DanielWalnut d27a7a5f54 fix(middleware): fix DanglingToolCallMiddleware inserting patches at wrong position (#904) ...

Previously used before_model which returned {"messages": patches}, causing
LangGraph's add_messages reducer to append patches at the end of the message
list. This resulted in invalid ordering (ToolMessage after a HumanMessage)
that LLMs reject with tool call ID mismatch errors.

Switch to wrap_model_call/awrap_model_call to insert synthetic ToolMessages
immediately after each dangling AIMessage before the request reaches the LLM,
without persisting the patches to state.

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-02-25 22:29:33 +08:00

..

lead_agent

Enforces config env var checks and improves startup handling (#892)

2026-02-25 16:12:59 +08:00

memory

Refactor base paths with centralized path management (#901)

2026-02-25 21:30:33 +08:00

middlewares

fix(middleware): fix DanglingToolCallMiddleware inserting patches at wrong position (#904)

2026-02-25 22:29:33 +08:00

__init__.py

feat: support function factory (#4)

2026-01-15 22:05:54 +08:00

thread_state.py

feat: add view_image tool and optimize web fetch tools

2026-01-29 13:44:39 +08:00