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- 13 files deleted (~2,679 lines): unused UI components, debug logs, outdated docs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

rate_limit_utils.py

@@ -6,6 +6,7 @@ Shared utilities for detecting and handling API rate limits.
 Used by both agent.py (production) and test_rate_limit_utils.py (tests).
 """
 
+import random
 import re
 from typing import Optional
 
@@ -81,18 +82,25 @@ def is_rate_limit_error(error_message: str) -> bool:
 
 def calculate_rate_limit_backoff(retries: int) -> int:
     """
-    Calculate exponential backoff for rate limits.
+    Calculate exponential backoff with jitter for rate limits.
 
-    Formula: min(60 * 2^retries, 3600) - caps at 1 hour
-    Sequence: 60s, 120s, 240s, 480s, 960s, 1920s, 3600s...
+    Base formula: min(15 * 2^retries, 3600)
+    Jitter: adds 0-30% random jitter to prevent thundering herd.
+    Base sequence: ~15-20s, ~30-40s, ~60-78s, ~120-156s, ...
+
+    The lower starting delay (15s vs 60s) allows faster recovery from
+    transient rate limits, while jitter prevents synchronized retries
+    when multiple agents hit limits simultaneously.
 
     Args:
         retries: Number of consecutive rate limit retries (0-indexed)
 
     Returns:
-        Delay in seconds (clamped to 1-3600 range)
+        Delay in seconds (clamped to 1-3600 range, with jitter)
     """
-    return int(min(max(60 * (2 ** retries), 1), 3600))
+    base = int(min(max(15 * (2 ** retries), 1), 3600))
+    jitter = random.uniform(0, base * 0.3)
+    return int(base + jitter)
 
 
 def calculate_error_backoff(retries: int) -> int: