Skip to content

fix(transports+agent): GLM reasoning_effort ultra + drop empty tool_calls key (#70058, #70126) #70182

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
ms-alan wants to merge 2 commits into from
Closed

fix(transports+agent): GLM reasoning_effort ultra + drop empty tool_calls key (#70058, #70126) #70182

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
fc2d497
fix(agent): drop tool_calls key instead of empty array when all are d…
Jul 23, 2026
dbf79ce
fix(transports): extend reasoning_effort ultra normalization to GLM m…
Jul 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
2 changes: 1 addition & 1 deletion agent/agent_runtime_helpers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2872,7 +2872,7 @@ def sanitize_api_messages(messages: List[Dict[str, Any]]) -> List[Dict[str, Any]
if cid:
seen_assistant_call_ids.add(cid)
kept_tcs.append(tc)
if len(kept_tcs) != len(msg.get("tool_calls") or []):
if kept_tcs:

@teknium1 teknium1 Jul 30, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

When every call is a duplicate, kept_tcs is empty and this leaves msg unchanged, including the original duplicate IDs. Please retain the changed-list check and remove the tool_calls key when no calls survive, so the sanitizer does not trade tool_calls: [] for duplicate-ID validation failures.

msg = {**msg, "tool_calls": kept_tcs}
deduped.append(msg)
elif role == "tool":
Expand Down
2 changes: 1 addition & 1 deletion agent/transports/chat_completions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ def _reasoning_config_for_model(model: str, reasoning_config: dict | None) -> di
if not isinstance(reasoning_config, dict):
return reasoning_config
if (
"gpt-5.6" in (model or "").lower()
("gpt-5.6" in (model or "").lower() or "glm-" in (model or "").lower())

@teknium1 teknium1 Jul 30, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Please scope this to verified GLM-5.2 aliases rather than every glm- model. The existing Z.AI profile only maps native reasoning effort for GLM-5.2 (plugins/model-providers/zai/__init__.py:49-82), and the direct summary path also needs the same normalization.

and str(reasoning_config.get("effort") or "").strip().lower() == "ultra"
):
normalized = dict(reasoning_config)
Expand Down
Loading