Fix compaction splitting tool-use/result pairs

s08_context_compact/README.en.md

@@ -39,20 +39,24 @@ Core design: cheap first, expensive last.
 
 The agent ran 80 turns of conversation, accumulating 160 `messages`. The very first "help me create hello.py" is barely relevant to current work, yet it still occupies space.
 
-Message count exceeds 50 → keep the first 3 (initial context) and the last 47 (current work), trim the middle:
+Message count exceeds 50 → keep the first 3 (initial context) and the last 47 (current work), trim the middle; the only extra boundary rule is that `assistant(tool_use)` must not be separated from the following `user(tool_result)`:
 
 ```python
 def snip_compact(messages, max_messages=50):
     if len(messages) <= max_messages:
         return messages
-    keep_head, keep_tail = 3, max_messages - 3
-    snipped = len(messages) - keep_head - keep_tail
-    placeholder = {"role": "user",
-                   "content": f"[snipped {snipped} messages from conversation middle]"}
-    return messages[:keep_head] + [placeholder] + messages[-keep_tail:]
+    head_end, tail_start = 3, len(messages) - (max_messages - 3)
+    if 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 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]"}
+    return messages[:head_end] + [placeholder] + messages[tail_start:]
 ```
 
-Entire messages are trimmed, but `tool_result` content within remaining messages keeps accumulating — message #34 may still hold 30KB of old file contents. → L2.
+Messages are still trimmed directly; this just adds one boundary guard. `tool_result` content within remaining messages still keeps accumulating — message #34 may still hold 30KB of old file contents. → L2.
 
 ### L2: micro_compact — Placeholder for Old Tool Results
 
@@ -130,15 +134,17 @@ def compact_history(messages):
 
 Sometimes the API still returns `prompt_too_long` (413) — when context grows faster than compression triggers.
 
-This triggers **reactive_compact**: more aggressive than compact_history, it retreats from the tail, trimming to an API-acceptable size with byte-level precision, keeping only the last 5 messages + summary.
+This triggers **reactive_compact**: more aggressive than compact_history, it retreats from the tail, but still avoids leaving an orphaned `tool_result`.
 
 ```python
 def reactive_compact(messages):
     transcript = write_transcript(messages)
     summary = summarize_history(messages)
-    tail = messages[-5:]
+    tail_start = max(0, len(messages) - 5)
+    if is_tool_result_message(messages[tail_start]) and has_tool_use(messages[tail_start - 1]):
+        tail_start -= 1
     return [{"role": "user",
-             "content": f"[Reactive compact]\n\n{summary}"}, *tail]
+             "content": f"[Reactive compact]\n\n{summary}"}, *messages[tail_start:]]
 ```
 
 Reactive compact has a retry limit (default 1). If it still fails, an exception is raised instead of looping forever. Full error recovery is deferred to s11.

s08_context_compact/README.ja.md

@@ -39,20 +39,24 @@ s07 のフック構造、スキルロード、サブ Agent の骨格を維持し
 
 Agent が 80 ラウンドの会話を実行し、`messages` が 160 件まで溜まった。先頭の「hello.py を作って」は現在の作業とほぼ無関係だが、スペースを占有し続けている。
 
-メッセージ数が 50 を超えた場合 → 先頭 3 件（初期コンテキスト）と末尾 47 件（現在の作業）を保持し、中間を切り捨て：
+メッセージ数が 50 を超えた場合 → 先頭 3 件（初期コンテキスト）と末尾 47 件（現在の作業）を保持して中間を切り詰める。ただし切れ目だけは調整し、`assistant(tool_use)` と後続の `user(tool_result)` を分断しない：
 
 ```python
 def snip_compact(messages, max_messages=50):
     if len(messages) <= max_messages:
         return messages
-    keep_head, keep_tail = 3, max_messages - 3
-    snipped = len(messages) - keep_head - keep_tail
-    placeholder = {"role": "user",
-                   "content": f"[snipped {snipped} messages from conversation middle]"}
-    return messages[:keep_head] + [placeholder] + messages[-keep_tail:]
+    head_end, tail_start = 3, len(messages) - (max_messages - 3)
+    if 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 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]"}
+    return messages[:head_end] + [placeholder] + messages[tail_start:]
 ```
 
-メッセージ全体は切り捨てたが、残ったメッセージ内の `tool_result` 内容はまだ蓄積され続けている。34 番目のメッセージに 30KB の古いファイル内容が残っているかもしれない。→ L2。
+切り捨て自体は単純なままで、境界だけを保護する。残ったメッセージ内の `tool_result` 内容はまだ蓄積され続けている。34 番目のメッセージに 30KB の古いファイル内容が残っているかもしれない。→ L2。
 
 ### L2: micro_compact — 古いツール結果をプレースホルダに置換
 
@@ -130,15 +134,17 @@ def compact_history(messages):
 
 API がまだ `prompt_too_long`（413）を返すことがある。コンテキストの増加速度が圧縮のトリガー速度を上回る場合。
 
-この時 **reactive_compact** がトリガーされる：compact_history よりもさらに積極的で、末尾からバイト単位の精度で API が受け入れ可能なサイズまで切り詰め、最後の 5 件のメッセージ + 要約のみを保持。
+この時 **reactive_compact** がトリガーされる：compact_history よりもさらに積極的だが、末尾を残す際も孤立した `tool_result` を残さないようにする。
 
 ```python
 def reactive_compact(messages):
     transcript = write_transcript(messages)
     summary = summarize_history(messages)
-    tail = messages[-5:]
+    tail_start = max(0, len(messages) - 5)
+    if is_tool_result_message(messages[tail_start]) and has_tool_use(messages[tail_start - 1]):
+        tail_start -= 1
     return [{"role": "user",
-             "content": f"[Reactive compact]\n\n{summary}"}, *tail]
+             "content": f"[Reactive compact]\n\n{summary}"}, *messages[tail_start:]]
 ```
 
 reactive compact にはリトライ上限がある（デフォルト 1 回）。さらに失敗した場合は例外をスローし、無限ループしない。完全なエラー回復ロジックは s11 に委ねる。

s08_context_compact/README.md

@@ -39,20 +39,24 @@ Agent 跑着跑着，不动了。
 
 Agent 跑了 80 轮对话，`messages` 攒了 160 条。最前面的"帮我创建 hello.py"和当前工作几乎无关了，但全占着位置。
 
-消息数超过 50 条 → 保留头部 3 条（初始上下文）和尾部 47 条（当前工作），中间裁掉：
+消息数超过 50 条 → 保留头部 3 条（初始上下文）和尾部 47 条（当前工作），中间裁掉；唯一额外边界条件是，不能把 `assistant(tool_use)` 和后面的 `user(tool_result)` 拆开：
 
 ```python
 def snip_compact(messages, max_messages=50):
     if len(messages) <= max_messages:
         return messages
-    keep_head, keep_tail = 3, max_messages - 3
-    snipped = len(messages) - keep_head - keep_tail
-    placeholder = {"role": "user",
-                   "content": f"[snipped {snipped} messages from conversation middle]"}
-    return messages[:keep_head] + [placeholder] + messages[-keep_tail:]
+    head_end, tail_start = 3, len(messages) - (max_messages - 3)
+    if 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 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]"}
+    return messages[:head_end] + [placeholder] + messages[tail_start:]
 ```
 
-裁掉了整条消息，但剩下的消息里 `tool_result` 内容仍在累积——第 34 条消息里可能躺着 30KB 的旧文件内容。→ L2。
+裁掉的是消息本身，只是在切口处多做一步保护；剩下的消息里 `tool_result` 内容仍在累积——第 34 条消息里可能躺着 30KB 的旧文件内容。→ L2。
 
 ### L2: micro_compact — 旧工具结果占位
 
@@ -130,15 +134,17 @@ def compact_history(messages):
 
 有时候 API 还是返回 `prompt_too_long`（413），上下文增长速度快于压缩触发速度时。
 
-这时触发 **reactive_compact**：比 compact_history 更激进，从尾部回退，以字节级精度裁剪到 API 可接受的大小，只保留最后 5 条消息 + 摘要。
+这时触发 **reactive_compact**：比 compact_history 更激进，从尾部回退，但仍要避免留下孤立 `tool_result`。
 
 ```python
 def reactive_compact(messages):
     transcript = write_transcript(messages)
     summary = summarize_history(messages)
-    tail = messages[-5:]
+    tail_start = max(0, len(messages) - 5)
+    if is_tool_result_message(messages[tail_start]) and has_tool_use(messages[tail_start - 1]):
+        tail_start -= 1
     return [{"role": "user",
-             "content": f"[Reactive compact]\n\n{summary}"}, *tail]
+             "content": f"[Reactive compact]\n\n{summary}"}, *messages[tail_start:]]
 ```
 
 reactive compact 有重试上限（默认 1 次）。再失败就抛出异常，不无限循环。完整的错误恢复逻辑留给 s11。

s08_context_compact/code.py

@@ -250,13 +250,40 @@ def spawn_subagent(task: str) -> str:
 
 def estimate_size(msgs): return len(str(msgs))
 
+def _block_type(block):
+    return getattr(block, "type", None) if not isinstance(block, dict) else block.get("type")
+
+def _has_tool_use(msg):
+    if msg.get("role") != "assistant":
+        return False
+    content = msg.get("content")
+    if not isinstance(content, list):
+        return False
+    return any(_block_type(block) == "tool_use" for block in content)
+
+def _is_tool_result_message(msg):
+    if msg.get("role") != "user":
+        return False
+    content = msg.get("content")
+    if not isinstance(content, list):
+        return False
+    return any(isinstance(block, dict) and block.get("type") == "tool_result" for block in content)
+
 
 # L1: snipCompact — trim middle messages
 def snip_compact(messages, max_messages=50):
     if len(messages) <= max_messages: return messages
     keep_head, keep_tail = 3, max_messages - 3
-    snipped = len(messages) - keep_head - keep_tail
-    return messages[:keep_head] + [{"role": "user", "content": f"[snipped {snipped} messages]"}] + messages[-keep_tail:]
+    head_end, tail_start = keep_head, len(messages) - keep_tail
+    if head_end > 0 and _has_tool_use(messages[head_end - 1]):
+        while head_end < len(messages) and _is_tool_result_message(messages[head_end]):
+            head_end += 1
+    if tail_start > 0 and tail_start < len(messages) and _is_tool_result_message(messages[tail_start]) and _has_tool_use(messages[tail_start - 1]):
+        tail_start -= 1
+    if head_end >= tail_start:
+        return messages
+    snipped = tail_start - head_end
+    return messages[:head_end] + [{"role": "user", "content": f"[snipped {snipped} messages]"}] + messages[tail_start:]
 
 
 # L2: microCompact — old result placeholders
@@ -333,7 +360,10 @@ def compact_history(messages):
 def reactive_compact(messages):
     transcript = write_transcript(messages)
     summary = summarize_history(messages)
-    return [{"role": "user", "content": f"[Reactive compact]\n\n{summary}"}, *messages[-5:]]
+    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 _has_tool_use(messages[tail_start - 1]):
+        tail_start -= 1
+    return [{"role": "user", "content": f"[Reactive compact]\n\n{summary}"}, *messages[tail_start:]]
 
 
 # ═══════════════════════════════════════════════════════════

s09_memory/code.py

@@ -451,9 +451,36 @@ def spawn_subagent(task: str) -> str:
 
 def estimate_size(msgs): return len(str(msgs))
 
+def _block_type(block):
+    return getattr(block, "type", None) if not isinstance(block, dict) else block.get("type")
+
+def _has_tool_use(msg):
+    if msg.get("role") != "assistant":
+        return False
+    content = msg.get("content")
+    if not isinstance(content, list):
+        return False
+    return any(_block_type(block) == "tool_use" for block in content)
+
+def _is_tool_result_message(msg):
+    if msg.get("role") != "user":
+        return False
+    content = msg.get("content")
+    if not isinstance(content, list):
+        return False
+    return any(isinstance(block, dict) and block.get("type") == "tool_result" for block in content)
+
 def snip_compact(msgs, mx=50):
     if len(msgs) <= mx: return msgs
-    return msgs[:3] + [{"role": "user", "content": f"[snipped {len(msgs)-mx} msgs]"}] + msgs[-(mx-3):]
+    head_end, tail_start = 3, len(msgs) - (mx - 3)
+    if head_end > 0 and _has_tool_use(msgs[head_end - 1]):
+        while head_end < len(msgs) and _is_tool_result_message(msgs[head_end]):
+            head_end += 1
+    if tail_start > 0 and tail_start < len(msgs) and _is_tool_result_message(msgs[tail_start]) and _has_tool_use(msgs[tail_start - 1]):
+        tail_start -= 1
+    if head_end >= tail_start:
+        return msgs
+    return msgs[:head_end] + [{"role": "user", "content": f"[snipped {tail_start - head_end} msgs]"}] + msgs[tail_start:]
 
 def collect_tool_results(msgs):
     blocks = []
@@ -514,7 +541,10 @@ def compact_history(msgs):
 def reactive_compact(msgs):
     write_transcript(msgs)
     summary = summarize_history(msgs)
-    return [{"role": "user", "content": f"[Reactive compact]\n\n{summary}"}, *msgs[-5:]]
+    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 _has_tool_use(msgs[tail_start - 1]):
+        tail_start -= 1
+    return [{"role": "user", "content": f"[Reactive compact]\n\n{summary}"}, *msgs[tail_start:]]
 
 
 # ═══════════════════════════════════════════════════════════

s20_comprehensive/code.py

@@ -1042,6 +1042,26 @@ def spawn_subagent(description: str) -> str:
 def estimate_size(messages: list) -> int:
     return len(json.dumps(messages, default=str))
 
+def block_type(block):
+    return getattr(block, "type", None) if not isinstance(block, dict) else block.get("type")
+
+def has_tool_use(message: dict) -> bool:
+    if message.get("role") != "assistant":
+        return False
+    content = message.get("content")
+    if not isinstance(content, list):
+        return False
+    return any(block_type(block) == "tool_use" for block in content)
+
+def is_tool_result_message(message: dict) -> bool:
+    if message.get("role") != "user":
+        return False
+    content = message.get("content")
+    if not isinstance(content, list):
+        return False
+    return any(isinstance(block, dict) and block.get("type") == "tool_result"
+               for block in content)
+
 
 def collect_tool_results(messages: list):
     found = []
@@ -1093,11 +1113,18 @@ def tool_result_budget(messages: list, max_bytes: int = 200_000) -> list:
 def snip_compact(messages: list, max_messages: int = 50) -> list:
     if len(messages) <= max_messages:
         return messages
-    keep_head, keep_tail = 3, max_messages - 3
-    snipped = len(messages) - keep_head - keep_tail
-    return (messages[:keep_head]
+    head_end, tail_start = 3, len(messages) - (max_messages - 3)
+    if head_end > 0 and has_tool_use(messages[head_end - 1]):
+        while head_end < len(messages) and is_tool_result_message(messages[head_end]):
+            head_end += 1
+    if tail_start > 0 and tail_start < len(messages) and is_tool_result_message(messages[tail_start]) and has_tool_use(messages[tail_start - 1]):
+        tail_start -= 1
+    if head_end >= tail_start:
+        return messages
+    snipped = tail_start - head_end
+    return (messages[:head_end]
             + [{"role": "user", "content": f"[snipped {snipped} messages]"}]
-            + messages[-keep_tail:])
+            + messages[tail_start:])
 
 
 def micro_compact(messages: list) -> list:
@@ -1145,8 +1172,11 @@ def reactive_compact(messages: list) -> list:
         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 has_tool_use(messages[tail_start - 1]):
+        tail_start -= 1
     return [{"role": "user", "content": f"[Reactive compact]\n\n{summary}"},
-            *messages[-5:]]
+            *messages[tail_start:]]
 
 
 # ── Error Recovery ──