Stale reasoning reuse and extraction fixes

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

• #20174 fix: scope reasoning-box extraction to the current turn (salvage #17055)

  merged to main

  files: run_agent.py, scripts/release.py, tests/cli/test_reasoning_command.py, tests/run_agent/test_last_reasoning_per_turn.py

  Show the diff

  • run_agent.py

    @@ -13952,9 +13952,19 @@ def _stop_spinner():
                 except Exception as exc:
                     logger.warning("post_llm_call hook failed: %s", exc)
     
    -        # Extract reasoning from the last assistant message (if any)
    +        # Extract reasoning from the CURRENT turn only.  Walk backwards
    +        # but stop at the user message that started this turn — anything
    +        # earlier is from a prior turn and must not leak into the reasoning
    +        # box (confusing stale display; #17055).  Within the current turn
    +        # we still want the *most recent* non-empty reasoning: many
    +        # providers (Claude thinking, DeepSeek v4, Codex Responses) emit
    +        # reasoning on the tool-call step and leave the final-answer step
    +        # with reasoning=None, so picking only the last assistant would
    +        # silently drop legitimate same-turn reasoning.
             last_reasoning = None
             for msg in reversed(messages):
    +            if msg.get("role") == "user":
    +                break  # turn boundary — don't cross into prior turns
                 if msg.get("role") == "assistant" and msg.get("reasoning"):
                     last_reasoning = msg["reasoning"]
                     break

  • scripts/release.py

    @@ -59,6 +59,7 @@
         "[redacted:email]": "TheEpTic",
         "[email protected]": "wmagev",
         "[redacted:email]": "ashermorse",
    +    "[email protected]": "happy5318",
         "[redacted:email]": "EmelyanenkoK",
         # Matrix parity salvage batch (April 2026)
         "sr@samirusani": "samrusani",

  • tests/cli/test_reasoning_command.py

    @@ -178,6 +178,8 @@ def test_reasoning_present(self):
             messages = self._build_messages(reasoning="Let me think...")
             last_reasoning = None
             for msg in reversed(messages):
    +            if msg.get("role") == "user":
    +                break
                 if msg.get("role") == "assistant" and msg.get("reasoning"):
                     last_reasoning = msg["reasoning"]
                     break
    @@ -187,6 +189,8 @@ def test_reasoning_none(self):
             messages = self._build_messages(reasoning=None)
             last_reasoning = None
             for msg in reversed(messages):
    +            if msg.get("role") == "user":
    +                break
                 if msg.get("role") == "assistant" and msg.get("reasoning"):
                     last_reasoning = msg["reasoning"]
                     break
    @@ -201,6 +205,8 @@ def test_picks_last_assistant(self):
             ]
             last_reasoning = None
             for msg in reversed(messages):
    +            if msg.get("role") == "user":
    +                break
                 if msg.get("role") == "assistant" and msg.get("reasoning"):
                     last_reasoning = msg["reasoning"]
                     break
    @@ -210,6 +216,8 @@ def test_empty_reasoning_treated_as_none(self):
             messages = self._build_messages(reasoning="")
             last_reasoning = None
             for msg in reversed(messages):
    +            if msg.get("role") == "user":
    +                break
                 if msg.get("role") == "assistant" and msg.get("reasoning"):
                     last_reasoning = msg["reasoning"]
                     break
    @@ -584,6 +592,8 @@ def test_openrouter_claude_pipeline(self):
     
             last_reasoning = None
             for msg in reversed(messages):
    +            if msg.get("role") == "user":
    +                break
                 if msg.get("role") == "assistant" and msg.get("reasoning"):
                     last_reasoning = msg["reasoning"]
                     break

  • tests/run_agent/test_last_reasoning_per_turn.py

    @@ -0,0 +1,107 @@
    +"""Tests for per-turn reasoning extraction in AIAgent.run_conversation.
    +
    +Verifies the reasoning field returned to display layers (CLI reasoning box,
    +gateway reasoning footer, TUI reasoning event) only reflects the CURRENT
    +turn's reasoning — never leaks from a prior turn — and is picked up
    +correctly when reasoning is attached to a tool-calling assistant step
    +rather than the final-answer assistant step.
    +"""
    +from __future__ import annotations
    +
    +
    +def _extract_last_reasoning(messages):
    +    """Replica of the extraction loop in run_agent.py (~line 13867).
    +
    +    Tests pin the loop's behaviour so that refactors can't silently
    +    regress the per-turn semantic.
    +    """
    +    last_reasoning = None
    +    for msg in reversed(messages):
    +        if msg.get("role") == "user":
    +            break
    +        if msg.get("role") == "assistant" and msg.get("reasoning"):
    +            last_reasoning = msg["reasoning"]
    +            break
    +    return last_reasoning
    +
    +
    +def test_simple_turn_reasoning_present():
    +    messages = [
    +        {"role": "user", "content": "hello"},
    +        {"role": "assistant", "content": "hi", "reasoning": "greeting the user"},
    +    ]
    +    assert _extract_last_reasoning(messages) == "greeting the user"
    +
    +
    +def test_simple_turn_no_reasoning():
    +    messages = [
    +        {"role": "user", "content": "hello"},
    +        {"role": "assistant", "content": "hi", "reasoning": None},
    +    ]
    +    assert _extract_last_reasoning(messages) is None
    +
    +
    +def test_tool_call_turn_reasoning_on_tool_call_step():
    +    """When the model reasons on the tool-call step and the final-answer
    +    step has no reasoning (Claude thinking / DeepSeek v4 / Codex Responses
    +    pattern), the box must show the tool-call-step reasoning, not empty.
    +    """
    +    messages = [
    +        {"role": "user", "content": "search the repo for X"},
    +        {
    +            "role": "assistant",
    +            "content": "",
    +            "reasoning": "I should use search_files",
    +            "tool_calls": [{"id": "c1", "type": "function",
    +                            "function": {"name": "search_files", "arguments": "{}"}}],
    +        },
    +        {"role": "tool", "tool_call_id": "c1", "content": "3 matches"},
    +        {"role": "assistant", "content": "Found 3 matches", "reasoning": None},
    +    ]
    +    assert _extract_last_reasoning(messages) == "I should use search_files"
    +
    +
    +def test_no_stale_reasoning_across_turns():
    +    """The regression the whole change exists for.  Prior turn had
    +    reasoning; current turn has none.  The reasoning box must NOT show
    +    the prior turn's text.
    +    """
    +    messages = [
    +        # prior turn
    +        {"role": "user", "content": "explain quantum tunneling"},
    +        {"role": "assistant", "content": "It's when...",
    +         "reasoning": "tunneling happens when particles..."},
    +        # current turn
    +        {"role": "user", "content": "thanks"},
    +        {"role": "assistant", "content": "You're welcome!", "reasoning": None},
    +    ]
    +    assert _extract_last_reasoning(messages) is None
    +
    +
    +def test_tool_call_turn_picks_latest_reasoning_within_turn():
    +    """If BOTH the tool-call step and the final step have reasoning
    +    (uncommon but possible), the final-step reasoning wins — it's the
    +    most recent thought within the current turn.
    +    """
    +    messages = [
    +        {"role": "user", "content": "search and summarize"},
    +        {
    +            "role": "assistant",
    +            "content": "",
    +            "reasoning": "initial plan",
    +            "tool_calls": [{"id": "c1", "type": "function",
    +                            "function": {"name": "search_files", "arguments": "{}"}}],
    +        },
    +        {"role": "tool", "tool_call_id": "c1", "content": "results"},
    +        {"role": "assistant", "content": "Here's the summary",
    +         "reasoning": "synthesized view of results"},
    +    ]
    +    assert _extract_last_reasoning(messages) == "synthesized view of results"
    +
    +
    +def test_empty_string_reasoning_treated_as_missing():
    +    messages = [
    +        {"role": "user", "content": "hi"},
    +        {"role": "assistant", "content": "hello", "reasoning": ""},
    +    ]
    +    assert _extract_last_reasoning(messages) is None