Stage 6: learn_call_flow rebuilt on the learner, docs truth sweep

The call-flow learner finally gets fed: exploration mode records its
IVR discoveries on the call (ActiveCall.exploration_steps) instead of
throwing them away, persistence stores them in the call record's
metadata, and the rebuilt learn_call_flow MCP tool turns a completed
exploration call into a stored flow via CallFlowLearner — correct
constructor (llm_client from get_llm, heuristic labels when the LLM
is unavailable), build for a new number, merge/refine when a flow
already exists. save_learned_flow/update_flow_from_model keep the
CallFlow↔row mapping in call_persistence.

Test gaps closed: tests/test_learner.py (discoveries→linked steps,
exploration persistence, learn-then-refine through the in-memory MCP
client, no-data and unknown-call answers) and tests/test_websocket.py
(4401 without token, trunk-status-then-replay on connect, per-call
stream filtering).

Docs aligned to code: README (15 tools incl. learn_call_flow, HTTP
not SSE, Python 3.12+, PostgreSQL+Alembic — no SQLite fallback, media
pipeline marked stub-mode until pjsua2 installed, Alembic and honest
/health checked off); docs/mcp-server.md rewritten against the actual
tool surface (hangup not end_call, real params, 3 real resources,
/mcp/ streamable HTTP + bearer auth); architecture/development/
configuration drift fixed.

pyproject: pruned never-imported deps (websockets, librosa,
soundfile, python-multipart).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

docs/configuration.md

@@ -126,7 +126,7 @@ uvicorn main:app --host 0.0.0.0 --port 8000 --reload
 ### Production
 
 ```bash
-# Use PostgreSQL instead of SQLite
+# PostgreSQL is required (no SQLite fallback)
 DATABASE_URL=postgresql+asyncpg://user:pass@localhost/hold_slayer
 
 # Use vLLM for faster inference