fix(tutorbot): correct question_type → question_types in deep-question SKILL.md#538
Closed
wedone wants to merge 3 commits into
Closed
fix(tutorbot): correct question_type → question_types in deep-question SKILL.md#538wedone wants to merge 3 commits into
wedone wants to merge 3 commits into
Conversation
…n SKILL.md
The deep-question SKILL.md documented the config parameter as
'question_type' (singular), but the capability implementation
in deeptutor/capabilities/deep_question.py reads
'question_types' (plural) via overrides.get('question_types').
This mismatch causes TutorBot's LLM to generate CLI commands
with --config question_type=<type>, which the capability
silently ignores, resulting in unexpected behavior.
…nd deep-solve SKILL.md deep-research SKILL.md documented a 'sources' config field, but DeepResearchRequestConfig (extra='forbid') only accepts 'mode' and 'depth'. Passing 'sources' causes a validation error. Sources are actually controlled via -t tool flags and --kb, not --config-json. deep-solve SKILL.md documented 'detailed_answer=false', but DeepSolveRequestConfig is an empty model with extra='forbid'. Passing any config key causes a validation error. Both fixes align SKILL.md documentation with the actual request contracts defined in deeptutor/capabilities/request_contracts.py.
--config key=value only passes scalar values, but question_types
requires a list. Using --config question_types=multiple_choice
passes a string which fails Pydantic validation. Must use
--config-json '{"question_types":["multiple_choice"]}' instead.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
The
deep-questionSKILL.md documented the config parameter asquestion_type(singular), but the capability implementation indeeptutor/capabilities/deep_question.pyreadsquestion_types(plural) viaoverrides.get("question_types").This mismatch causes TutorBot's LLM to generate CLI commands with
--config question_type=<type>, which the capability silently ignores, resulting in the parameter having no effect. Users see errors like "question_type 参数不被当前版本支持" and the LLM must self-correct by retrying without the parameter.Fix: Align SKILL.md parameter name with the actual code —
question_type→question_types.Related Issues
N/A (no existing issue found)
Module(s) Affected
agentsapiconfigcoreknowledgeloggingservicestoolsutilsweb(Frontend)docs(Documentation)scriptsteststutorbot/skillsChecklist
pre-commit run --all-filesand fixed any issues.Additional Notes
Root cause analysis:
The
--config key=valueCLI flag maps directly toconfig_overrides[key], soquestion_typeandquestion_typesare different keys. The SKILL.md was documenting the wrong key name.