close guardrail gaps and fix the scoring pipeline top to bottom

Constraint resolver: aggregate mass/footprint across a combo instead of
pairwise-only checks, treat medium/atmosphere as agreement not supply/demand,
reduce multi-provider checks by best/sum instead of AND-ing every provider,
fail closed on unrecognized mutex values, add a propulsion-viability
(thrust-to-weight) rule. Seed data updated to match (nuclear/solar-sail
footprint floors, water-medium exclusions, explicit ground/gravity providers).

Domain metric units were stored globally per metric name instead of
per-domain, silently corrupting cost_efficiency for every domain but the
first one seeded — fixed with a schema migration.

Stub estimator's cost_efficiency/safety/availability/reliability were a
backwards formula and flat constants; replaced with heuristics grounded in
each entity's thrust_profile/energy_form/infrastructure.

LLM estimate_physics() now receives each metric's unit and expected range
instead of a bare name, fixing wildly miscalibrated estimates traced back to
the prompt's own hardcoded example anchoring the model to the wrong order of
magnitude. Sharpened the safety-estimation and plausibility-review prompts.
Deduped provider parsing logic into llm/parsing.py.

Web pipeline form can now pick an LLM provider per run instead of only via
server env var.

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

tests/test_ollama_provider.py

@@ -1,36 +1,10 @@
-"""Tests for the Ollama provider's parsing logic and registry wiring."""
+"""Tests for the Ollama provider's registry wiring."""
 
 from __future__ import annotations
 
-import pytest
-
 from physcom.llm.providers.ollama import OllamaLLMProvider
 
 
-@pytest.fixture
-def provider():
-    return OllamaLLMProvider()
-
-
-def test_parse_json_strips_fences(provider):
-    text = '```json\n{"power_density": 500.0, "safety": 0.7}\n```'
-    result = provider._parse_json(text, ["power_density", "safety"])
-    assert result == {"power_density": 500.0, "safety": 0.7}
-
-
-def test_parse_json_falls_back_on_invalid(provider):
-    result = provider._parse_json("not json", ["power_density", "safety"])
-    assert result == {"power_density": 0.5, "safety": 0.5}
-
-
-def test_parse_verdict_plausible(provider):
-    assert provider._parse_verdict("blah blah\nVERDICT: PLAUSIBLE") is True
-
-
-def test_parse_verdict_implausible(provider):
-    assert provider._parse_verdict("blah blah\nVERDICT: IMPLAUSIBLE") is False
-
-
 def test_registry_builds_ollama_provider(monkeypatch):
     from physcom.llm.registry import build_llm_provider