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
..
providers	fix(api): sanitize orphaned tool messages at request-building layer	2026-04-10 01:35:00 +09:00
client.rs	fix(api): route DashScope models to dashscope config, not openai	2026-04-08 18:04:37 +09:00
error.rs	fix(api): auth-provider error copy — prefix-routing hints + sk-ant-* bearer detection — closes ROADMAP #28	2026-04-08 16:29:03 +09:00
http_client.rs	feat: b6-openai-models — batch 6	2026-04-07 15:52:30 +09:00
lib.rs	feat: b6-pdf-extract-v2 follow-up work — batch 6	2026-04-07 16:11:51 +09:00
prompt_cache.rs	feat(api): add tuning params (temperature, top_p, penalties, stop) to MessageRequest	2026-04-08 07:07:33 +09:00
sse.rs	fix(api): enrich JSON parse errors with response body, provider, and model	2026-04-07 14:22:05 +09:00
types.rs	feat(api): add reasoning_effort field to MessageRequest and OpenAI-compat path	2026-04-09 04:02:59 +09:00