Skip to content

[Fix][Generator] Correct chat history length for retoknenize codepath with env.init #214

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

Merged
CharlieFRuan merged 2 commits into from
Aug 28, 2025
Merged

[Fix][Generator] Correct chat history length for retoknenize codepath with env.init #214

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bae52bd
[Fix][Generator] Correct chat history length for retoknenize codepath…
CharlieFRuan Aug 28, 2025
5b25b0d
fix lint
CharlieFRuan Aug 28, 2025
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
3 changes: 2 additions & 1 deletion skyrl-train/skyrl_train/generators/skyrl_gym_generator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -145,6 +145,7 @@ async def agent_loop(

# init() returns the first prompt to be given to the model, and optional metadata dict
chat_history, _ = env.init(chat_history)
initial_chat_history_length = len(chat_history)
chat_end_index = len(chat_history)
input_ids = self.tokenizer.apply_chat_template(
chat_history,
Expand Down Expand Up @@ -221,7 +222,7 @@ async def agent_loop(
prompt_ids = input_ids[:initial_prompt_length]
if retokenize_chat_history:
response_encodings = self.tokenizer.apply_chat_template(
chat_history[len(prompt) :],
chat_history[initial_chat_history_length:],
chat_template=self.custom_chat_template,
add_generation_prompt=False,
return_dict=True,
Expand Down