fix(display): strip standalone tool-call XML tags from visible text

Port from openclaw/openclaw#67318. Some open models (notably Gemma
variants served via OpenRouter) emit tool calls as XML blocks inside
assistant content instead of via the structured tool_calls field:

  <function name="read_file"><parameter name="path">/tmp/x</parameter></function>
  <tool_call>{"name":"x"}</tool_call>
  <function_calls>[{...}]</function_calls>

Left unstripped, this raw XML leaked to gateway users (Discord, Telegram,
Matrix, Feishu, Signal, WhatsApp, etc.) and the CLI, since hermes-agent's
existing reasoning-tag stripper handled only <think>/<thinking>/<thought>
variants.

Extend _strip_think_blocks (run_agent.py) and _strip_reasoning_tags
(cli.py) to cover:
  * <tool_call>, <tool_calls>, <tool_result>
  * <function_call>, <function_calls>
  * <function name="..."> ... </function> (Gemma-style)

The <function> variant is boundary-gated (only strips when the tag sits
at start-of-line or after sentence punctuation AND carries a name="..."
attribute) so prose mentions like 'Use <function> declarations in JS'
are preserved. Dangling <function name="..."> with no close is
intentionally left visible — matches OpenClaw's asymmetry so a truncated
streaming tail still reaches the user.

Tests: 9 new cases in TestStripThinkBlocks (run_agent) + 9 in new file
tests/run_agent/test_strip_reasoning_tags_cli.py. Covers Qwen-style
<tool_call>, Gemma-style <function name="...">, multi-line payloads,
prose preservation, stray close tags, dangling open tags, and mixed
reasoning+tool_call content.

Note: this port covers the post-streaming final-text path, which is what
gateway adapters and CLI display consume. Extending the per-delta stream
filter in gateway/stream_consumer.py to hide these tags live as they
stream is a separate follow-up; for now users may see raw XML briefly
during a stream before the final cleaned text replaces it.

Refs: openclaw/openclaw#67318
This commit is contained in:
Teknium 2026-04-19 17:22:26 -07:00 committed by Teknium
parent 64b61cc24b
commit c345ec9a63
4 changed files with 232 additions and 0 deletions

30
cli.py
View file

@ -108,6 +108,11 @@ def _strip_reasoning_tags(text: str) -> str:
``<thought>`` (Gemma 4). Must stay in sync with
``run_agent.py::_strip_think_blocks`` and the stream consumer's
``_OPEN_THINK_TAGS`` / ``_CLOSE_THINK_TAGS`` tuples.
Also strips tool-call XML blocks some open models leak into visible
content (``<tool_call>``, ``<function_calls>``, Gemma-style
``<function name=""></function>``). Ported from
openclaw/openclaw#67318.
"""
cleaned = text
for tag in _REASONING_TAGS:
@ -132,6 +137,31 @@ def _strip_reasoning_tags(text: str) -> str:
cleaned,
flags=re.IGNORECASE,
)
# Tool-call XML blocks (openclaw/openclaw#67318).
for tc_tag in ("tool_call", "tool_calls", "tool_result",
"function_call", "function_calls"):
cleaned = re.sub(
rf"<{tc_tag}\b[^>]*>.*?</{tc_tag}>\s*",
"",
cleaned,
flags=re.DOTALL | re.IGNORECASE,
)
# <function name="..."> — boundary + attribute gated to avoid prose FPs.
cleaned = re.sub(
r'(?:(?<=^)|(?<=[\n\r.!?:]))[ \t]*'
r'<function\b[^>]*\bname\s*=[^>]*>'
r'(?:(?:(?!</function>).)*)</function>\s*',
'',
cleaned,
flags=re.DOTALL | re.IGNORECASE,
)
# Stray tool-call close tags.
cleaned = re.sub(
r'</(?:tool_call|tool_calls|tool_result|function_call|function_calls|function)>\s*',
'',
cleaned,
flags=re.IGNORECASE,
)
return cleaned.strip()