Merge pull request #364 from costajohnt/refactor/reactive-compact-summarize-old-history

refactor: summarize only trimmed history in reactive_compact

s08_context_compact/README.en.md

@@ -46,10 +46,12 @@ def snip_compact(messages, max_messages=50):
     if len(messages) <= max_messages:
         return messages
     head_end, tail_start = 3, len(messages) - (max_messages - 3)
-    if _message_has_tool_use(messages[head_end - 1]):
+    if head_end > 0 and _message_has_tool_use(messages[head_end - 1]):
         while head_end < len(messages) and _is_tool_result_message(messages[head_end]):
             head_end += 1
-    if _is_tool_result_message(messages[tail_start]) and _message_has_tool_use(messages[tail_start - 1]):
+    if (tail_start > 0 and tail_start < len(messages)
+            and _is_tool_result_message(messages[tail_start])
+            and _message_has_tool_use(messages[tail_start - 1])):
         tail_start -= 1
     snipped = tail_start - head_end
     placeholder = {"role": "user", "content": f"[snipped {snipped} messages from conversation middle]"}
@@ -139,10 +141,12 @@ This triggers **reactive_compact**: more aggressive than compact_history, it ret
 ```python
 def reactive_compact(messages):
     transcript = write_transcript(messages)
-    summary = summarize_history(messages)
     tail_start = max(0, len(messages) - 5)
-    if _is_tool_result_message(messages[tail_start]) and _message_has_tool_use(messages[tail_start - 1]):
+    if (tail_start > 0 and tail_start < len(messages)
+            and _is_tool_result_message(messages[tail_start])
+            and _message_has_tool_use(messages[tail_start - 1])):
         tail_start -= 1
+    summary = summarize_history(messages[:tail_start])
     return [{"role": "user",
              "content": f"[Reactive compact]\n\n{summary}"}, *messages[tail_start:]]
 ```

s08_context_compact/README.ja.md

@@ -46,10 +46,12 @@ def snip_compact(messages, max_messages=50):
     if len(messages) <= max_messages:
         return messages
     head_end, tail_start = 3, len(messages) - (max_messages - 3)
-    if _message_has_tool_use(messages[head_end - 1]):
+    if head_end > 0 and _message_has_tool_use(messages[head_end - 1]):
         while head_end < len(messages) and _is_tool_result_message(messages[head_end]):
             head_end += 1
-    if _is_tool_result_message(messages[tail_start]) and _message_has_tool_use(messages[tail_start - 1]):
+    if (tail_start > 0 and tail_start < len(messages)
+            and _is_tool_result_message(messages[tail_start])
+            and _message_has_tool_use(messages[tail_start - 1])):
         tail_start -= 1
     snipped = tail_start - head_end
     placeholder = {"role": "user", "content": f"[snipped {snipped} messages from conversation middle]"}
@@ -139,10 +141,12 @@ API がまだ `prompt_too_long`（413）を返すことがある。コンテキ
 ```python
 def reactive_compact(messages):
     transcript = write_transcript(messages)
-    summary = summarize_history(messages)
     tail_start = max(0, len(messages) - 5)
-    if _is_tool_result_message(messages[tail_start]) and _message_has_tool_use(messages[tail_start - 1]):
+    if (tail_start > 0 and tail_start < len(messages)
+            and _is_tool_result_message(messages[tail_start])
+            and _message_has_tool_use(messages[tail_start - 1])):
         tail_start -= 1
+    summary = summarize_history(messages[:tail_start])
     return [{"role": "user",
              "content": f"[Reactive compact]\n\n{summary}"}, *messages[tail_start:]]
 ```

s08_context_compact/README.md

@@ -46,10 +46,12 @@ def snip_compact(messages, max_messages=50):
     if len(messages) <= max_messages:
         return messages
     head_end, tail_start = 3, len(messages) - (max_messages - 3)
-    if _message_has_tool_use(messages[head_end - 1]):
+    if head_end > 0 and _message_has_tool_use(messages[head_end - 1]):
         while head_end < len(messages) and _is_tool_result_message(messages[head_end]):
             head_end += 1
-    if _is_tool_result_message(messages[tail_start]) and _message_has_tool_use(messages[tail_start - 1]):
+    if (tail_start > 0 and tail_start < len(messages)
+            and _is_tool_result_message(messages[tail_start])
+            and _message_has_tool_use(messages[tail_start - 1])):
         tail_start -= 1
     snipped = tail_start - head_end
     placeholder = {"role": "user", "content": f"[snipped {snipped} messages from conversation middle]"}
@@ -139,10 +141,12 @@ def compact_history(messages):
 ```python
 def reactive_compact(messages):
     transcript = write_transcript(messages)
-    summary = summarize_history(messages)
     tail_start = max(0, len(messages) - 5)
-    if _is_tool_result_message(messages[tail_start]) and _message_has_tool_use(messages[tail_start - 1]):
+    if (tail_start > 0 and tail_start < len(messages)
+            and _is_tool_result_message(messages[tail_start])
+            and _message_has_tool_use(messages[tail_start - 1])):
         tail_start -= 1
+    summary = summarize_history(messages[:tail_start])
     return [{"role": "user",
              "content": f"[Reactive compact]\n\n{summary}"}, *messages[tail_start:]]
 ```

s08_context_compact/code.py

@@ -382,12 +382,12 @@ def compact_history(messages):
 # Emergency: reactiveCompact — on API error
 def reactive_compact(messages):
     transcript = write_transcript(messages)
-    summary = summarize_history(messages)
     tail_start = max(0, len(messages) - 5)
     if (tail_start > 0 and tail_start < len(messages)
             and _is_tool_result_message(messages[tail_start])
             and _message_has_tool_use(messages[tail_start - 1])):
         tail_start -= 1
+    summary = summarize_history(messages[:tail_start])
     return [{"role": "user", "content": f"[Reactive compact]\n\n{summary}"}, *messages[tail_start:]]
 
 

s09_memory/code.py

@@ -540,12 +540,12 @@ def compact_history(msgs):
 
 def reactive_compact(msgs):
     write_transcript(msgs)
-    summary = summarize_history(msgs)
     tail_start = max(0, len(msgs) - 5)
     if (tail_start > 0 and tail_start < len(msgs)
             and _is_tool_result_message(msgs[tail_start])
             and _message_has_tool_use(msgs[tail_start - 1])):
         tail_start -= 1
+    summary = summarize_history(msgs[:tail_start])
     return [{"role": "user", "content": f"[Reactive compact]\n\n{summary}"}, *msgs[tail_start:]]
 
 

s20_comprehensive/code.py

@@ -1190,15 +1190,15 @@ def compact_history(messages: list) -> list:
 def reactive_compact(messages: list) -> list:
     transcript = write_transcript(messages)
     print(f"  \033[31m[reactive compact] transcript saved: {transcript}\033[0m")
-    try:
-        summary = summarize_history(messages)
-    except Exception:
-        summary = "Earlier conversation was trimmed after a prompt-too-long error."
     tail_start = max(0, len(messages) - 5)
     if (tail_start > 0 and tail_start < len(messages)
             and is_tool_result_message(messages[tail_start])
             and message_has_tool_use(messages[tail_start - 1])):
         tail_start -= 1
+    try:
+        summary = summarize_history(messages[:tail_start])
+    except Exception:
+        summary = "Earlier conversation was trimmed after a prompt-too-long error."
     return [{"role": "user", "content": f"[Reactive compact]\n\n{summary}"},
             *messages[tail_start:]]
 

tests/test_compaction_tool_pairs.py

@@ -178,6 +178,72 @@ class CompactionToolPairTests(unittest.TestCase):
                 self.assertEqual(compacted[1], messages[3])
                 assert_no_orphan_tool_results(self, compacted)
 
+    def test_reactive_compact_summarizes_only_old_history(self):
+        messages = [
+            user_text(),
+            assistant_text(),
+            user_text(),
+            assistant_text(),
+            user_text(),
+            assistant_text(),
+            user_text(),
+            assistant_text(),
+            user_text(),
+        ]
+
+        for name, path in MODULES.items():
+            with self.subTest(name=name), tempfile.TemporaryDirectory() as tmp:
+                module = load_module(f"{name}_reactive_oldhist_under_test", path, Path(tmp))
+                module.write_transcript = lambda _messages: Path("transcript.jsonl")
+                captured = {}
+
+                def fake_summarize(passed, _store=captured):
+                    _store["messages"] = list(passed)
+                    return "summary"
+
+                module.summarize_history = fake_summarize
+                compacted = module.reactive_compact(list(messages))
+                # The summary must cover only the old history, not the kept tail.
+                self.assertEqual(captured["messages"], messages[:4])
+                # The recent tail is appended verbatim after the summary message.
+                self.assertEqual(compacted[1:], messages[4:])
+                assert_no_orphan_tool_results(self, compacted)
+
+    def test_reactive_compact_summary_excludes_tail_pair_pulled_in(self):
+        # A tool_use/tool_result pair straddles the tail boundary, so the
+        # adjustment pulls the tool_use into the kept tail. The summary must
+        # cover only what stays trimmed (messages[:adjusted_tail_start]), i.e.
+        # it must not re-summarize the tool_use that is kept verbatim.
+        messages = [
+            user_text(),
+            assistant_text(),
+            user_text(),
+            tool_use_message("reactive-tool"),
+            tool_result_message("reactive-tool"),
+            assistant_text(),
+            user_text(),
+            assistant_text(),
+            user_text(),
+        ]
+
+        for name, path in MODULES.items():
+            with self.subTest(name=name), tempfile.TemporaryDirectory() as tmp:
+                module = load_module(f"{name}_reactive_pairscope_under_test", path, Path(tmp))
+                module.write_transcript = lambda _messages: Path("transcript.jsonl")
+                captured = {}
+
+                def fake_summarize(passed, _store=captured):
+                    _store["messages"] = list(passed)
+                    return "summary"
+
+                module.summarize_history = fake_summarize
+                compacted = module.reactive_compact(list(messages))
+                # tail_start starts at 4, decrements to 3 to keep the pair intact.
+                self.assertEqual(captured["messages"], messages[:3])
+                self.assertEqual(compacted[1], messages[3])
+                self.assertEqual(compacted[1:], messages[3:])
+                assert_no_orphan_tool_results(self, compacted)
+
     def test_s20_has_tool_use_still_accepts_content_blocks(self):
         with tempfile.TemporaryDirectory() as tmp:
             module = load_module("s20_has_tool_use_under_test", MODULES["s20"], Path(tmp))