feat(rag): lite-model document summaries — non-markdown docs summarized at import, summary chunk retrieves and resolves to the full source doc

tests/unit/test_config.py

@@ -25,6 +25,9 @@ def test_defaults_match_locked_decisions(monkeypatch: pytest.MonkeyPatch) -> Non
     s = _settings()
     assert s.llm_chat_model == "turbo"
     assert s.llm_embed_model == "embed"
+    # A5 extended (phase 30): one-shot completions default to the ``lite``
+    # model on the same endpoint.
+    assert s.llm_summary_model == "lite"
     assert s.embedding_dim == 768
     assert s.llm_base_url.endswith("/v1")
     # A8 (revised): the honesty gate input is the best cosine, default 0.62.
@@ -53,6 +56,22 @@ def test_env_override(monkeypatch) -> None:
     assert s.llm_chat_model == "juggernaut"
 
 
+def test_llm_summary_model_env_override(monkeypatch) -> None:
+    """Phase 30: ``BOR_LLM_SUMMARY_MODEL`` overrides the ``lite`` default"""
+    monkeypatch.setenv("BOR_LLM_SUMMARY_MODEL", "mini")
+    s = _settings()
+    assert s.llm_summary_model == "mini"
+
+
+def test_summary_max_chars_default_and_env_override(monkeypatch: pytest.MonkeyPatch) -> None:
+    """Phase 30: document content sent to the ``lite`` model is capped at
+    ``BOR_SUMMARY_MAX_CHARS`` (default 12 000 chars per call)."""
+    monkeypatch.delenv("BOR_SUMMARY_MAX_CHARS", raising=False)
+    assert _settings().summary_max_chars == 12_000
+    monkeypatch.setenv("BOR_SUMMARY_MAX_CHARS", "5000")
+    assert _settings().summary_max_chars == 5000
+
+
 def test_max_output_tokens_env_override(monkeypatch) -> None:
     monkeypatch.setenv("BOR_MAX_OUTPUT_TOKENS", "1234")
     s = _settings()