feat(backend): Implement multi-take sequence differencing and text formatting utility

tests/test_synthesis_formatter.py

@@ -0,0 +1,59 @@
+import pytest
+from src.synthesis_formatter import format_takes_diff
+
+def test_format_takes_diff_empty():
+ assert format_takes_diff({}) == ""
+
+def test_format_takes_diff_single_take():
+ takes = {
+  "take1": [
+   {"role": "user", "content": "hello"},
+   {"role": "assistant", "content": "hi"}
+  ]
+ }
+ expected = "=== Shared History ===\nuser: hello\nassistant: hi\n\n=== Variations ===\n"
+ assert format_takes_diff(takes) == expected
+
+def test_format_takes_diff_common_prefix():
+ takes = {
+  "take1": [
+   {"role": "user", "content": "hello"},
+   {"role": "assistant", "content": "hi"},
+   {"role": "user", "content": "how are you?"},
+   {"role": "assistant", "content": "I am fine."}
+  ],
+  "take2": [
+   {"role": "user", "content": "hello"},
+   {"role": "assistant", "content": "hi"},
+   {"role": "user", "content": "what is the time?"},
+   {"role": "assistant", "content": "It is noon."}
+  ]
+ }
+ expected = (
+  "=== Shared History ===\n"
+  "user: hello\n"
+  "assistant: hi\n\n"
+  "=== Variations ===\n"
+  "[take1]\n"
+  "user: how are you?\n"
+  "assistant: I am fine.\n\n"
+  "[take2]\n"
+  "user: what is the time?\n"
+  "assistant: It is noon.\n"
+ )
+ assert format_takes_diff(takes) == expected
+
+def test_format_takes_diff_no_common_prefix():
+ takes = {
+  "take1": [{"role": "user", "content": "a"}],
+  "take2": [{"role": "user", "content": "b"}]
+ }
+ expected = (
+  "=== Shared History ===\n\n"
+  "=== Variations ===\n"
+  "[take1]\n"
+  "user: a\n\n"
+  "[take2]\n"
+  "user: b\n"
+ )
+ assert format_takes_diff(takes) == expected