[doc, ci] fix: fix sandbox doc and enhance CI trigger filter and doc error checking (#2267)

### What does this PR do?

- fix sandbox doc 
- enhance CI trigger filter and doc error checking
- add a rule to check PR description

### Checklist Before Starting

- [x] Search for similar PRs. Paste at least one query link here: ...
- [x] Format the PR title as `[{modules}] {type}: {description}` (This
will be checked by the CI)
- `{modules}` include `fsdp`, `megatron`, `sglang`, `vllm`, `rollout`,
`trainer`, `ci`, `training_utils`, `recipe`, `hardware`, `deployment`,
`ray`, `worker`, `single_controller`, `misc`, `perf`, `model`, `algo`,
`env`, `tool`, `ckpt`, `doc`, `data`
- If this PR involves multiple modules, separate them with `,` like
`[megatron, fsdp, doc]`
  - `{type}` is in `feat`, `fix`, `refactor`, `chore`, `test`
- If this PR breaks any API (CLI arguments, config, function signature,
etc.), add `[BREAKING]` to the beginning of the title.
  - Example: `[BREAKING][fsdp, megatron] feat: dynamic batching`


### Checklist Before Submitting

> [!IMPORTANT]
> Please check all the following items before requesting a review,
otherwise the reviewer might deprioritize this PR for review.

- [x] Read the [Contribute
Guide](https://github.com/volcengine/verl?tab=readme-ov-file#contribution-guide).
- [x] Apply [pre-commit
checks](https://github.com/volcengine/verl?tab=readme-ov-file#code-linting-and-formatting):
`pre-commit install && pre-commit run --all-files --show-diff-on-failure
--color=always`
- [x] Add / Update [the
documentation](https://github.com/volcengine/verl/tree/main/docs).
- [ ] Add unit or end-to-end test(s) to [the CI
workflow](https://github.com/volcengine/verl/tree/main/.github/workflows)
to cover all the code. If not feasible, explain why: ...
- [x] Once your PR is ready for CI, send a message in [the `ci-request`
channel](https://verl-project.slack.com/archives/C091TCESWB1) in [the
`verl` Slack
workspace](https://join.slack.com/t/verl-project/shared_invite/zt-3855yhg8g-CTkqXu~hKojPCmo7k_yXTQ).
This commit is contained in:
H
2025-06-29 17:02:03 -07:00
committed by GitHub
parent 86ef66ebe6
commit 2805ce9137
8 changed files with 191 additions and 71 deletions

View File

@ -50,3 +50,9 @@ jobs:
run: python3 tests/special_sanity/check_pr_title.py
env:
PR_TITLE: ${{ github.event.pull_request.title }}
- name: Run PR description checker
run: python3 tests/special_sanity/check_pr_description.py
env:
PR_TITLE: ${{ github.event.pull_request.title }}
GITHUB_EVENT_PATH: ${{ github.event_path }}

View File

@ -94,3 +94,7 @@ jobs:
echo "🚨 Sphinx doc build contained WARNING. Please check inline emphasis is correct. See _build/sphinx.log for details"
exit 1
fi
if grep -q "WARNING: Definition list ends without a blank line" _build/sphinx.log; then
echo "🚨 Sphinx doc build contained WARNING. Please check if the indentation is correct. See _build/sphinx.log for details"
exit 1
fi

View File

@ -42,7 +42,7 @@ on:
- main
- v0.*
paths:
- "**/*.py"
- "verl/*.py"
# Other entrypoints
- "!examples/*trainer*"
- "!tests/**"
@ -50,6 +50,8 @@ on:
- "!verl/trainer/fsdp_sft_trainer.py"
# Megatron
- "!verl/workers/**/megatron_*.py"
- "!recipe/**"
- "recipe/dapo"
pull_request:
branches:
- main

View File

@ -51,6 +51,8 @@ on:
- "!tests/**"
- "!verl/trainer/main_*.py"
- "!verl/trainer/fsdp_sft_trainer.py"
- "!recipe/**"
- "recipe/r1"
- "!recipe/r1/README.md"
pull_request:
branches:

View File

@ -39,6 +39,11 @@ on:
branches:
- main
- v0.*
paths:
- "**/*.py"
- "tests/**"
- "!recipe/**"
- "recipe/genrm_remote"
pull_request:
branches:
- main

View File

@ -3,7 +3,10 @@
## Build the docs
```bash
# Install dependencies.
# If you want to view auto-generated API docstring, please make sure verl is available in python path. For instance, install verl via:
# pip install .. -e[test]
# Install dependencies needed for building docs.
pip install -r requirements-docs.txt
# Build the docs.
@ -16,4 +19,4 @@ make html
```bash
python -m http.server -d _build/html/
```
Launch your browser and navigate to http://localhost:8000 to view the documentation.
Launch your browser and navigate to http://localhost:8000 to view the documentation. Alternatively you could drag the file `_build/html/index.html` to your local browser and view directly.

View File

@ -214,75 +214,79 @@ we provide e2e test scripts in `tests/special_e2e` folder, named `tests/special_
by setting 'trainer.rollout_data_dir' you can dump the rollout data to local disk. here is an sample taken from the rollout data:
{
"input": "
system\nYou are a math expert. You are given a question and you need to solve it step by step. Reasoning step by step before any tool call. You should use the `calc_gsm8k_reward` tool after step by step solving the question, before generate final answer at least once and refine your answer if necessary. Put your final answer in the format of `#### <answer>`.\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"code_interpreter\", \"description\": \"A tool for executing code.\", \"parameters\": {\"type\": \"object\", \"properties\": {\"code\": {\"type\": \"string\", \"description\": \"The code to execute.\", \"enum\": null}}, \"required\": [\"code\"]}, \"strict\": false}}\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n
user\nJohn gets a bonus that's the same percentage every year. Last year he made $100,000 and got a $10,000 bonus. This year he makes $200,000. How much will John make this year when adding both his total pay and bonus together? Let's think step by step and output the final answer after `####`.\n
assistant\n",
"output": "assistant\n<think>\nOkay, let's see. John gets a bonus that's the same percentage every year. Last year, he made $100,000 and got a $10,000 bonus. This year, he makes $200,000. The question is asking how much he'll make this year when adding both his total pay and bonus together.\n\nFirst, I need to figure out the percentage bonus he gets. Since the bonus is the same percentage each year, if I can find that percentage based on last year's details, I can apply it to this year's earnings to find this year's bonus. Then, I'll add that bonus to his total pay this year.\n\nLast year, he earned $100,000 and got a $10,000 bonus. To find the percentage, I can divide the bonus by his total earnings. So, 10,000 divided by 100,000. Let me calculate that.\n\n10,000 / 100,000 equals 0.1, which is 10% as a percentage. So, his bonus is 10% of his pay each year.\n\nThis year, he makes $200,000. So, the bonus this year would be 10% of 200,000. Let me compute that using the code interpreter to ensure accuracy.\n
<tool_call>\n{\"name\": \"code_interpreter\", \"arguments\": {\"code\": \"total_pay_this_year = 200000\\nbonus_percentage = 10 / 100\\nbonus_this_year = total_pay_this_year * bonus_percentage\\ntotal_income_this_year = total_pay_this_year + bonus_this_year\\nprint(total_income_this_year)\", \"executes\": \"True\"}}\n</tool_call>\n
tool\n220000.0\n\n
assistant\n<think>\nSo the code shows that John's total income this year would be $220,000. This is consistent with the 10% bonus on last year's pay of $100,000, which was $10,000. Therefore, this year's bonus of $20,000 added to his total pay of $200,000 results in a total income of $220,000.\n\nI need to verify that there are no other factors at play. The problem states it's a constant percentage bonus each year, so there's no mention of changing percentages or other variables. Therefore, applying a straightforward percentage of 10% on this year's partial salary amount would result in $20,000. Adding that to his total pay gives $220,000. The calculation is correct and aligns with the question's parameters.\n</think>\n\n#### 220000.0",
"score": 0,
"step": 1
}
.. code-block:: python
{
"input": "
system\nYou are a math expert. You are given a question and you need to solve it step by step. Reasoning step by step before any tool call. You should use the `calc_gsm8k_reward` tool after step by step solving the question, before generate final answer at least once and refine your answer if necessary. Put your final answer in the format of `#### <answer>`.\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"code_interpreter\", \"description\": \"A tool for executing code.\", \"parameters\": {\"type\": \"object\", \"properties\": {\"code\": {\"type\": \"string\", \"description\": \"The code to execute.\", \"enum\": null}}, \"required\": [\"code\"]}, \"strict\": false}}\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n
user\nJohn gets a bonus that's the same percentage every year. Last year he made $100,000 and got a $10,000 bonus. This year he makes $200,000. How much will John make this year when adding both his total pay and bonus together? Let's think step by step and output the final answer after `####`.\n
assistant\n",
"output": "assistant\n<think>\nOkay, let's see. John gets a bonus that's the same percentage every year. Last year, he made $100,000 and got a $10,000 bonus. This year, he makes $200,000. The question is asking how much he'll make this year when adding both his total pay and bonus together.\n\nFirst, I need to figure out the percentage bonus he gets. Since the bonus is the same percentage each year, if I can find that percentage based on last year's details, I can apply it to this year's earnings to find this year's bonus. Then, I'll add that bonus to his total pay this year.\n\nLast year, he earned $100,000 and got a $10,000 bonus. To find the percentage, I can divide the bonus by his total earnings. So, 10,000 divided by 100,000. Let me calculate that.\n\n10,000 / 100,000 equals 0.1, which is 10% as a percentage. So, his bonus is 10% of his pay each year.\n\nThis year, he makes $200,000. So, the bonus this year would be 10% of 200,000. Let me compute that using the code interpreter to ensure accuracy.\n
<tool_call>\n{\"name\": \"code_interpreter\", \"arguments\": {\"code\": \"total_pay_this_year = 200000\\nbonus_percentage = 10 / 100\\nbonus_this_year = total_pay_this_year * bonus_percentage\\ntotal_income_this_year = total_pay_this_year + bonus_this_year\\nprint(total_income_this_year)\", \"executes\": \"True\"}}\n</tool_call>\n
tool\n220000.0\n\n
assistant\n<think>\nSo the code shows that John's total income this year would be $220,000. This is consistent with the 10% bonus on last year's pay of $100,000, which was $10,000. Therefore, this year's bonus of $20,000 added to his total pay of $200,000 results in a total income of $220,000.\n\nI need to verify that there are no other factors at play. The problem states it's a constant percentage bonus each year, so there's no mention of changing percentages or other variables. Therefore, applying a straightforward percentage of 10% on this year's partial salary amount would result in $20,000. Adding that to his total pay gives $220,000. The calculation is correct and aligns with the question's parameters.\n</think>\n\n#### 220000.0",
"score": 0,
"step": 1
}
here is the readable format version:
[system]
.. code-block:: python
You are a math expert. You are given a question and you need to solve it step by step. Reasoning step by step before any tool call. You should use the `calc_gsm8k_reward` tool after step by step solving the question, before generate final answer at least once and refine your answer if necessary. Put your final answer in the format of `#### <answer>`.
# Tools
You may call one or more functions to assist with the user query.
You are provided with function signatures within <tools></tools> XML tags:
<tools>
{"type": "function", "function": {"name": "code_interpreter", "description": "A tool for executing code.", "parameters": {"type": "object", "properties": {"code": {"type": "string", "description": "The code to execute.", "enum": null}}, "required": ["code"]}, "strict": false}}
</tools>
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call>
[user]
John gets a bonus that's the same percentage every year. Last year he made $100,000 and got a $10,000 bonus. This year he makes $200,000. How much will John make this year when adding both his total pay and bonus together? Let's think step by step and output the final answer after `####`.
[assistant]
<think>
Okay, let's see. John gets a bonus that's the same percentage every year. Last year, he made $100,000 and got a $10,000 bonus. This year, he makes $200,000. The question is asking how much he'll make this year when adding both his total pay and bonus together.
First, I need to figure out the percentage bonus he gets. Since the bonus is the same percentage each year, if I can find that percentage based on last year's details, I can apply it to this year's earnings to find this year's bonus. Then, I'll add that bonus to his total pay this year.
Last year, he earned $100,000 and got a $10,000 bonus. To find the percentage, I can divide the bonus by his total earnings. So, 10,000 divided by 100,000. Let me calculate that.
10,000 / 100,000 equals 0.1, which is 10% as a percentage. So, his bonus is 10% of his pay each year.
This year, he makes $200,000. So, the bonus this year would be 10% of 200,000. Let me compute that using the code interpreter to ensure accuracy.
<tool_call>
{"name": "code_interpreter", "arguments": {"code": "total_pay_this_year = 200000\nbonus_percentage = 10 / 100\nbonus_this_year = total_pay_this_year * bonus_percentage\ntotal_income_this_year = total_pay_this_year + bonus_this_year\nprint(total_income_this_year)", "executes": "True"}}
</tool_call>
[tool]
220000.0
[assistant]
<think>
So the code shows that John's total income this year would be $220,000. This is consistent with the 10% bonus on last year's pay of $100,000, which was $10,000. Therefore, this year's bonus of $20,000 added to his total pay of $200,000 results in a total income of $220,000.
I need to verify that there are no other factors at play. The problem states it's a constant percentage bonus each year, so there's no mention of changing percentages or other variables. Therefore, applying a straightforward percentage of 10% on this year's partial salary amount would result in $20,000. Adding that to his total pay gives $220,000. The calculation is correct and aligns with the question's parameters.
</think>
#### 220000.0
[system]
You are a math expert. You are given a question and you need to solve it step by step. Reasoning step by step before any tool call. You should use the `calc_gsm8k_reward` tool after step by step solving the question, before generate final answer at least once and refine your answer if necessary. Put your final answer in the format of `#### <answer>`.
# Tools
You may call one or more functions to assist with the user query.
You are provided with function signatures within <tools></tools> XML tags:
<tools>
{"type": "function", "function": {"name": "code_interpreter", "description": "A tool for executing code.", "parameters": {"type": "object", "properties": {"code": {"type": "string", "description": "The code to execute.", "enum": null}}, "required": ["code"]}, "strict": false}}
</tools>
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call>
[user]
John gets a bonus that's the same percentage every year. Last year he made $100,000 and got a $10,000 bonus. This year he makes $200,000. How much will John make this year when adding both his total pay and bonus together? Let's think step by step and output the final answer after `####`.
[assistant]
<think>
Okay, let's see. John gets a bonus that's the same percentage every year. Last year, he made $100,000 and got a $10,000 bonus. This year, he makes $200,000. The question is asking how much he'll make this year when adding both his total pay and bonus together.
First, I need to figure out the percentage bonus he gets. Since the bonus is the same percentage each year, if I can find that percentage based on last year's details, I can apply it to this year's earnings to find this year's bonus. Then, I'll add that bonus to his total pay this year.
Last year, he earned $100,000 and got a $10,000 bonus. To find the percentage, I can divide the bonus by his total earnings. So, 10,000 divided by 100,000. Let me calculate that.
10,000 / 100,000 equals 0.1, which is 10% as a percentage. So, his bonus is 10% of his pay each year.
This year, he makes $200,000. So, the bonus this year would be 10% of 200,000. Let me compute that using the code interpreter to ensure accuracy.
<tool_call>
{"name": "code_interpreter", "arguments": {"code": "total_pay_this_year = 200000\nbonus_percentage = 10 / 100\nbonus_this_year = total_pay_this_year * bonus_percentage\ntotal_income_this_year = total_pay_this_year + bonus_this_year\nprint(total_income_this_year)", "executes": "True"}}
</tool_call>
[tool]
220000.0
[assistant]
<think>
So the code shows that John's total income this year would be $220,000. This is consistent with the 10% bonus on last year's pay of $100,000, which was $10,000. Therefore, this year's bonus of $20,000 added to his total pay of $200,000 results in a total income of $220,000.
I need to verify that there are no other factors at play. The problem states it's a constant percentage bonus each year, so there's no mention of changing percentages or other variables. Therefore, applying a straightforward percentage of 10% on this year's partial salary amount would result in $20,000. Adding that to his total pay gives $220,000. The calculation is correct and aligns with the question's parameters.
</think>
#### 220000.0

View File

@ -0,0 +1,94 @@
# Copyright 2025 Bytedance Ltd. and/or its affiliates
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#!/usr/bin/env python3
import json
import os
# Number of lines to check
NUM_LINES = 5
# Custom exception types for clear error handling
class TemplateFileError(Exception):
pass
class PRBodyLoadError(Exception):
pass
class PRDescriptionError(Exception):
pass
# Path to the PR template file
template_file = os.path.join(os.getenv("GITHUB_WORKSPACE", "."), ".github", "PULL_REQUEST_TEMPLATE.md")
def load_template(path):
"""
Load only the first NUM_LINES of the PR template file as a list of lines,
without stripping any characters.
"""
lines = []
try:
with open(path, encoding="utf-8") as f:
for _ in range(NUM_LINES):
line = f.readline()
if not line:
break
lines.append(line.strip())
return lines
except Exception as e:
raise TemplateFileError(f"Failed to read PR template (first {NUM_LINES} lines) at {path}: {e}") from e
def load_pr_body(event_path):
try:
with open(event_path, encoding="utf-8") as f:
payload = json.load(f)
return payload.get("pull_request", {}).get("body", "") or ""
except Exception as e:
raise PRBodyLoadError(f"Failed to read PR body from {event_path}: {e}") from e
def check_pr_description(body, template_lines):
"""
Compare the first NUM_LINES lines of the PR body to the template lines.
If they match exactly, the placeholder was not modified.
"""
pr_lines = body.splitlines(keepends=True)
pr_first = [x.strip() for x in pr_lines[:NUM_LINES]]
if pr_first == template_lines:
raise PRDescriptionError("It looks like you haven't updated the '### What does this PR do?' section. Please replace the placeholder text with a concise description of what your PR does.")
else:
print(pr_first)
print(template_lines)
def main():
event_path = os.getenv("GITHUB_EVENT_PATH")
if not event_path:
raise OSError("GITHUB_EVENT_PATH is not set.")
template_lines = load_template(template_file)
pr_body = load_pr_body(event_path)
check_pr_description(pr_body, template_lines)
print("'### What does this PR do?' section has been filled out.")
if __name__ == "__main__":
main()