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- 13 files deleted (~2,679 lines): unused UI components, debug logs, outdated docs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>

test_rate_limit_utils.py

@@ -162,11 +162,20 @@ class TestBackoffFunctions(unittest.TestCase):
     """Test backoff calculation functions from rate_limit_utils."""
 
     def test_rate_limit_backoff_sequence(self):
-        """Test that rate limit backoff follows expected exponential sequence."""
-        expected = [60, 120, 240, 480, 960, 1920, 3600, 3600]  # Caps at 3600
-        for retries, expected_delay in enumerate(expected):
+        """Test that rate limit backoff follows expected exponential sequence with jitter.
+
+        Base formula: 15 * 2^retries with 0-30% jitter.
+        Base values: 15, 30, 60, 120, 240, 480, 960, 1920, 3600, 3600
+        With jitter the result should be in [base, base * 1.3].
+        """
+        base_values = [15, 30, 60, 120, 240, 480, 960, 1920, 3600, 3600]
+        for retries, base in enumerate(base_values):
             delay = calculate_rate_limit_backoff(retries)
-            assert delay == expected_delay, f"Retry {retries}: expected {expected_delay}, got {delay}"
+            # Delay must be at least the base value (jitter is non-negative)
+            assert delay >= base, f"Retry {retries}: {delay} < base {base}"
+            # Delay must not exceed base + 30% jitter (int truncation means <= base * 1.3)
+            max_with_jitter = int(base * 1.3)
+            assert delay <= max_with_jitter, f"Retry {retries}: {delay} > max {max_with_jitter}"
 
     def test_error_backoff_sequence(self):
         """Test that error backoff follows expected linear sequence."""