YeonGyu-Kim a3d0c9e5e7 fix(api): sanitize orphaned tool messages at request-building layer ...

Adds sanitize_tool_message_pairing() called from build_chat_completion_request()
after translate_message() runs. Drops any role:"tool" message whose
immediately-preceding non-tool message is role:"assistant" but has no
tool_calls entry matching the tool_call_id.

This is the second layer of the tool-pairing invariant defense:
- 6e301c8: compaction boundary fix (producer layer)
- this commit: request-builder sanitizer (sender layer)

Together these close the 400-error loop for resumed/compacted multi-turn
tool sessions on OpenAI-compatible backends.

Sanitization only fires when preceding message is role:assistant (not
user/system) to avoid dropping valid translation artifacts from mixed
user-message content blocks.

Regression tests: sanitize_drops_orphaned_tool_messages covers valid pair,
orphaned tool (no tool_calls in preceding assistant), mismatched id, and
two tool results both referencing the same assistant turn.

116 api + 159 CLI + 431 runtime tests pass. Fmt clean.

2026-04-10 01:35:00 +09:00

..

src

fix(api): sanitize orphaned tool messages at request-building layer

2026-04-10 01:35:00 +09:00

tests

…

Cargo.toml

…