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- 13 files deleted (~2,679 lines): unused UI components, debug logs, outdated docs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

@@ -992,31 +992,26 @@ def main():
     failed += pkill_failed
 
     # Commands that SHOULD be blocked
+    # Note: blocklisted commands (sudo, shutdown, dd, aws) are tested in
+    # test_blocklist_enforcement(). chmod validation is tested in
+    # test_validate_chmod(). init.sh validation is tested in
+    # test_validate_init_script(). pkill validation is tested in
+    # test_pkill_extensibility(). The entries below focus on scenarios
+    # NOT covered by those dedicated tests.
     print("\nCommands that should be BLOCKED:\n")
     dangerous = [
         # Not in allowlist - dangerous system commands
-        "shutdown now",
         "reboot",
-        "dd if=/dev/zero of=/dev/sda",
         # Not in allowlist - common commands excluded from minimal set
         "wget https://example.com",
         "python app.py",
         "killall node",
-        # pkill with non-dev processes
+        # pkill with non-dev processes (pkill python tested in test_pkill_extensibility)
         "pkill bash",
         "pkill chrome",
-        "pkill python",
         # Shell injection attempts
         "$(echo pkill) node",
         'eval "pkill node"',
-        # chmod with disallowed modes
-        "chmod 777 file.sh",
-        "chmod 755 file.sh",
-        "chmod +w file.sh",
-        "chmod -R +x dir/",
-        # Non-init.sh scripts
-        "./setup.sh",
-        "./malicious.sh",
     ]
 
     for cmd in dangerous:
@@ -1026,6 +1021,10 @@ def main():
             failed += 1
 
     # Commands that SHOULD be allowed
+    # Note: chmod +x variants are tested in test_validate_chmod().
+    # init.sh variants are tested in test_validate_init_script().
+    # The combined "chmod +x init.sh && ./init.sh" below serves as the
+    # integration test verifying the hook routes to both validators correctly.
     print("\nCommands that should be ALLOWED:\n")
     safe = [
         # File inspection
@@ -1076,16 +1075,7 @@ def main():
         "ls | grep test",
         # Full paths
         "/usr/local/bin/node app.js",
-        # chmod +x (allowed)
-        "chmod +x init.sh",
-        "chmod +x script.sh",
-        "chmod u+x init.sh",
-        "chmod a+x init.sh",
-        # init.sh execution (allowed)
-        "./init.sh",
-        "./init.sh --production",
-        "/path/to/init.sh",
-        # Combined chmod and init.sh
+        # Combined chmod and init.sh (integration test for both validators)
         "chmod +x init.sh && ./init.sh",
     ]