Bug: Cross-provider reasoning promotion leaks stale content to DeepSeek/Kimi thinking mode

Background

DeepSeek V4 and Kimi/Moonshot thinking modes require reasoning_content="" on every assistant tool-call message. If the field is missing on replay, the API returns HTTP 400:

The reasoning_content in the thinking mode must be passed back to the API.

When a session switches providers mid-conversation (e.g. MiniMax → DeepSeek), the internal reasoning field from the prior provider can leak into the reasoning_content field sent to the new provider, causing HTTP 400.

Root Cause

In _copy_reasoning_content_for_api (run_agent.py), the normalized_reasoning promotion path returns before the DeepSeek/Kimi empty-string guard can execute:

# Current (buggy) ordering in origin/main:
explicit_reasoning = source_msg.get("reasoning_content")
if isinstance(explicit_reasoning, str):        # False when switching from MiniMax
    api_msg["reasoning_content"] = explicit_reasoning
    return

normalized_reasoning = source_msg.get("reasoning")  # "MiniMax chain of thought..."
if isinstance(normalized_reasoning, str) and normalized_reasoning:
    api_msg["reasoning_content"] = normalized_reasoning  # ← LEAKED
    return                                            # ← DeepSeek/Kimi guard never reached

# This guard is unreachable for cross-provider histories
if source_msg.get("tool_calls") and (self._needs_kimi...() or self._needs_deepseek...()):
    api_msg["reasoning_content"] = ""

When the session history contains a tool-call message from MiniMax with reasoning="MiniMax thinking..." and no reasoning_content, switching to DeepSeek causes:

1. reasoning_content key absent → first check returns False
2. reasoning key present → promoted to reasoning_content
3. DeepSeek receives MiniMax's reasoning → HTTP 400

Fix

Reorder the logic so that:

1. reasoning_content already set → preserve verbatim (including DeepSeek's own "" placeholder written at creation time)
2. Tool-call turns with neither reasoning_content nor reasoning → inject "" for DeepSeek/Kimi (poisoned history from prior provider)
3. reasoning present → promote to reasoning_content (healthy same-provider path)

The key addition is not has_reasoning in the guard, which distinguishes "this provider has reasoning to promote" from "a prior provider left reasoning that should not be forwarded".

Affected Scenarios

Related Issues

• [Bug]: DeepSeek V4 Flash Discord session poisoned when tool-call assistant lacks reasoning_content #15250 — DeepSeek V4 Flash Discord session poisoned when tool-call assistant lacks reasoning_content
• [Bug]: HTTP 400 "reasoning_content must be passed back" with deepseek-v4-pro in cron/auxiliary path (thinking mode works in main loop, breaks elsewhere) #15213 — HTTP 400 in cron/auxiliary path (same root cause, different trigger)
• PR fix: support DeepSeek v4-flash/v4-pro thinking mode toggle and fix reasoning_content 400 error #15228 — earlier fix that introduced this ordering issue
• PR fix: extract DeepSeek reasoning_content from model_extra #14973 — extract DeepSeek reasoning_content from model_extra

Test Coverage

All 21 existing tests in tests/run_agent/test_deepseek_reasoning_content_echo.py pass with this fix.