mirror of
https://github.com/pewdiepie-archdaemon/odysseus.git
synced 2026-06-15 17:25:26 -04:00
fix(skills): tolerate a stray brace before the JSON in skill extraction (#2200)
maybe_extract_skill() sliced the LLM response from the first '{' to the
last '}'. When a model emits a stray brace in prose before the real
object (e.g. "uses {placeholder} then {...}"), the slice starts at the
prose brace, json.loads fails, and a valid skill is silently dropped.
Factor parsing into _extract_json_object(), which tries the whole
(de-fenced) string first and then each '{' start position, returning the
first candidate that parses to a JSON object.
Adds tests/test_skill_extractor_json.py.
This commit is contained in:
committed by
GitHub
parent
c5ac89f01f
commit
92ef01d4fa
@@ -0,0 +1,43 @@
|
||||
"""Regression: skill-extraction JSON parsing must tolerate a stray brace in prose.
|
||||
|
||||
maybe_extract_skill() sliced the LLM response from the first '{' to the last
|
||||
'}'. When a model emits a stray brace in prose before the real object
|
||||
(e.g. "uses {placeholder} then {...}"), that slice starts at the prose brace and
|
||||
json.loads fails, so a perfectly good skill is silently dropped. Extraction now
|
||||
tries each '{' start position and returns the first candidate that parses to a
|
||||
JSON object.
|
||||
"""
|
||||
from services.memory import skill_extractor
|
||||
|
||||
|
||||
def test_stray_brace_before_real_json_is_recovered():
|
||||
resp = (
|
||||
'The user mentioned {placeholder} before the actual JSON '
|
||||
'{"title": "Restart the service", "steps": ["a", "b"]}'
|
||||
)
|
||||
data = skill_extractor._extract_json_object(resp)
|
||||
assert isinstance(data, dict)
|
||||
assert data["title"] == "Restart the service"
|
||||
|
||||
|
||||
def test_clean_json_object():
|
||||
data = skill_extractor._extract_json_object('{"title": "Y", "steps": []}')
|
||||
assert data["title"] == "Y"
|
||||
|
||||
|
||||
def test_code_fenced_json():
|
||||
data = skill_extractor._extract_json_object('```json\n{"title": "Z"}\n```')
|
||||
assert data["title"] == "Z"
|
||||
|
||||
|
||||
def test_no_json_object_returns_none():
|
||||
assert skill_extractor._extract_json_object("just prose, no object here") is None
|
||||
|
||||
|
||||
def test_non_object_json_returns_none():
|
||||
# A bare array is valid JSON but not a skill object.
|
||||
assert skill_extractor._extract_json_object("[1, 2, 3]") is None
|
||||
|
||||
|
||||
def test_empty_input_returns_none():
|
||||
assert skill_extractor._extract_json_object("") is None
|
||||
Reference in New Issue
Block a user