Fixed issue where AI was generating inconsistent subtask IDs (101-105, 601-603)
instead of sequential numbering (1, 2, 3...) after the generateObject migration.
Changes:
- Updated all expand-task prompt variants with forceful "CRITICAL" instructions
- Made ID requirements explicit with examples: id={{nextSubtaskId}}, id={{nextSubtaskId}}+1
- Added warning not to use parent task ID in subtask numbering
- Removed parseSubtasksFromText post-processing that was overwriting AI-generated IDs
This ensures subtasks display correctly as X.1, X.2, X.3 format and the
`tm show X.Y` command works as expected.
* feat: add support for claude code context
- code context for:
- add-task
- update-subtask
- update-task
- update
* feat: fix CI and format + refactor
* chore: format
* chore: fix broken tests
* chore: fix test
- Fixed bug where expand task generated generic authentication subtasks
- The complexity-report prompt variant now includes parent task details
- Added comprehensive unit tests to prevent regression
- Added debug logging to help diagnose similar issues
Previously, when using a complexity report with expansionPrompt, only the
expansion guidance was sent to the AI, missing the actual task context.
This caused the AI to generate unrelated generic subtasks.
Fixes the issue where all tasks would get the same generic auth-related
subtasks regardless of their actual purpose (AWS infrastructure, Docker
containerization, etc.)
Co-authored-by: Sadaqat Ali <32377500+sadaqat12@users.noreply.github.com>
* fix: improve projectRoot
* fix: improve task-master lang command
* feat: add documentation to the readme so more people can access it
* fix: expand command subtask dependency validation
* fix: update command more reliable with perplexity and other models
* chore: fix CI
* chore: implement requested changes
* chore: fix CI
