docs: bring README and docs current for v1.25

Reflect the v1.25 surface without touching the changelog or version
numbers.

- README highlights now cover the new clinical signals (respiratory
  rate, the opt-in PHQ-9 / GAD-7 mental-wellbeing self-checks with calm
  crisis handling, grip strength, pain score, waist / body measurements,
  longevity labs), the signal registry that wires each one across charts,
  correlations, the coach, FHIR, and the API at once, structured records
  (allergies, family history; immunizations noted out of scope), the
  opt-in environmental-context module, inbound document extraction
  (transcribe, never interpret), and the self-description posture (a
  record-keeping and wellness tool, not a medical device).
- ai-providers.md gains a "what the Coach is — and isn't" section: the
  non-diagnostic standard and the calm proactive morning check-in
  behaviour.
- mcp-capabilities.md notes that the new measurement signals reach the
  assistant through the existing metric and labs tools via the registry,
  that the mental-wellbeing instruments / records / documents are
  deliberately not exposed over MCP, and ties the grounding contract to
  the project-wide self-description standard.
- getting-started.md lists the environmental module's Open-Meteo egress
  as an opt-in outbound dependency.

docs/api/mcp-capabilities.md

@@ -28,7 +28,10 @@ them up front):
 4. **Data and context only.** The server ships facts; it never returns a
    diagnosis, clinical verdict, risk score, or treatment change. The
    assistant narrates the facts and leaves clinical judgement to the
-   user's clinician.
+   user's clinician. This mirrors HealthLog's project-wide self-description
+   standard: the app is a personal health record-keeping and wellness tool,
+   not a medical device, and nothing it surfaces — here or in the UI —
+   diagnoses or treats.
 
 Discover before fetching: call `list_metrics` (or read the
 `healthlog://measurements/inventory` resource) first to see what exists,
@@ -95,6 +98,19 @@ Every read tool is annotated read-only / non-destructive / idempotent /
 closed-world — the read-only guarantee is structural (only read tools are
 registered for a read session), and the annotation merely advertises it.
 
+The v1.25 clinical-signal additions reach the assistant through these same
+tools rather than new tool names: respiratory rate, grip strength, the 0–10
+pain score, and waist / body measurements appear via `list_metrics` →
+`get_metric_series` / `get_metrics`, and the longevity lab markers via
+`get_labs`. A new signal is declared once in the in-app signal registry and
+shows up across the metric tools, correlations, and the FHIR map together,
+so the MCP surface never advertises a signal the record can't return. The
+opt-in mental-wellbeing instruments (PHQ-9, GAD-7), the structured records
+(allergies, family history), and the inbound-document store are deliberately
+**not** exposed over MCP: the instrument answers are kept out of the
+assistant by design, and the document pipeline extracts facts for the user
+to confirm in-app rather than streaming them to a model.
+
 ## Resources
 
 Read-only context the assistant can attach alongside tool results. Like