mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: show reasoning/thinking blocks when show_reasoning is enabled

Browse source 
- Add <thinking> tag to streaming filter's tag list
- When show_reasoning is on, route XML reasoning content to the
  reasoning display box instead of silently discarding it
- Expand _strip_think_blocks to handle all tag variants:
  <think>, <thinking>, <THINKING>, <reasoning>, <REASONING_SCRATCHPAD>
This commit is contained in:
Test 2026-03-19 19:44:31 -07:00
parent 04b6ecadc4
commit b1832faaae
2 changed files with 26 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

23
cli.py
View file

@ -1522,9 +1522,11 @@ class HermesCLI:
# Track whether we're inside a reasoning/thinking block.
# These tags are model-generated (system prompt tells the model
# to use them) and get stripped from final_response. We must
# suppress them during streaming too.
_OPEN_TAGS = ("<REASONING_SCRATCHPAD>", "<think>", "<reasoning>", "<THINKING>")
_CLOSE_TAGS = ("</REASONING_SCRATCHPAD>", "</think>", "</reasoning>", "</THINKING>")
# suppress them during streaming too — unless show_reasoning is
# enabled, in which case we route the inner content to the
# reasoning display box instead of discarding it.
_OPEN_TAGS = ("<REASONING_SCRATCHPAD>", "<think>", "<reasoning>", "<THINKING>", "<thinking>")
_CLOSE_TAGS = ("</REASONING_SCRATCHPAD>", "</think>", "</reasoning>", "</THINKING>", "</thinking>")
# Append to a pre-filter buffer first
self._stream_prefilt = getattr(self, "_stream_prefilt", "") + text
@ -1564,6 +1566,12 @@ class HermesCLI:
idx = self._stream_prefilt.find(tag)
if idx != -1:
self._in_reasoning_block = False
# When show_reasoning is on, route inner content to
# the reasoning display box instead of discarding.
if self.show_reasoning:
inner = self._stream_prefilt[:idx]
if inner:
self._stream_reasoning_delta(inner)
after = self._stream_prefilt[idx + len(tag):]
self._stream_prefilt = ""
# Process remaining text after close tag through full
@ -1571,10 +1579,15 @@ class HermesCLI:
if after:
self._stream_delta(after)
return
# Still inside reasoning block — keep only the tail that could
# be a partial close tag prefix (save memory on long blocks).
# When show_reasoning is on, stream reasoning content live
# instead of silently accumulating. Keep only the tail that
# could be a partial close tag prefix.
max_tag_len = max(len(t) for t in _CLOSE_TAGS)
if len(self._stream_prefilt) > max_tag_len:
if self.show_reasoning:
# Route the safe prefix to reasoning display
safe_reasoning = self._stream_prefilt[:-max_tag_len]
self._stream_reasoning_delta(safe_reasoning)
self._stream_prefilt = self._stream_prefilt[-max_tag_len:]
return