feat: Phase 3 - Logic Nodes + Conditional Branching
Backend: - logic_evaluator.py (NEU, 307 Zeilen): Deterministischer Logic Evaluator - Vergleichsoperatoren: EQ, NEQ, IN, NOT_IN, GT, LT, GTE, LTE, CONTAINS - Logische Operatoren: AND, OR, NOT mit Verschachtelung - Resolve signal references (node_id.question_type) - Error handling für UNCLEAR/INVALID/NOT_DECIDABLE Signale - workflow_executor.py (ERWEITERT): - execute_logic_node(): Bedingungen evaluieren, Pfade aktivieren/deaktivieren - execute_workflow(): BFS-Traversierung mit Edge-Activation statt Sequential - _apply_fallback(): 4 Fallback-Strategien (CONSERVATIVE_SKIP, DEFAULT_PATH, UNCERTAINTY_PATH, DOCUMENT_ONLY) - _has_active_incoming_edge(): Prüft ob Node erreichbar ist - _get_edges_by_label(): Findet then/else/uncertainty Pfade - workflow_models.py (ERWEITERT): - LogicOperator.CONTAINS hinzugefügt - version.py: 0.9k → 0.9l, workflow 0.3.0 → 0.4.0 Tests: - test_phase3_logic_evaluator.py (NEU): 20 Unit Tests (alle passing) - Comparison operators (EQ, NEQ, IN, GT, LT, CONTAINS) - Logical operators (AND, OR, NOT) - Nested expressions - Error handling (missing refs, UNCLEAR/INVALID signals) - test_phase2_workflow_executor.py (AKTUALISIERT): 11 Tests (alle passing) - execute_node() graph parameter hinzugefügt (Phase 3 requirement) - test_execute_node_unknown_type: logic → join (logic jetzt implementiert) - test_phase3_workflow_branching.py (NEU): Integration Tests vorbereitet - Erfordert vollständige DB-Mock-Strategie (wird in E2E-Test nachgeholt) Phase 2 Backward Compatibility: ✅ Alle Phase 2 Tests bestehen weiterhin Konzept: .claude/task/Workflow_engine_prompting_engine/konzept_workflow_engine_konsolidated.md Anforderungsanalyse: .claude/task/Workflow_engine_prompting_engine/phase3_anforderungsanalyse.md Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
1 parent
16dc08cd7d
commit
2ce0874dcb
7 files changed
+1735
-41
No files matched your search
@@ -192,24 +192,25 @@ def test_aggregate_results_formatting():
|
||||
async def test_execute_node_start_end():
|
||||
"""Test: Start/End Nodes sind No-Ops"""
|
||||
from workflow_executor import execute_node
|
||||
from workflow_models import WorkflowNode
|
||||
from workflow_models import WorkflowNode, WorkflowGraph
|
||||
|
||||
start_node = WorkflowNode(id="start", type="start")
|
||||
end_node = WorkflowNode(id="end", type="end")
|
||||
|
||||
context = {"variables": {}, "profile_id": "test"}
|
||||
catalog = {}
|
||||
mock_graph = WorkflowGraph(nodes=[], edges=[]) # Phase 3: graph parameter required
|
||||
|
||||
async def mock_llm(prompt, model):
|
||||
return "should not be called"
|
||||
|
||||
# Test start
|
||||
result = await execute_node(start_node, context, catalog, mock_llm)
|
||||
result = await execute_node(start_node, context, catalog, mock_graph, mock_llm)
|
||||
assert result.status == NodeStatus.EXECUTED
|
||||
assert result.analysis_core is None
|
||||
|
||||
# Test end
|
||||
result = await execute_node(end_node, context, catalog, mock_llm)
|
||||
result = await execute_node(end_node, context, catalog, mock_graph, mock_llm)
|
||||
assert result.status == NodeStatus.EXECUTED
|
||||
assert result.analysis_core is None
|
||||
|
||||
@@ -218,29 +219,30 @@ async def test_execute_node_start_end():
|
||||
async def test_execute_node_unknown_type():
|
||||
"""Test: Unbekannter Node-Typ wirft Fehler"""
|
||||
from workflow_executor import execute_node
|
||||
from workflow_models import WorkflowNode
|
||||
from workflow_models import WorkflowNode, WorkflowGraph
|
||||
|
||||
# Phase 2 unterstützt nur start, end, analysis
|
||||
logic_node = WorkflowNode(id="logic1", type="logic")
|
||||
# Phase 3: logic is now implemented, test with join instead
|
||||
join_node = WorkflowNode(id="join1", type="join")
|
||||
|
||||
context = {"variables": {}, "profile_id": "test"}
|
||||
catalog = {}
|
||||
mock_graph = WorkflowGraph(nodes=[], edges=[])
|
||||
|
||||
async def mock_llm(prompt, model):
|
||||
return ""
|
||||
|
||||
result = await execute_node(logic_node, context, catalog, mock_llm)
|
||||
result = await execute_node(join_node, context, catalog, mock_graph, mock_llm)
|
||||
|
||||
# Sollte FAILED sein mit Fehlermeldung
|
||||
assert result.status == NodeStatus.FAILED
|
||||
assert "not implemented in Phase 2" in result.error
|
||||
assert "not implemented" in result.error.lower() or "phase 4" in result.error.lower()
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_execute_node_analysis_simple():
|
||||
"""Test: Analysis Node ohne Fragenergänzung"""
|
||||
from workflow_executor import execute_node
|
||||
from workflow_models import WorkflowNode
|
||||
from workflow_models import WorkflowNode, WorkflowGraph
|
||||
|
||||
node = WorkflowNode(
|
||||
id="test_node",
|
||||
@@ -251,6 +253,7 @@ async def test_execute_node_analysis_simple():
|
||||
|
||||
context = {"variables": {"name": "Test"}, "profile_id": "test"}
|
||||
catalog = {}
|
||||
mock_graph = WorkflowGraph(nodes=[], edges=[])
|
||||
|
||||
# Mock LLM
|
||||
async def mock_llm(prompt, model):
|
||||
@@ -260,7 +263,7 @@ async def test_execute_node_analysis_simple():
|
||||
with patch('workflow_executor.load_prompt_template') as mock_load:
|
||||
mock_load.return_value = "Test prompt for {{name}}"
|
||||
|
||||
result = await execute_node(node, context, catalog, mock_llm)
|
||||
result = await execute_node(node, context, catalog, mock_graph, mock_llm)
|
||||
|
||||
assert result.status == NodeStatus.EXECUTED
|
||||
assert result.analysis_core == "Test analysis content"
|
||||
@@ -271,7 +274,7 @@ async def test_execute_node_analysis_simple():
|
||||
async def test_execute_node_analysis_with_questions():
|
||||
"""Test: Analysis Node mit Fragenergänzung und Normalisierung"""
|
||||
from workflow_executor import execute_node
|
||||
from workflow_models import WorkflowNode, QuestionAugmentation
|
||||
from workflow_models import WorkflowNode, QuestionAugmentation, WorkflowGraph
|
||||
|
||||
node = WorkflowNode(
|
||||
id="test_node",
|
||||
@@ -294,6 +297,7 @@ async def test_execute_node_analysis_with_questions():
|
||||
"normalization_rules": None
|
||||
}
|
||||
}
|
||||
mock_graph = WorkflowGraph(nodes=[], edges=[])
|
||||
|
||||
# Mock LLM
|
||||
async def mock_llm(prompt, model):
|
||||
@@ -309,7 +313,7 @@ Test analysis
|
||||
with patch('workflow_executor.load_prompt_template') as mock_load:
|
||||
mock_load.return_value = "Base prompt"
|
||||
|
||||
result = await execute_node(node, context, catalog, mock_llm)
|
||||
result = await execute_node(node, context, catalog, mock_graph, mock_llm)
|
||||
|
||||
assert result.status == NodeStatus.EXECUTED
|
||||
assert result.analysis_core == "Test analysis"
|
||||
@@ -330,7 +334,7 @@ async def test_execute_node_hybrid_model_override():
|
||||
Regression-Test für: https://github.com/anthropics/claude-code/issues/XXX
|
||||
"""
|
||||
from workflow_executor import execute_node
|
||||
from workflow_models import WorkflowNode, QuestionAugmentation
|
||||
from workflow_models import WorkflowNode, QuestionAugmentation, WorkflowGraph
|
||||
|
||||
# Node mit ANDEREM Spektrum als Catalog
|
||||
node = WorkflowNode(
|
||||
@@ -356,6 +360,7 @@ async def test_execute_node_hybrid_model_override():
|
||||
"normalization_rules": None
|
||||
}
|
||||
}
|
||||
mock_graph = WorkflowGraph(nodes=[], edges=[])
|
||||
|
||||
# Mock LLM gibt "decrease" zurück (gültig für Node, ungültig für Catalog)
|
||||
async def mock_llm(prompt, model):
|
||||
@@ -370,7 +375,7 @@ Gewicht gesunken
|
||||
with patch('workflow_executor.load_prompt_template') as mock_load:
|
||||
mock_load.return_value = "Base prompt"
|
||||
|
||||
result = await execute_node(node, context, catalog, mock_llm)
|
||||
result = await execute_node(node, context, catalog, mock_graph, mock_llm)
|
||||
|
||||
# Assertions: "decrease" muss VALID sein (Node-Spektrum), nicht INVALID (Catalog)
|
||||
assert result.status == NodeStatus.EXECUTED
|
||||
|
||||
Reference in new issue
Block a user