Merge pull request #331 from tseaver/fix-329-330-reconfig-and-extras

fix: include 'db_path'/'config' in 'extras'

haiku_rag_slim/haiku/rag/skills/_tools.py

@@ -249,7 +249,13 @@ def create_skill_extras(
 ) -> dict[str, Any]:
     """Create non-tool utility functions bound to a specific database.
 
-    Returns a dict of callables that can be attached to a Skill's extras.
+    Returns a dict of values that can be attached to a Skill's extras:
+
+    Keys:
+    - 'db_path': path to the LanceDB used to configure the skill
+    - 'config': config passed to (or derived for) the skill
+    - 'list_documents': returns info for documents in the database
+    - 'visualize_chunk': returns visualizations for chunks in the database
     """
 
     async def visualize_chunk(chunk_id: str) -> list:
@@ -283,6 +289,8 @@ def create_skill_extras(
             ]
 
     return {
+        "db_path": db_path,
+        "config": config,
         "visualize_chunk": visualize_chunk,
         "list_documents": list_documents,
     }

haiku_rag_slim/haiku/rag/skills/rlm.py

@@ -54,7 +54,7 @@ def create_skill(
         config: haiku.rag AppConfig instance. If None, uses get_config().
     """
     from haiku.rag.config import get_config
-    from haiku.rag.skills._tools import create_skill_tools
+    from haiku.rag.skills._tools import create_skill_extras, create_skill_tools
 
     if config is None:
         config = get_config()
@@ -67,6 +67,7 @@ def create_skill(
             db_path = config.storage.data_dir / "haiku.rag.lancedb"
 
     tools = create_skill_tools(db_path, config, RLMState, ["analyze"])
+    extras = create_skill_extras(db_path, config)
 
     return Skill(
         metadata=skill_metadata(),
@@ -74,6 +75,7 @@ def create_skill(
         path=_skill_path,
         instructions=instructions(),
         tools=list(tools.values()),
+        extras=extras,
         state_type=STATE_TYPE,
         state_namespace=STATE_NAMESPACE,
     )

tests/skills/conftest.py

@@ -5,6 +5,7 @@ import pytest
 from pydantic_ai import RunContext
 
 from haiku.rag.client import HaikuRAG
+from haiku.rag.config.models import AppConfig
 from haiku.rag.embeddings import EmbedderWrapper
 from haiku.skills.state import SkillRunDeps
 
@@ -45,6 +46,11 @@ def mock_embedder(monkeypatch):
     monkeypatch.setattr(EmbedderWrapper, "embed_documents", fake_embed_documents)
 
 
+@pytest.fixture
+def test_app_config():
+    return AppConfig(environment="skills-test")
+
+
 @pytest.fixture
 async def rag_db(temp_db_path):
     """Create a test database with sample documents."""

tests/skills/test_rag.py

@@ -42,10 +42,10 @@ class TestRAGModuleAPI:
         assert isinstance(result, str)
         assert len(result) > 0
 
-    def test_constants_match_create_skill(self, temp_db_path):
+    def test_constants_match_create_skill(self, test_app_config, temp_db_path):
         from haiku.rag.skills.rag import create_skill
 
-        skill = create_skill(db_path=temp_db_path)
+        skill = create_skill(config=test_app_config, db_path=temp_db_path)
         assert skill.state_type is STATE_TYPE
         assert skill.state_namespace == STATE_NAMESPACE
         assert skill.metadata == skill_metadata()
@@ -53,18 +53,18 @@ class TestRAGModuleAPI:
 
 
 class TestRAGSkillCreation:
-    def test_create_skill_returns_valid_skill(self, temp_db_path):
+    def test_create_skill_returns_valid_skill(self, test_app_config, temp_db_path):
         from haiku.rag.skills.rag import create_skill
 
-        skill = create_skill(db_path=temp_db_path)
+        skill = create_skill(config=test_app_config, db_path=temp_db_path)
         assert skill.metadata.name == "rag"
         assert skill.metadata.description
         assert skill.instructions
 
-    def test_create_skill_has_expected_tools(self, temp_db_path):
+    def test_create_skill_has_expected_tools(self, test_app_config, temp_db_path):
         from haiku.rag.skills.rag import create_skill
 
-        skill = create_skill(db_path=temp_db_path)
+        skill = create_skill(config=test_app_config, db_path=temp_db_path)
         tool_names = {getattr(t, "__name__") for t in skill.tools if callable(t)}
         assert tool_names == {
             "search",
@@ -74,17 +74,19 @@ class TestRAGSkillCreation:
             "research",
         }
 
-    def test_create_skill_has_state(self, temp_db_path):
+    def test_create_skill_has_state(self, test_app_config, temp_db_path):
         from haiku.rag.skills.rag import RAGState, create_skill
 
-        skill = create_skill(db_path=temp_db_path)
+        skill = create_skill(config=test_app_config, db_path=temp_db_path)
         assert skill._state_type is RAGState
         assert skill._state_namespace == "rag"
 
-    def test_create_skill_has_extras(self, temp_db_path):
+    def test_create_skill_has_extras(self, test_app_config, temp_db_path):
         from haiku.rag.skills.rag import create_skill
 
-        skill = create_skill(db_path=temp_db_path)
+        skill = create_skill(config=test_app_config, db_path=temp_db_path)
+        assert skill.extras["config"] is test_app_config
+        assert skill.extras["db_path"] is temp_db_path
         assert "visualize_chunk" in skill.extras
         assert "list_documents" in skill.extras
         assert callable(skill.extras["visualize_chunk"])
@@ -99,33 +101,42 @@ class TestRAGSkillCreation:
 
 
 class TestSkillExtras:
-    async def test_list_documents_returns_all(self, rag_db):
+    async def test_list_documents_returns_all(self, test_app_config, rag_db):
         from haiku.rag.skills.rag import create_skill
 
-        skill = create_skill(db_path=rag_db)
+        skill = create_skill(config=test_app_config, db_path=rag_db)
         list_docs = skill.extras["list_documents"]
         results = await list_docs()
         assert len(results) == 2
         assert all(k in results[0] for k in ("id", "title", "uri", "metadata"))
 
-    async def test_list_documents_with_filter(self, rag_db):
+    async def test_list_documents_with_filter(self, test_app_config, rag_db):
         from haiku.rag.skills.rag import create_skill
 
-        skill = create_skill(db_path=rag_db)
+        skill = create_skill(config=test_app_config, db_path=rag_db)
         list_docs = skill.extras["list_documents"]
         results = await list_docs(filter="title = 'AI Overview'")
         assert len(results) == 1
         assert results[0]["title"] == "AI Overview"
 
-    async def test_visualize_chunk_unknown_returns_empty(self, rag_db):
+    async def test_visualize_chunk_unknown_returns_empty(
+        self,
+        test_app_config,
+        rag_db,
+    ):
         from haiku.rag.skills.rag import create_skill
 
-        skill = create_skill(db_path=rag_db)
+        skill = create_skill(config=test_app_config, db_path=rag_db)
         visualize = skill.extras["visualize_chunk"]
         result = await visualize("nonexistent-chunk-id")
         assert result == []
 
-    async def test_visualize_chunk_returns_images(self, rag_db, monkeypatch):
+    async def test_visualize_chunk_returns_images(
+        self,
+        test_app_config,
+        rag_db,
+        monkeypatch,
+    ):
         from haiku.rag.client import HaikuRAG
         from haiku.rag.skills.rag import create_skill
 
@@ -133,7 +144,7 @@ class TestSkillExtras:
             HaikuRAG, "visualize_chunk", AsyncMock(return_value=["img1"])
         )
 
-        skill = create_skill(db_path=rag_db)
+        skill = create_skill(config=test_app_config, db_path=rag_db)
         visualize = skill.extras["visualize_chunk"]
 
         # Get a real chunk_id from the db

tests/skills/test_rlm.py

@@ -39,10 +39,10 @@ class TestRLMModuleAPI:
         assert isinstance(result, str)
         assert len(result) > 0
 
-    def test_constants_match_create_skill(self, temp_db_path):
+    def test_constants_match_create_skill(self, test_app_config, temp_db_path):
         from haiku.rag.skills.rlm import create_skill
 
-        skill = create_skill(db_path=temp_db_path)
+        skill = create_skill(config=test_app_config, db_path=temp_db_path)
         assert skill.state_type is STATE_TYPE
         assert skill.state_namespace == STATE_NAMESPACE
         assert skill.metadata == skill_metadata()
@@ -50,28 +50,39 @@ class TestRLMModuleAPI:
 
 
 class TestRLMSkillCreation:
-    def test_create_skill_returns_valid_skill(self, temp_db_path):
+    def test_create_skill_returns_valid_skill(self, test_app_config, temp_db_path):
         from haiku.rag.skills.rlm import create_skill
 
-        skill = create_skill(db_path=temp_db_path)
+        skill = create_skill(config=test_app_config, db_path=temp_db_path)
         assert skill.metadata.name == "rag-rlm"
         assert skill.metadata.description
         assert skill.instructions
 
-    def test_create_skill_has_expected_tools(self, temp_db_path):
+    def test_create_skill_has_expected_tools(self, test_app_config, temp_db_path):
         from haiku.rag.skills.rlm import create_skill
 
-        skill = create_skill(db_path=temp_db_path)
+        skill = create_skill(config=test_app_config, db_path=temp_db_path)
         tool_names = {getattr(t, "__name__") for t in skill.tools if callable(t)}
         assert tool_names == {"analyze"}
 
-    def test_create_skill_has_state(self, temp_db_path):
+    def test_create_skill_has_state(self, test_app_config, temp_db_path):
         from haiku.rag.skills.rlm import RLMState, create_skill
 
-        skill = create_skill(db_path=temp_db_path)
+        skill = create_skill(config=test_app_config, db_path=temp_db_path)
         assert skill._state_type is RLMState
         assert skill._state_namespace == "rlm"
 
+    def test_create_skill_has_extras(self, test_app_config, temp_db_path):
+        from haiku.rag.skills.rlm import create_skill
+
+        skill = create_skill(config=test_app_config, db_path=temp_db_path)
+        assert skill.extras["config"] is test_app_config
+        assert skill.extras["db_path"] is temp_db_path
+        assert "visualize_chunk" in skill.extras
+        assert "list_documents" in skill.extras
+        assert callable(skill.extras["visualize_chunk"])
+        assert callable(skill.extras["list_documents"])
+
     def test_create_skill_from_env(self, monkeypatch, temp_db_path):
         monkeypatch.setenv("HAIKU_RAG_DB", str(temp_db_path))
         from haiku.rag.skills.rlm import create_skill