Releases: Unsupervisedcom/deepwork
Releases · Unsupervisedcom/deepwork
0.14.0
Added
- New
PLUG-REQ-001.15: Hook Script CLI Invocationrequirement indoc/specs/deepwork/cli_plugins/PLUG-REQ-001-claude-code-plugin.md
Changed
claude_plugin_hook_deepwork_invocationreview rule now requires plugin hook scripts to invoke the CLI viauvx deepworkinstead of merely providing auvx deepworkfallback (PLUG-REQ-001.15)- Plugin hook scripts (
post_commit_reminder.sh,deepschema_write.sh,post_compact.sh) now invoke thedeepworkCLI exclusively viauvx deepwork ..., matching the MCP server launch inplugins/claude/.mcp.json - Flake
shellHookno longer runsuv tool install -e— the editable user-leveldeepworkinstall is redundant now that plugin hooks go throughuvx
Fixed
- Plugin hooks no longer fail when the end user has a stale user-level
deepworkinstall (e.g.,uv tool install deepworkpinned to an older release) that wins PATH lookup but lacks the hook module being requested. The 0.13.9 fallback still used PATH first; this release bypasses PATH entirely so hooks resolve to the sameuvxcache that the MCP server populated
Removed
0.13.9
Added
- New
claude_plugin_hook_deepwork_invocationreview rule inplugins/claude/.deepreviewthat flags plugin hook scripts which call baredeepworkwithout auvx deepworkfallback
Changed
Fixed
- Plugin hook scripts (
post_commit_reminder.sh,deepschema_write.sh,post_compact.sh) now fall back touvx deepworkwhen the baredeepworkbinary is not on PATH. End-user installs launch the MCP server viauvx deepwork serve, sodeepworkis not available as a command — previously these hooks failed with exit 127 on every Bash tool use, and Claude Code reported them as failed PostToolUse hooks (regression introduced in PR #361)
Removed
0.14.0a1
0.13.8
Added
Changed
- Renamed default reviewer agent from
reviewertodeepwork:reviewer(plugin-namespaced) in review instructions output /reviewskill now checks fordeepwork:revieweragent availability before proceeding and directs users to/reload-pluginsif missing
Fixed
Removed
0.13.7
0.13.6
Added
Changed
- Deprecated the
steps/folder pattern for job definitions — step instructions are now inlined injob.yml; moved supplemental reference files fromsteps/to job root directories - Repair workflow now instructs agents to
git rmstep instruction files after inlining - Moved
specs/todoc/specs/and consolidateddocs/intodoc/to reduce root directory clutter
Removed
coverage_report.md(stale snapshot)job_refactor.md(superseded planning notes)CLAUDE_PLUGINS_README.md(redundant with README.md)
Fixed
Removed
0.13.5
0.13.4
Added
Changed
- Post-commit review reminder hook now short-circuits when all applicable (non-catch-all) review rules for the committed files are already marked as passed, emitting "No re-review needed" instead of nagging
- Renamed all "Task tool" references to "Agent tool" across codebase to match Claude Code's current tool naming
- Review formatter now emits
description,subagent_type, andpromptfields (droppednamefield) to match Agent tool signature - Hook wrapper tool mappings updated:
Task/task→Agent/agent
Fixed
- Review instruction files now include a
## Project Rootdirective stating the absolute project root so reviewer subagents read files from the correct working tree — fixes spurious findings in git-worktree setups where the subagent's cwd differed from the worktree the commits actually lived in (REVIEW-REQ-005.1.9)
Removed
- Removed automatic DeepPlan workflow injection from startup_context.sh hook (no longer forces plan mode into DeepPlan)
- Deprecated JOBS-REQ-014.5.1 (startup hook DeepPlan trigger) and REVIEW-REQ-006.3.3a (name field in review output)
0.13.3
Added
/recordskill: "watch and learn" approach to creating DeepWork workflows — users do their work normally, then/deepwork learnturns it into a repeatable job/new_userskill: guided onboarding that introduces DeepWork, offers review rule setup for code projects, and offers to record a first workflow/deepwork learnnow routes to thenew_jobworkflow when invoked after/deepwork:record- Requirements specs PLUG-REQ-002 (record skill) and PLUG-REQ-003 (new user skill)
- Anonymous DeepSchemas for both new skills
Changed
- README install commands consolidated into a single
&&-joined command ending with/deepwork:new_user deepwork setupnow openshttps://www.deepwork.md/successin the default browser after completing configuration
Fixed
Removed
0.13.2
Added
deepwork setupCLI command that auto-configures Claude Code settings (marketplace, plugin, MCP permissions, auto-update) (#343)deepwork setupalso grants project-root-relativeRead/Write/Editpermissions for/.deepwork/**/*so the plugin can operate on.deepwork/in every project without per-prompt approval- Integration tests for quality gate review caching (JOBS-REQ-004.5.7)
- Requirements traceability coverage now at 100% (#346)
- Added section-level REQ ID annotations to 32 existing test files for traceability
- Wrote 218 new tests across 5 files for learning-agents requirements (LA-REQ-001, 003, 004, 005, 006, 010, 011)
- Added 6 anonymous DeepSchemas for judgment-based learning-agents skill requirements (LA-REQ-002, 007, 008, 009, 012)
- Added new PLUG-REQ-001.12 tests for session/agent identity injection hooks
- New
req-ids-in-commentsrequirement in the standard DeepSchema definition: requirement IDs must be placed in YAML comments, not requirement body text
Changed
- JOBS-REQ-004.5.7 strengthened to explicit MUST requirement for skipping already-passed reviews
Fixed
- DeepSchema PostToolUse hook (
deepschema_write) no longer reportsFile is not valid JSONfor YAML files whose name has no extension (e.g..deepreview). The hook now parses target files and the referenced JSON Schema as YAML, which is a superset of JSON, so both formats are accepted regardless of file extension. DW-REQ-011.7.3 updated to match. (Mirrors the fix shipped in #338 for the workflow quality gate.) review:blocks declared ontype: stringstep outputs are now actually executed. Previously they were silently dropped because the review pipeline only matched against file paths, leaving authors with misconfigured-but-silent quality gates. String output reviews now produce syntheticReviewTaskobjects with the string value carried on a newReviewTask.inline_contentfield and rendered into the instruction file as a "Content to Review" section. New requirements: JOBS-REQ-004.8, REVIEW-REQ-005.1.8, REVIEW-REQ-009.1.7. (#350)