced to 0.5s (was 2s)
- Orchestrator consolidated to 1 DB query per loop (was 5-7)
- Testing agents batch 3 features per session (was 1)
- Smart context compaction preserves critical state, discards noise

Bug fixes:
- Removed ghost feature_release_testing MCP tool (wasted tokens every test session)
- Forward all 9 Vertex AI env vars to chat sessions (was missing 3)
- Fix DetachedInstanceError risk in test batch ORM access
- Prevent duplicate testing of same features in parallel mode

Code deduplication:
- _get_project_path(): 9 copies -> 1 shared utility (project_helpers.py)
- validate_project_name(): 9 copies -> 2 variants in 1 file (validation.py)
- ROOT_DIR: 10 copies -> 1 definition (chat_constants.py)
- API_ENV_VARS: 4 copies -> 1 source of truth (env_constants.py)

Security hardening:
- Unified sensitive directory blocklist (14 dirs, was two divergent lists)
- Cached get_blocked_paths() for O(1) directory listing checks
- Terminal security warning when ALLOW_REMOTE=1 exposes WebSocket
- 20 new security tests for EXTRA_READ_PATHS blocking
- Extracted _validate_command_list() and _validate_pkill_processes() helpers

Type safety:
- 87 mypy errors -> 0 across 58 source files
- Installed types-PyYAML for proper yaml stub types
- Fixed SQLAlchemy Column[T] coercions across all routers

Dead code removed:
- 13 files deleted (~2,679 lines): unused UI components, debug logs, outdated docs
- 7 unused npm packages removed (Radix UI components with 0 imports)
- AgentAvatar.tsx reduced from 615 -> 119 lines (SVGs extracted to mascotData.tsx)

New CLI options:
- --testing-batch-size (1-5) for parallel mode test batching
- --testing-feature-ids for direct multi-feature testing

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

api/dependency_resolver.py

@@ -7,6 +7,7 @@ Includes cycle detection, validation, and helper functions for dependency manage
 """
 
 import heapq
+from collections import deque
 from typing import TypedDict
 
 # Security: Prevent DoS via excessive dependencies
@@ -301,19 +302,20 @@ def compute_scheduling_scores(features: list[dict]) -> dict[int, float]:
 
     # Calculate depths via BFS from roots
     # Use visited set to prevent infinite loops from circular dependencies
+    # Use deque for O(1) popleft instead of list.pop(0) which is O(n)
     depths: dict[int, int] = {}
     visited: set[int] = set()
     roots = [f["id"] for f in features if not parents[f["id"]]]
-    queue = [(root, 0) for root in roots]
-    while queue:
-        node_id, depth = queue.pop(0)
+    bfs_queue: deque[tuple[int, int]] = deque((root, 0) for root in roots)
+    while bfs_queue:
+        node_id, depth = bfs_queue.popleft()
         if node_id in visited:
             continue  # Skip already visited nodes (handles cycles)
         visited.add(node_id)
         depths[node_id] = depth
         for child_id in children[node_id]:
             if child_id not in visited:
-                queue.append((child_id, depth + 1))
+                bfs_queue.append((child_id, depth + 1))
 
     # Handle orphaned nodes (shouldn't happen but be safe)
     for f in features: