Unify in-memory session state in AgentSessionOrchestrator ...

Replace scattered _runs + _busy_sessions + _session_sockets with a
single _sessions: dict[str, SessionState] on the orchestrator.

- SessionState dataclass holds run, busy_event, and websockets
- _session_sockets module-level global removed from websocket.py;
  socket tracking moved into orchestrator (add/remove_websocket)
- Event bus subscriber _on_recall_update moved into orchestrator
- Per-session asyncio.Lock added to protect concurrent-run guard
- _cleanup() auto-removes empty SessionState entries

Tests updated to reference _sessions instead of legacy _runs.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Pass explicit ToolContext to tools instead of hidden ContextVars ...

Add ToolContext dataclass (session_id, event_sink, stop_event, model,
user_id, user_role, user_info) and thread it through the execution chain:
Agent._execute_tools_with_sink → ToolExecutor → tool.execute().

All ~25 tools updated to accept ctx parameter. Tools that previously
read ContextVar now prefer ctx when provided, falling back to
ContextVar for backward compatibility.

Tests updated to pass ToolContext explicitly — no more test fixtures
that set current_session_id / current_user_id ContextVars.

ContextVar setters remain as fallback for non-tool consumers
(ai_helper, context_builder, planning) and will be removed in a
follow-up refactor.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Mark architecture weak spot #10 (MCP caching/backoff) as resolved ...

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Mark architecture weak spot #7 (DRY tool_executor) as resolved ...

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Mark architecture weak spot #6 (cross-registry patching) as resolved ...

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Mark architecture weak spot #5 (duplicate PostgreSQL pools) as resolved ...

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Mark architecture weak spot #4 (mutable settings) as resolved ...

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Mark architecture weak spots #2 and #3 as resolved ...

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Step 5-7: Extract async generators from run_stream, unify run() as wrapper ...

- _compression_events_preturn / _compression_events_midturn
- _consume_stream (uses StreamState)
- _execute_tools_with_sink
- run() is now a thin wrapper around run_stream() collecting StreamEnd
- Remove dead imports (json, LLMChunk)
- Mark god-object decomposition complete in architecture_weak_spots.md

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Extract ContextCompressor, fix STL viewer, expand test suite, add architecture audit docs ...

- Extract ContextCompressor from agent.py (Step 1 of god-object refactor)
- Add retry + hard-truncate fallback logic to ContextCompressor
- Add unit tests: agent loop (14), compressor (18), KV store (8),
  auth encrypt (3), auth deps (13), todo/scratchpad/image_view/memory
- Fix WebGL STL viewer: allow-same-origin sandbox + graceful fallback
- Add CompressionStarted event and client-side compression notice
- Add docs/architecture_weak_spots.md and plan_01_god_object_agent.md
- Update test_events.py and test_agent_context_size.py for new logic

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>