fix(anthropic): also enforce leading-user + empty-array recovery

Extend `_merge_consecutive` so the three invariants from
`LLMProvider._enforce_role_alternation` all hold for Anthropic:

1. collapse consecutive same-role turns (unchanged)
2. no trailing assistant — Anthropic rejects prefill (unchanged)
3. no leading assistant — Anthropic requires the first turn be user
4. non-empty messages array — recover the last stripped assistant as a
   user turn when every turn got stripped, so callers don't hit a
   secondary "messages array empty" 400

Anthropic-specific wrinkle: `tool_use` blocks live inside `content` (not
a separate `tool_calls` field) and are illegal inside user turns, so
both recovery paths skip any message carrying them rather than silently
producing a malformed request.

Adds 4 unit tests covering the new branches, including the tool_use
opt-outs, and updates the existing `test_single_assistant_stripped` to
reflect the new rerouting contract.

Made-with: Cursor

nanobot/providers/anthropic_provider.py

@@ -246,12 +246,39 @@ class AnthropicProvider(LLMProvider):
         }
 
     @staticmethod
-    def _merge_consecutive(msgs: list[dict[str, Any]]) -> list[dict[str, Any]]:
+    def _has_tool_use(msg: dict[str, Any]) -> bool:
-        """Anthropic requires alternating user/assistant roles.
+        """True if ``msg.content`` carries any ``tool_use`` block.
 
-        Also strips trailing assistant messages since Anthropic does not
+        Anthropic forbids ``tool_use`` inside ``user`` turns, so messages that
-        support assistant-message prefill and will reject the request with
+        issued a tool call cannot be safely rerouted when we patch the role.
-        a 400 error if the conversation ends with an assistant turn.
+        """
+        content = msg.get("content")
+        if not isinstance(content, list):
+            return False
+        return any(
+            isinstance(block, dict) and block.get("type") == "tool_use"
+            for block in content
+        )
+
+    @staticmethod
+    def _merge_consecutive(msgs: list[dict[str, Any]]) -> list[dict[str, Any]]:
+        """Normalize a message sequence for Anthropic's ``/messages`` endpoint.
+
+        Anthropic's contract is stricter than OpenAI's:
+
+        1. Consecutive same-role turns must be collapsed into one.
+        2. The conversation cannot end with an ``assistant`` turn — Anthropic
+           does not support assistant-message prefill and returns 400.
+        3. The conversation cannot start with an ``assistant`` turn — the
+           first message must be ``user``.
+
+        Rules 2 and 3 mirror ``LLMProvider._enforce_role_alternation`` in
+        ``base.py``, which applies the equivalent invariants to OpenAI-compat
+        providers.  The only Anthropic-specific wrinkle: ``tool_use`` blocks
+        live inside ``content`` (not a separate ``tool_calls`` field) and are
+        invalid inside ``user`` turns, so the recovery paths below must skip
+        any message carrying them rather than silently producing a malformed
+        request.
         """
         merged: list[dict[str, Any]] = []
         for msg in msgs:
@@ -268,10 +295,34 @@ class AnthropicProvider(LLMProvider):
             else:
                 merged.append(msg)
 
-        # Drop trailing assistant messages to avoid Anthropic's
+        # Rule 2: strip trailing assistant turns — Anthropic rejects prefill.
-        # "does not support assistant message prefill" 400 error.
+        last_popped: dict[str, Any] | None = None
         while merged and merged[-1].get("role") == "assistant":
-            merged.pop()
+            last_popped = merged.pop()
+
+        # Recovery for rule 2: if stripping removed every turn, reroute the
+        # last popped assistant as a user turn so upstream code still gets a
+        # valid request instead of a secondary "messages array empty" 400.
+        # Skip when the message carried ``tool_use`` blocks (see _has_tool_use).
+        if (
+            not merged
+            and last_popped is not None
+            and not AnthropicProvider._has_tool_use(last_popped)
+        ):
+            merged.append({"role": "user", "content": last_popped.get("content")})
+
+        # Rule 3: prepend a synthetic opener if the first surviving turn is an
+        # assistant (e.g. upstream history truncation dropped the original
+        # user request).  ``tool_use``-carrying assistants are left alone —
+        # that message will still fail validation, but injecting an opener
+        # before it would orphan the tool_use/tool_result pair that follows,
+        # turning a recoverable 400 into a harder-to-diagnose one.
+        if (
+            merged
+            and merged[0].get("role") == "assistant"
+            and not AnthropicProvider._has_tool_use(merged[0])
+        ):
+            merged.insert(0, {"role": "user", "content": "(conversation continued)"})
 
         return merged
 

tests/providers/test_anthropic_merge_consecutive.py

@@ -60,7 +60,80 @@ class TestMergeConsecutive:
         result = AnthropicProvider._merge_consecutive(msgs)
         assert len(result) == 1
 
-    def test_single_assistant_stripped(self):
+    def test_single_assistant_rerouted_to_user(self):
+        """When stripping leaves nothing, the last assistant is rerouted to
+        ``user`` so we don't produce an empty messages array."""
         msgs = [{"role": "assistant", "content": "hi"}]
         result = AnthropicProvider._merge_consecutive(msgs)
-        assert len(result) == 0
+        assert len(result) == 1
+        assert result[0]["role"] == "user"
+        assert result[0]["content"] == "hi"
+
+    def test_all_assistants_collapse_then_rerouted(self):
+        """Consecutive trailing assistants merge into one, which is then
+        rerouted as a user turn carrying the merged content."""
+        msgs = [
+            {"role": "assistant", "content": "a"},
+            {"role": "assistant", "content": "b"},
+        ]
+        result = AnthropicProvider._merge_consecutive(msgs)
+        assert len(result) == 1
+        assert result[0]["role"] == "user"
+        # "b" was merged into "a"'s block list during the merge pass.
+        assert result[0]["content"] == [
+            {"type": "text", "text": "a"},
+            {"type": "text", "text": "b"},
+        ]
+
+    def test_assistant_with_tool_use_not_rerouted(self):
+        """A trailing assistant carrying ``tool_use`` blocks cannot become a
+        user turn (Anthropic rejects ``tool_use`` inside user messages), so
+        the method returns an empty list rather than forging a bad request."""
+        msgs = [
+            {
+                "role": "assistant",
+                "content": [
+                    {"type": "text", "text": "let me search"},
+                    {"type": "tool_use", "id": "t1", "name": "search", "input": {}},
+                ],
+            }
+        ]
+        result = AnthropicProvider._merge_consecutive(msgs)
+        assert result == []
+
+    def test_leading_assistant_gets_synthetic_user(self):
+        """If the first turn is a bare assistant (e.g. history truncation
+        dropped the original user request), prepend a synthetic opener so
+        the conversation still starts with ``user``."""
+        msgs = [
+            {"role": "assistant", "content": "hi"},
+            {"role": "user", "content": "ok"},
+            {"role": "assistant", "content": "reply"},
+        ]
+        result = AnthropicProvider._merge_consecutive(msgs)
+        assert [m["role"] for m in result] == ["user", "assistant", "user"]
+        assert result[0]["content"] == "(conversation continued)"
+        assert result[1]["content"] == "hi"
+        assert result[2]["content"] == "ok"
+
+    def test_leading_assistant_with_tool_use_left_alone(self):
+        """Don't prepend a synthetic opener before an assistant carrying
+        ``tool_use``; doing so would orphan the paired ``tool_result`` that
+        follows.  The caller will see the original 400 rather than a
+        harder-to-diagnose tool-pair mismatch."""
+        msgs = [
+            {
+                "role": "assistant",
+                "content": [
+                    {"type": "tool_use", "id": "t1", "name": "search", "input": {}},
+                ],
+            },
+            {
+                "role": "user",
+                "content": [
+                    {"type": "tool_result", "tool_use_id": "t1", "content": "ok"},
+                ],
+            },
+        ]
+        result = AnthropicProvider._merge_consecutive(msgs)
+        assert [m["role"] for m in result] == ["assistant", "user"]