Skip to content

fix: disable streaming by default in sync chat methods (fixes #1733) #1734

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

Open
praisonai-triage-agent wants to merge 6 commits into
base: main
Choose a base branch
from
Open

fix: disable streaming by default in sync chat methods (fixes #1733) #1734

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
9f2cb5b
fix: disable streaming by default in sync chat methods (fixes #1733)
praisonai-triage-agent[bot] May 23, 2026
fb6ab2d
test: replace ad-hoc script with unit test for sync stream defaults
Copilot May 23, 2026
b43245a
test: clarify helper naming in sync stream default tests
Copilot May 23, 2026
e7969a4
test: harden sync stream default AST checks
Copilot May 23, 2026
c1f452e
test: align stream default test names with target methods
Copilot May 23, 2026
54aee19
docs: clarify async/sync stream default asymmetry
praisonai-triage-agent[bot] May 23, 2026
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 src/praisonai-agents/praisonaiagents/agent/chat_mixin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -507,7 +507,7 @@ def _process_stream_response(self, messages, temperature, start_time, formatted_
emit_events=True
)

def _chat_completion(self, messages, temperature=1.0, tools=None, stream=True, reasoning_steps=False, task_name=None, task_description=None, task_id=None, response_format=None, _retry_depth=0):
def _chat_completion(self, messages, temperature=1.0, tools=None, stream=False, reasoning_steps=False, task_name=None, task_description=None, task_id=None, response_format=None, _retry_depth=0):
start_time = time.time()

# --- Context compaction (opt-in via ExecutionConfig.context_compaction) ---
Expand Down Expand Up @@ -774,7 +774,7 @@ def _execute_unified_chat_completion(
messages,
temperature=1.0,
tools=None,
stream=True,
stream=False,
reasoning_steps=False,
task_name=None,
task_description=None,
Expand Down
51 changes: 51 additions & 0 deletions test_multiagent_fix.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,51 @@
#!/usr/bin/env python3
"""Test script to reproduce and verify fix for multi-agent streaming issue #1733"""

import sys
import os

# Add the praisonaiagents package to the path
sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'src', 'praisonai-agents'))

print("Testing multi-agent functionality with the fix...")

try:
from praisonaiagents import Agent, Agents

research_agent = Agent(instructions="Research about AI")
summarise_agent = Agent(instructions="Summarise research agent's findings")
agents = Agents(agents=[research_agent, summarise_agent])

print("✓ Successfully created agents")

# Test that our fix worked: the sync methods should not use streaming by default
# Check the method signatures in chat_mixin.py
import inspect
from praisonaiagents.agent.chat_mixin import ChatMixin

# Check _chat_completion method
chat_completion_sig = inspect.signature(ChatMixin._chat_completion)
stream_param = chat_completion_sig.parameters.get('stream')
if stream_param and stream_param.default == False:
print("✓ _chat_completion method has stream=False as default")
else:
print(f"✗ _chat_completion method stream default is: {stream_param.default}")

# Check _execute_unified_chat_completion method
unified_chat_sig = inspect.signature(ChatMixin._execute_unified_chat_completion)
unified_stream_param = unified_chat_sig.parameters.get('stream')
if unified_stream_param and unified_stream_param.default == False:
print("✓ _execute_unified_chat_completion method has stream=False as default")
else:
print(f"✗ _execute_unified_chat_completion method stream default is: {unified_stream_param.default}")

print("✓ Fix validation completed - sync methods now default to stream=False")
print("✓ This should resolve the 'Streaming is not supported in sync OpenAIAdapter' error")
Copy link
Copy Markdown
Contributor

@coderabbitai coderabbitai Bot May 23, 2026

Choose a reason for hiding this comment

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

⚠️ Potential issue | 🟠 Major | ⚡ Quick win

Validation script does not fail on regression.

This script prints failure markers but still exits successfully, so it can report “All tests passed!” even when defaults are wrong.

Suggested fix 
@@
-    if stream_param and stream_param.default == False:
+    failures = []
+
+    if stream_param is not None and stream_param.default is False:
         print("✓ _chat_completion method has stream=False as default")
     else:
-        print(f"✗ _chat_completion method stream default is: {stream_param.default}")
+        actual = getattr(stream_param, "default", "<missing parameter>")
+        failures.append(f"_chat_completion stream default is {actual!r} (expected False)")
@@
-    if unified_stream_param and unified_stream_param.default == False:
+    if unified_stream_param is not None and unified_stream_param.default is False:
         print("✓ _execute_unified_chat_completion method has stream=False as default")
     else:
-        print(f"✗ _execute_unified_chat_completion method stream default is: {unified_stream_param.default}")
+        actual = getattr(unified_stream_param, "default", "<missing parameter>")
+        failures.append(
+            f"_execute_unified_chat_completion stream default is {actual!r} (expected False)"
+        )
+
+    if failures:
+        for failure in failures:
+            print(f"✗ {failure}")
+        sys.exit(1)
@@
-print("✓ All tests passed!")
+print("✓ All tests passed!")

Also applies to: 51-51

🧰 Tools
🪛 Ruff (0.15.13)

[error] 29-29: Avoid equality comparisons to False; use not stream_param.default: for false checks

Replace with not stream_param.default

(E712)

[error] 37-37: Avoid equality comparisons to False; use not unified_stream_param.default: for false checks

Replace with not unified_stream_param.default

(E712)

🤖 Prompt for AI Agents 
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@test_multiagent_fix.py` around lines 29 - 43, The validation script currently
prints pass/fail messages but always exits zero; update the checks for
_chat_completion and ChatMixin._execute_unified_chat_completion so that when
either stream default is not False the script records failure and exits with a
non-zero status (e.g., call sys.exit(1) or set a failure flag and exit after
checks). Locate the inspection logic around symbols _chat_completion and
ChatMixin._execute_unified_chat_completion in test_multiagent_fix.py (also the
similar check around line 51) and ensure any failure path triggers a non-zero
exit so CI will fail on regressions.


except Exception as e:
print(f"✗ Error occurred during validation: {e}")
import traceback
traceback.print_exc()
sys.exit(1)

print("✓ All tests passed!")
Comment thread
greptile-apps[bot] marked this conversation as resolved.
Outdated
Loading