Skip to content

fix(json stream): emit all objects in a chunk, not just the first #2487

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
Diwak4r wants to merge 1 commit into from
+13 −2
Closed

fix(json stream): emit all objects in a chunk, not just the first #2487

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions instructor/v2/core/json.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -117,7 +117,7 @@ def extract_json_from_stream(chunks: Iterable[str]) -> Generator[str, None, None
yield from buffer
buffer = []
json_started = False
break
continue

@chatgpt-codex-connector chatgpt-codex-connector Bot Jul 26, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Stop scanning arbitrary suffix text after JSON

When a complete JSON value and trailing prose arrive in the same provider chunk, this continue resumes scanning outside the JSON value, and any later balanced {...} or [...] prose is emitted because new roots are accepted without validation. For example, before {"a":1} See [section] for details now yields {"a":1}[section], corrupting downstream parsers; before this change the same-chunk suffix was skipped. Consider continuing only across whitespace/separators into another immediate JSON root rather than scanning arbitrary suffix text.

Useful? React with 👍 / 👎.


buffer.append(char)
continue
Expand Down Expand Up @@ -207,7 +207,7 @@ async def extract_json_from_stream_async(
yield buffered_char
buffer = []
json_started = False
break
continue

buffer.append(char)
continue
Expand Down
11 changes: 11 additions & 0 deletions tests/v2/test_json_helpers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,6 +89,17 @@ def test_extract_json_from_stream_preserves_triple_backticks_in_plain_string() -
assert "".join(extract_json_from_stream(chunks)) == '{"code":"```py```"}'


def test_extract_json_from_stream_yields_all_objects_in_one_chunk() -> None:
# A complete object must not swallow a second object sharing its chunk.
chunks = ['{"a":1}{"b":2}']
assert "".join(extract_json_from_stream(chunks)) == '{"a":1}{"b":2}'


def test_extract_json_from_stream_yields_all_objects_in_fenced_chunk() -> None:
chunks = ['```json\n{"a":1}{"b":2}\n```']
assert "".join(extract_json_from_stream(chunks)) == '{"a":1}{"b":2}'


def test_extract_json_from_stream_preserves_backticks_in_fenced_string() -> None:
chunks = ["```json\n", '{"code":"`inline`"}', "\n```"]

Expand Down