Skip to content

Commit 22d4550

Browse files
nhortonclaude
andauthored
chore: Prepare 0.4.0 release (#136)
- Consolidate changelog entries from 0.4.0-0.5.2 into single 0.4.0 release - Update pyproject.toml version to 0.4.0 - Add Unreleased section to changelog for future development - Update uv.lock https://claude.ai/code/session_016YPnt3NbKETi7iXrbCaKBC Co-authored-by: Claude <noreply@anthropic.com>
1 parent 9243604 commit 22d4550

3 files changed

Lines changed: 36 additions & 38 deletions

File tree

CHANGELOG.md

Lines changed: 34 additions & 36 deletions
Original file line numberDiff line numberDiff line change
@@ -5,46 +5,17 @@ All notable changes to DeepWork will be documented in this file.
55
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
66
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
77

8-
## [0.5.2] - 2026-01-22
8+
## [Unreleased]
99

10-
### Fixed
11-
- Fixed COMMAND rules promise handling to properly update queue status
12-
- When an agent provides a promise tag for a FAILED command rule, the queue entry is now correctly updated to SKIPPED status
13-
- Previously, FAILED queue entries remained in FAILED state even after being acknowledged via promise
14-
- This ensures the rules queue accurately reflects rule state throughout the workflow
15-
16-
## [0.5.1] - 2026-01-22
17-
18-
### Fixed
19-
- Fixed quality criteria validation logic in skill template (#111)
20-
- Changed promise condition from AND to OR: promise OR all criteria met now passes
21-
- Changed failure condition from OR to AND: requires both criteria NOT met AND promise missing to fail
22-
- This corrects the logic so the promise mechanism properly serves as a bypass for quality criteria
23-
24-
## [0.5.0] - 2026-01-20
10+
### Added
2511

2612
### Changed
27-
- **BREAKING**: Renamed `document_type` to `doc_spec` throughout the codebase
28-
- Job.yml field: `document_type``doc_spec` (e.g., `outputs: [{file: "report.md", doc_spec: ".deepwork/doc_specs/report.md"}]`)
29-
- Class: `DocumentTypeDefinition``DocSpec` (backward compat alias provided)
30-
- Methods: `has_document_type()``has_doc_spec()`, `validate_document_type_references()``validate_doc_spec_references()`
31-
- Template variables: `has_document_type``has_doc_spec`, `document_type``doc_spec`
32-
- Internal: `_load_document_type()``_load_doc_spec()`, `_doc_type_cache``_doc_spec_cache`
3313

34-
### Added
35-
- Comprehensive tests for generator doc spec integration (9 new tests)
36-
- `test_load_doc_spec_returns_parsed_spec` - Verifies doc spec loading
37-
- `test_load_doc_spec_caches_result` - Verifies caching behavior
38-
- `test_load_doc_spec_returns_none_for_missing_file` - Graceful handling of missing files
39-
- `test_generate_step_skill_with_doc_spec` - End-to-end skill generation with doc spec
40-
- `test_build_step_context_includes_doc_spec_info` - Context building verification
14+
### Fixed
4115

42-
### Migration Guide
43-
- Update job.yml files: Change `document_type:` to `doc_spec:` in output definitions
44-
- Update any code importing `DocumentTypeDefinition`: Use `DocSpec` instead (alias still works)
45-
- Run `deepwork install` to regenerate skills with updated terminology
16+
### Removed
4617

47-
## [0.4.0] - 2026-01-20
18+
## [0.4.0] - 2026-01-23
4819

4920
### Added
5021
- Doc specs (document specifications) as a first-class feature for formalizing document quality criteria
@@ -67,12 +38,39 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
6738
- New `OutputSpec` dataclass in parser for structured output handling
6839
- Comprehensive doc spec documentation in `doc/doc-specs.md`
6940
- New test fixtures for doc spec validation and parsing
41+
- Comprehensive tests for generator doc spec integration (9 new tests)
42+
- `test_load_doc_spec_returns_parsed_spec` - Verifies doc spec loading
43+
- `test_load_doc_spec_caches_result` - Verifies caching behavior
44+
- `test_load_doc_spec_returns_none_for_missing_file` - Graceful handling of missing files
45+
- `test_generate_step_skill_with_doc_spec` - End-to-end skill generation with doc spec
46+
- `test_build_step_context_includes_doc_spec_info` - Context building verification
7047

7148
### Changed
49+
- **BREAKING**: Renamed `document_type` to `doc_spec` throughout the codebase
50+
- Job.yml field: `document_type``doc_spec` (e.g., `outputs: [{file: "report.md", doc_spec: ".deepwork/doc_specs/report.md"}]`)
51+
- Class: `DocumentTypeDefinition``DocSpec` (backward compat alias provided)
52+
- Methods: `has_document_type()``has_doc_spec()`, `validate_document_type_references()``validate_doc_spec_references()`
53+
- Template variables: `has_document_type``has_doc_spec`, `document_type``doc_spec`
54+
- Internal: `_load_document_type()``_load_doc_spec()`, `_doc_type_cache``_doc_spec_cache`
7255
- `Step.outputs` changed from `list[str]` to `list[OutputSpec]` for richer output metadata
7356
- `SkillGenerator.generate_all_skills()` now accepts `project_root` parameter for doc spec loading
7457
- Updated `deepwork_jobs` to v0.6.0 with doc spec-related quality criteria
7558

59+
### Fixed
60+
- Fixed COMMAND rules promise handling to properly update queue status
61+
- When an agent provides a promise tag for a FAILED command rule, the queue entry is now correctly updated to SKIPPED status
62+
- Previously, FAILED queue entries remained in FAILED state even after being acknowledged via promise
63+
- This ensures the rules queue accurately reflects rule state throughout the workflow
64+
- Fixed quality criteria validation logic in skill template (#111)
65+
- Changed promise condition from AND to OR: promise OR all criteria met now passes
66+
- Changed failure condition from OR to AND: requires both criteria NOT met AND promise missing to fail
67+
- This corrects the logic so the promise mechanism properly serves as a bypass for quality criteria
68+
69+
### Migration Guide
70+
- Update job.yml files: Change `document_type:` to `doc_spec:` in output definitions
71+
- Update any code importing `DocumentTypeDefinition`: Use `DocSpec` instead (alias still works)
72+
- Run `deepwork install` to regenerate skills with updated terminology
73+
7674
## [0.3.1] - 2026-01-20
7775

7876
### Added
@@ -180,8 +178,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
180178

181179
Initial version.
182180

183-
[0.5.0]: https://github.com/anthropics/deepwork/releases/tag/0.5.0
184-
[0.4.0]: https://github.com/anthropics/deepwork/releases/tag/0.4.0
181+
[Unreleased]: https://github.com/anthropics/deepwork/compare/0.4.0...HEAD
182+
[0.4.0]: https://github.com/anthropics/deepwork/compare/0.3.1...0.4.0
185183
[0.3.1]: https://github.com/anthropics/deepwork/releases/tag/0.3.1
186184
[0.3.0]: https://github.com/anthropics/deepwork/releases/tag/0.3.0
187185
[0.1.1]: https://github.com/anthropics/deepwork/releases/tag/0.1.1

pyproject.toml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
[project]
22
name = "deepwork"
3-
version = "0.5.2"
3+
version = "0.4.0"
44
description = "Framework for enabling AI agents to perform complex, multi-step work tasks"
55
readme = "README.md"
66
requires-python = ">=3.11"

uv.lock

Lines changed: 1 addition & 1 deletion
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

0 commit comments

Comments
 (0)