propagate changes

- raw_response -> api_output
- remove flow_run_cache

CF_CodeCriticWrongAttempt.yaml

@@ -82,6 +82,6 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response: "code_feedback"
+      api_output: "code_feedback"
 output_keys:
   - "code_feedback"

CF_CodeCriticWrongAttemptWithPlan.yaml

@@ -89,6 +89,6 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response: "code_feedback"
+      api_output: "code_feedback"
 output_keys:
   - "code_feedback"

CF_CodeDebug.yaml

@@ -17,7 +17,7 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.code: "code"
+      code: "code"
 output_keys:
   - "code"
 
@@ -46,13 +46,14 @@ subflows_config:
         - _target_: flows.data_transformations.RegexFirstOccurrenceExtractor
           regex: '(?<=```python)([\s\S]*?)(?=```)'
           regex_fallback: '(?<=```)([\s\S]*?)(?=```)'
-          input_key: "raw_response"
+          input_key: "api_output"
           output_key: "code"
           strip: True
           assert_unique: True
 
         - _target_: flows.data_transformations.EndOfInteraction
           end_of_interaction_string: "Final answer"
+          input_key: "api_output"
           output_key: "end_of_interaction"
 
       output_keys:

CF_CodeDebugCollab.yaml

@@ -17,7 +17,7 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.code: "code"
+      code: "code"
 output_keys:
   - "code"
 
@@ -51,13 +51,14 @@ subflows_config:
         - _target_: flows.data_transformations.RegexFirstOccurrenceExtractor
           regex: '(?<=```python)([\s\S]*?)(?=```)'
           regex_fallback: '(?<=```)([\s\S]*?)(?=```)'
-          input_key: "raw_response"
+          input_key: "api_output"
           output_key: "code"
           strip: True
           assert_unique: True
 
         - _target_: flows.data_transformations.EndOfInteraction
           end_of_interaction_string: "Final answer"
+          input_key: "api_output"
           output_key: "end_of_interaction"
 
       output_keys:

CF_CodeDebugCollabWithPlan.yaml

@@ -18,7 +18,7 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.code: "code"
+      code: "code"
 output_keys:
   - "code"
 
@@ -52,13 +52,14 @@ subflows_config:
         - _target_: flows.data_transformations.RegexFirstOccurrenceExtractor
           regex: '(?<=```python)([\s\S]*?)(?=```)'
           regex_fallback: '(?<=```)([\s\S]*?)(?=```)'
-          input_key: "raw_response"
+          input_key: "api_output"
           output_key: "code"
           strip: True
           assert_unique: True
 
         - _target_: flows.data_transformations.EndOfInteraction
           end_of_interaction_string: "Final answer"
+          input_key: "api_output"
           output_key: "end_of_interaction"
 
       output_keys:

CF_CodeDebugCritic.yaml

@@ -15,9 +15,9 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.testing_results_summary: "testing_results_summary"
-      raw_response.all_tests_passed: "all_tests_passed"
-      raw_response.code_feedback: "code_feedback"
+      testing_results_summary: "testing_results_summary"
+      all_tests_passed: "all_tests_passed"
+      code_feedback: "code_feedback"
 output_keys:
   - "testing_results_summary"
   - "all_tests_passed"

CF_CodeDebugCriticWithPlan.yaml

@@ -16,9 +16,9 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.testing_results_summary: "testing_results_summary"
-      raw_response.all_tests_passed: "all_tests_passed"
-      raw_response.code_feedback: "code_feedback"
+      testing_results_summary: "testing_results_summary"
+      all_tests_passed: "all_tests_passed"
+      code_feedback: "code_feedback"
 output_keys:
   - "testing_results_summary"
   - "all_tests_passed"

CF_CodeWithPlan.yaml

@@ -82,6 +82,7 @@ output_data_transformations:
   - _target_: flows.data_transformations.RegexFirstOccurrenceExtractor
     regex: '(?<=```python)([\s\S]*?)(?=```)'
     regex_fallback: '(?<=```)([\s\S]*?)(?=```)'
+    input_key: "api_output"
     output_key: "code"
     strip: True
     assert_unique: True

CF_Plan.yaml

@@ -24,6 +24,7 @@ output_data_transformations:
     regex: '(?<=Conceptual solution)([\s\S]*?)(?=\n\n# [A-Z]|\Z)'
     regex_fallback:
       - '(?<=Conceptual solution:)([\s\S]*?)(?=\n\n# [A-Z]|\Z)'
+    input_key: "api_output"
     output_key: "plan"
     strip: True
     assert_unique: True

CF_PlanCollab.yaml

@@ -16,7 +16,7 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.plan: "plan"
+      plan: "plan"
 output_keys:
   - "plan"
 
@@ -48,12 +48,14 @@ subflows_config:
           regex: '(?<=Conceptual solution)([\s\S]*?)(?=\n\n# [A-Z]|\Z)'
           regex_fallback:
             - '(?<=Conceptual solution:)([\s\S]*?)(?=\n\n# [A-Z]|\Z)'
+          input_key: "api_output"
           output_key: "plan"
           strip: True
           assert_unique: True
 
         - _target_: flows.data_transformations.EndOfInteraction
           end_of_interaction_string: "Final answer"
+          input_key: "api_output"
           output_key: "end_of_interaction"
 
       output_keys:
@@ -65,4 +67,4 @@ subflows_config:
       output_data_transformations:
         - _target_: flows.data_transformations.KeyRename
           old_key2new_key:
-            raw_response: "plan_feedback"
+            api_output: "plan_feedback"

CF_PlanCollab_Code.yaml

@@ -13,7 +13,7 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.code: "code"
+      code: "code"
 output_keys:
   - "code"
 

CF_PlanReflect.yaml

@@ -16,7 +16,7 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.plan: "plan"
+      plan: "plan"
 output_keys:
   - "plan"
 
@@ -34,12 +34,14 @@ subflows_config:
           regex: '(?<=Conceptual solution)([\s\S]*?)(?=\n\n# [A-Z]|\Z)'
           regex_fallback:
             - '(?<=Conceptual solution:)([\s\S]*?)(?=\n\n# [A-Z]|\Z)'
+          input_key: "api_output"
           output_key: "plan"
           strip: True
           assert_unique: True
 
         - _target_: flows.data_transformations.EndOfInteraction
           end_of_interaction_string: "Final answer"
+          input_key: "api_output"
           output_key: "end_of_interaction"
 
       output_keys:

CF_PlanReflect_Code.yaml

@@ -13,7 +13,7 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.code: "code"
+      code: "code"
 output_keys:
   - "code"
 

CF_Plan_Code.yaml

@@ -13,7 +13,7 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.code: "code"
+      code: "code"
 output_keys:
   - "code"
 

CodeTesting.py

@@ -33,14 +33,12 @@ class CodeTesting(AtomicFlow):
         return cls(**kwargs)
 
     def run(self,
-            input_data: Dict[str, Any],
-            private_keys: Optional[List[str]] = [],
-            keys_to_ignore_for_hash: Optional[List[str]] = []) -> Dict[str, Any]:
+            input_data: Dict[str, Any]) -> Dict[str, Any]:
 
         # ~~~ Retrieve the test data ~~~
         test_data = self._get_test_data(input_data)
 
         # ~~~ Run tests ~~~
-        response = self._run_tests(input_data, test_data)
+        response: Dict[str, Any] = self._run_tests(input_data, test_data)
 
         return response

FixedReply_PlanReflect.yaml

@@ -8,7 +8,7 @@ input_keys: []
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response: "plan_reflect_message"
+      fixed_reply: "plan_reflect_message"
 output_keys:
   - "plan_reflect_message"
 

LC_CodeCriticWrongAttempt.yaml

@@ -83,6 +83,6 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response: "code_feedback"
+      api_output: "code_feedback"
 output_keys:
   - "code_feedback"

LC_CodeCriticWrongAttemptWithPlan.yaml

@@ -91,6 +91,6 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response: "code_feedback"
+      api_output: "code_feedback"
 output_keys:
   - "code_feedback"

LC_CodeDebug.yaml

@@ -17,7 +17,7 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.code: "code"
+      code: "code"
 output_keys:
   - "code"
 
@@ -46,13 +46,14 @@ subflows_config:
         - _target_: flows.data_transformations.RegexFirstOccurrenceExtractor
           regex: '(?<=```python)([\s\S]*?)(?=```)'
           regex_fallback: '(?<=```)([\s\S]*?)(?=```)'
-          input_key: "raw_response"
+          input_key: "api_output"
           output_key: "code"
           strip: True
           assert_unique: True
 
         - _target_: flows.data_transformations.EndOfInteraction
           end_of_interaction_string: "Final answer"
+          input_key: "api_output"
           output_key: "end_of_interaction"
 
       output_keys:

LC_CodeDebugCollab.yaml

@@ -17,7 +17,7 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.code: "code"
+      code: "code"
 output_keys:
   - "code"
 
@@ -51,13 +51,14 @@ subflows_config:
         - _target_: flows.data_transformations.RegexFirstOccurrenceExtractor
           regex: '(?<=```python)([\s\S]*?)(?=```)'
           regex_fallback: '(?<=```)([\s\S]*?)(?=```)'
-          input_key: "raw_response"
+          input_key: "api_output"
           output_key: "code"
           strip: True
           assert_unique: True
 
         - _target_: flows.data_transformations.EndOfInteraction
           end_of_interaction_string: "Final answer"
+          input_key: "api_output"
           output_key: "end_of_interaction"
 
       output_keys:

LC_CodeDebugCollabWithPlan.yaml

@@ -18,7 +18,7 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.code: "code"
+      code: "code"
 output_keys:
   - "code"
 
@@ -52,13 +52,14 @@ subflows_config:
         - _target_: flows.data_transformations.RegexFirstOccurrenceExtractor
           regex: '(?<=```python)([\s\S]*?)(?=```)'
           regex_fallback: '(?<=```)([\s\S]*?)(?=```)'
-          input_key: "raw_response"
+          input_key: "api_output"
           output_key: "code"
           strip: True
           assert_unique: True
 
         - _target_: flows.data_transformations.EndOfInteraction
           end_of_interaction_string: "Final answer"
+          input_key: "api_output"
           output_key: "end_of_interaction"
 
       output_keys:

LC_CodeDebugCritic.yaml

@@ -15,9 +15,9 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.testing_results_summary: "testing_results_summary"
-      raw_response.all_tests_passed: "all_tests_passed"
-      raw_response.code_feedback: "code_feedback"
+      testing_results_summary: "testing_results_summary"
+      all_tests_passed: "all_tests_passed"
+      code_feedback: "code_feedback"
 output_keys:
   - "testing_results_summary"
   - "all_tests_passed"

LC_CodeDebugCriticWithPlan.yaml

@@ -16,9 +16,9 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.testing_results_summary: "testing_results_summary"
-      raw_response.all_tests_passed: "all_tests_passed"
-      raw_response.code_feedback: "code_feedback"
+      testing_results_summary: "testing_results_summary"
+      all_tests_passed: "all_tests_passed"
+      code_feedback: "code_feedback"
 output_keys:
   - "testing_results_summary"
   - "all_tests_passed"

LC_CodeTesting.yaml

@@ -12,7 +12,7 @@ output_keys:
   - "testing_results_summary"
 output_data_transformations:
   - _target_: .src.data_transformations.CorrectnessFlag
-    input_key: "raw_response.public_tests_results"
+    input_key: "public_tests_results"
     output_key: "all_tests_passed"
   - _target_: .src.data_transformations.TestingResultsSummaryGeneration
     output_key: "testing_results_summary"

LC_CodeWithPlan.yaml

@@ -83,6 +83,7 @@ output_data_transformations:
   - _target_: flows.data_transformations.RegexFirstOccurrenceExtractor
     regex: '(?<=```python)([\s\S]*?)(?=```)'
     regex_fallback: '(?<=```)([\s\S]*?)(?=```)'
+    input_key: "api_output"
     output_key: "code"
     strip: True
     assert_unique: True

LC_Plan.yaml

@@ -23,6 +23,7 @@ output_data_transformations:
     regex: '(?<=Conceptual solution)([\s\S]*?)(?=\n\n# [A-Z]|\Z)'
     regex_fallback:
       - '(?<=Conceptual solution:)([\s\S]*?)(?=\n\n# [A-Z]|\Z)'
+    input_key: "api_output"
     output_key: "plan"
     strip: True
     assert_unique: True

LC_PlanCollab.yaml

@@ -16,7 +16,7 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.plan: "plan"
+      plan: "plan"
 output_keys:
   - "plan"
 
@@ -48,12 +48,14 @@ subflows_config:
           regex: '(?<=Conceptual solution)([\s\S]*?)(?=\n\n# [A-Z]|\Z)'
           regex_fallback:
             - '(?<=Conceptual solution:)([\s\S]*?)(?=\n\n# [A-Z]|\Z)'
+          input_key: "api_output"
           output_key: "plan"
           strip: True
           assert_unique: True
 
         - _target_: flows.data_transformations.EndOfInteraction
           end_of_interaction_string: "Final answer"
+          input_key: "api_output"
           output_key: "end_of_interaction"
 
       output_keys:
@@ -65,4 +67,4 @@ subflows_config:
       output_data_transformations:
         - _target_: flows.data_transformations.KeyRename
           old_key2new_key:
-            raw_response: "plan_feedback"
+            api_output: "plan_feedback"

LC_PlanCollab_Code.yaml

@@ -13,7 +13,7 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.code: "code"
+      code: "code"
 output_keys:
   - "code"
 

LC_PlanReflect.yaml

@@ -15,7 +15,7 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.plan: "plan"
+      plan: "plan"
 output_keys:
   - "plan"
 
@@ -33,12 +33,14 @@ subflows_config:
           regex: '(?<=Conceptual solution)([\s\S]*?)(?=\n\n# [A-Z]|\Z)'
           regex_fallback:
             - '(?<=Conceptual solution:)([\s\S]*?)(?=\n\n# [A-Z]|\Z)'
+          input_key: "api_output"
           output_key: "plan"
           strip: True
           assert_unique: True
 
         - _target_: flows.data_transformations.EndOfInteraction
           end_of_interaction_string: "Final answer"
+          input_key: "api_output"
           output_key: "end_of_interaction"
 
       output_keys:

LC_Plan_Code.yaml

@@ -13,7 +13,7 @@ input_keys:
 output_data_transformations:
   - _target_: flows.data_transformations.KeyRename
     old_key2new_key:
-      raw_response.code: "code"
+      code: "code"
 output_keys:
   - "code"
 

src/data_transformations/testing_results_summary_generation.py

@@ -17,7 +17,7 @@ class TestingResultsSummaryGeneration(DataTransformation):
             data_dict[self.output_key] = self.params["no_error_template"]
             return data_dict
 
-        test_data = unflatten_dict(data_dict)["raw_response"]
+        test_data = unflatten_dict(data_dict)
 
         if not test_data["compilation_status"]:
             # compilation error occurred