Fix shadow observer lifecycle, learning and prediction correctness

ROADMAP.md

@@ -39,7 +39,7 @@ Current behavior: **shadow mode only**. `generic_thermostat` remains the one and
 
 **Objective:** Make the existing observer trustworthy before extending it.
 
-- [ ] Perform a source audit of v0.2.1: pure model, optimizer, config/options, coordinator update timing, persistent model and entity lifecycle.
+- [x] Perform a source audit of v0.2.1: pure model, optimizer, config/options, coordinator update timing, persistent model and entity lifecycle.
 - [ ] Add Home Assistant test harness coverage for initial setup, update, restart/reload, options changes, missing sensors, `heat/off`, target changes, teardown and uninstall.
 - [ ] Verify that **zero physical-device service calls** occur in observation mode, including restart and failed update cases.
 - [ ] Establish deterministic handling of 5-minute transitions, polling jitter, timestamp discontinuities, missing data and real switch transitions between samples.
@@ -52,6 +52,20 @@ Current behavior: **shadow mode only**. `generic_thermostat` remains the one and
 
 **Exit criteria:** No control writes; reproducible tests covering HA lifecycle; clean upgrade/removal; clear status during outages; no significant model-data loss or silent corruption on restart.
 
+### Audit update — 2026-10-26
+
+See [AUDIT.md](AUDIT.md). The source audit and focused repairs are complete;
+Milestone 0 acceptance is **not** complete. Offline boundary doubles cover setup,
+reload/unload, migration, removal, corrupt storage, missing inputs and manual off.
+They are not a full HA test harness. Per-room accepted ON/OFF counts, additive
+payload schema v2, conservative relay-transition rejection, jitter normalization,
+Fahrenheit targets and forecast input-change guards are implemented.
+
+Next implement configurable freshness/alignment with diagnostics and a supported
+HA test harness/CI. Then improve event-based sampling and identity/persistence
+migration tests. Only after those reliability checks proceed to Milestone 1's
+recorded forecasts and walk-forward evaluation. Live control remains unauthorized.
+
 ## Milestone 1 — Explainable forecasts and dashboards (target v0.3.0)
 
 **Objective:** Users can verify what the model predicts and whether it is actually accurate.