[Bug]: `ag_ui_langgraph` drops Anthropic extended-thinking signature on Bedrock Converse streams

[nielsdebruin]

Pre-flight Checklist

• I have searched existing issues and this hasn't been reported yet.
• I am using the latest version AG-UI.

Describe the Bug

ag_ui_langgraph drops Anthropic extended-thinking signature on Bedrock Converse streams

Summary

When ChatBedrockConverse streams Anthropic extended-thinking output, the reasoning block's cryptographic signature is silently dropped and the reasoning block is closed one chunk early. Downstream, no REASONING_ENCRYPTED_VALUE event is ever emitted, so the assistant message cannot be replayed to Bedrock on the next Converse turn.

Affected: ag_ui_langgraph/utils.py::resolve_reasoning_content and ag_ui_langgraph/agent.py::LangGraphAgent.handle_reasoning_event.

Bedrock Converse stream shape

Unlike Anthropic's native API, Bedrock splits a single thinking block across chunks and delivers the signature on its own chunk with no text field, preceded by an empty-text flush:

[{'type': 'reasoning_content', 'reasoning_content': {'text': 'The'},              'index': 0}]
[{'type': 'reasoning_content', 'reasoning_content': {'text': ' user wants ...'},  'index': 0}]
[{'type': 'reasoning_content', 'reasoning_content': {'text': ''},                 'index': 0}]   # empty-text flush
[{'type': 'reasoning_content', 'reasoning_content': {'signature': 'EpcCC...=='},  'index': 0}]   # signature-only
[]                                                                                                # reasoning block closed
[{'type': 'text', 'text': 'Streaming LLM responses is', 'index': 1}]
...

Core issues

1. resolve_reasoning_content gates on truthy text — the signature-only chunk fails if rc.get("text"): and resolves to None:

   if block_type == "reasoning_content" and isinstance(block.get("reasoning_content"), dict):
       rc = block["reasoning_content"]
       if rc.get("text"):                    # signature-only chunk falls through
           result = LangGraphReasoning(text=rc["text"], ...)
           if rc.get("signature"):
               result["signature"] = rc["signature"]
           return result

2. Empty-text chunk triggers premature close-out — the resolver also returns None for {"text": ""}. In agent.py, reasoning_data is None with an active reasoning_process fires REASONING_MESSAGE_END + REASONING_END immediately, one chunk before the signature arrives.

3. handle_reasoning_event returns before signature accumulation — even if (1) were fixed, the method's early return discards the signature:

   if not reasoning_data["text"]:            # signature-only chunk has "" text
       if reasoning_data.get("id"):
           self.active_run["pending_reasoning_id"] = reasoning_data["id"]
       return                                # <-- signature never stored
   ...
   if reasoning_data.get("signature"):
       self.active_run["reasoning_process"]["signature"] = reasoning_data["signature"]

Net effect: REASONING_ENCRYPTED_VALUE is never emitted for Bedrock Converse; on the next turn, replaying the assistant message either silently degrades multi-turn thinking or, in strict-verification modes, is rejected by Bedrock.

Reproduction

Steps to Reproduce

import os
from langchain_aws import ChatBedrockConverse

llm = ChatBedrockConverse(
    model="eu.anthropic.claude-sonnet-4-6",
    region_name=os.environ.get("AWS_REGION", "eu-central-1"),
    provider="anthropic",
    max_tokens=128000,
    additional_model_request_fields={
        "thinking": {"type": "adaptive"},
        "output_config": {"effort": "medium"},
    },
    timeout=3600,
)

for chunk in llm.stream([
    ("system", "You are a helpful assistant."),
    ("human", "Explain streaming LLM responses in 2 sentences."),
]):
    print(chunk.content)

Observed: a {'reasoning_content': {'text': ''}} chunk followed by a {'reasoning_content': {'signature': '...'}} chunk, both index: 0.

Minimal isolation of the bug against the library:

from ag_ui_langgraph.utils import resolve_reasoning_content

class C:
    def __init__(self, content): self.content = content

# Text chunk — works
print(resolve_reasoning_content(C([
    {"type": "reasoning_content", "reasoning_content": {"text": "The"}, "index": 0}
])))
# -> {'text': 'The', 'type': 'text', 'index': 0}

# Signature-only chunk — BUG: returns None, signature lost
print(resolve_reasoning_content(C([
    {"type": "reasoning_content", "reasoning_content": {"signature": "EpcCC=="}, "index": 0}
])))
# -> None   (expected: LangGraphReasoning with signature="EpcCC==")

# Empty-text chunk — BUG: returns None, triggers premature reasoning close-out
print(resolve_reasoning_content(C([
    {"type": "reasoning_content", "reasoning_content": {"text": ""}, "index": 0}
])))
# -> None   (expected: pass-through no-op, keep reasoning open)

Expected Behavior

Correctly, parse

Environment

## Environment

- `langchain-aws` (`ChatBedrockConverse`) against Bedrock Converse
- Model: `eu.anthropic.claude-sonnet-4-6` with `additional_model_request_fields={"thinking": {"type": "adaptive"}}`
- `ag_ui_langgraph` —v0.0.42
- `ag_ui_protocol` —v0.1.19

Screenshots

No response

Logs & Errors

Additional Context

No response

[jstar0]

Hi @ag-ui-protocol/copilotkit, I'd like to take this.

I reproduced the text -> empty-text flush -> signature-only Bedrock Converse sequence against current main. My proposed fix is to surface empty/signature-only reasoning_content chunks as text-less carriers, keep the active reasoning message open through the flush, and accumulate the signature before the existing text-less early return. I would add focused resolver coverage plus a full-stream regression that asserts exactly one REASONING_ENCRYPTED_VALUE before reasoning closes.

Could a maintainer assign #2174 to me if this direction looks right? I won't open a PR until the assignment/approval requirement is satisfied.