mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-06-22 10:32:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 10

docs: clean up three stale comments from the #32848 audit

Browse source 
- tools/memory_tool.py:20 — 'read' action was intentionally removed
  but the docstring still listed it. Now matches the schema.
- tools/fuzzy_match.py:9 — unicode_normalized was added but the
  chain-count docstring still said '8-strategy'. Now says '9'.
- run_agent.py:1485 — 'See #<TBD>.' placeholder was never filled in.
  Replaced with a backfill note.

Fixes #32848 (parts 3, 4, and 12)
This commit is contained in:
KeyArgo 2026-06-13 07:55:51 -06:00
parent ba44de06da
commit 6fd661d64b
3 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
run_agent.py
View file

@ -1482,7 +1482,7 @@ class AIAgent:
a raw ``tool`` message and the next user turn lands as a raw ``tool`` message and the next user turn lands as
``...tool, user, user`` — a protocol-invalid sequence that most ``...tool, user, user`` — a protocol-invalid sequence that most
providers silently reject (returns empty content), causing the providers silently reject (returns empty content), causing the
empty-retry loop to fire forever. See #<TBD>. empty-retry loop to fire forever. (issue number to be backfilled once filed)
""" """
# Pass 1: strip the flagged scaffolding messages themselves. # Pass 1: strip the flagged scaffolding messages themselves.
dropped_scaffolding = False dropped_scaffolding = False

2
tools/fuzzy_match.py
View file

@ -6,7 +6,7 @@ Implements a multi-strategy matching chain to robustly find and replace text,
accommodating variations in whitespace, indentation, and escaping common accommodating variations in whitespace, indentation, and escaping common
in LLM-generated code. in LLM-generated code.
The 8-strategy chain (inspired by OpenCode), tried in order: The 9-strategy chain (inspired by OpenCode), tried in order:
1. Exact match - Direct string comparison 1. Exact match - Direct string comparison
2. Line-trimmed - Strip leading/trailing whitespace per line 2. Line-trimmed - Strip leading/trailing whitespace per line
3. Whitespace normalized - Collapse multiple spaces/tabs to single space 3. Whitespace normalized - Collapse multiple spaces/tabs to single space

2
tools/memory_tool.py
View file

@ -17,7 +17,7 @@ Entry delimiter: § (section sign). Entries can be multiline.
Character limits (not tokens) because char counts are model-independent. Character limits (not tokens) because char counts are model-independent.
Design: Design:
- Single `memory` tool with action parameter: add, replace, remove, read - Single `memory` tool with action parameter: add, replace, remove
- replace/remove use short unique substring matching (not full text or IDs) - replace/remove use short unique substring matching (not full text or IDs)
- Behavioral guidance lives in the tool schema description - Behavioral guidance lives in the tool schema description
- Frozen snapshot pattern: system prompt is stable, tool responses show live state - Frozen snapshot pattern: system prompt is stable, tool responses show live state