Add policy to enforce version updates

.deepwork.policy.yml

@@ -40,4 +40,32 @@
     3. Run `deepwork install --platform claude` to sync changes
     4. Verify the changes propagated correctly
 
-    See CLAUDE.md section "CRITICAL: Editing Standard Jobs" for details.
+    See CLAUDE.md section "CRITICAL: Editing Standard Jobs" for details.
+
+- name: "Version and Changelog Update"
+  trigger: "src/**/*"
+  safety:
+    - "pyproject.toml"
+    - "CHANGELOG.md"
+  instructions: |
+    Source code in src/ has been modified. **You MUST evaluate whether version and changelog updates are needed.**
+
+    **Evaluate the changes:**
+    1. Is this a bug fix, new feature, breaking change, or internal refactor?
+    2. Does this change affect the public API or user-facing behavior?
+    3. Would users need to know about this change when upgrading?
+
+    **If version update is needed:**
+    1. Update the `version` field in `pyproject.toml` following semantic versioning:
+       - PATCH (0.1.x): Bug fixes, minor internal changes
+       - MINOR (0.x.0): New features, non-breaking changes
+       - MAJOR (x.0.0): Breaking changes
+    2. Add an entry to `CHANGELOG.md` under an appropriate version header:
+       - Use categories: Added, Changed, Fixed, Removed, Deprecated, Security
+       - Include a clear, user-facing description of what changed
+       - Follow the Keep a Changelog format
+
+    **If NO version update is needed** (e.g., tests only, comments, internal refactoring with no behavior change):
+    - Explicitly state why no version bump is required
+
+    **This policy requires explicit action** - either update both files or justify why no update is needed.

CHANGELOG.md

@@ -5,8 +5,37 @@ All notable changes to DeepWork will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.1.1] - 2026-01-15
+
+### Added
+- `compare_to` option in policy system for flexible change detection (#34)
+  - `base` (default): Compare to merge-base with default branch
+  - `default_tip`: Two-dot diff against default branch tip
+  - `prompt`: Compare to state captured at prompt submission
+- New `learn` command replacing `refine` for conversation-driven job improvement (#27)
+  - Analyzes conversations where DeepWork jobs were run
+  - Classifies learnings as generalizable (→ instructions) or bespoke (→ AGENTS.md)
+  - Creates learning_summary.md documenting all changes
+- "Think deeply" prompt in learn step for enhanced reasoning (#33)
+- Supplementary markdown file support for job steps (#19)
+- Browser automation capability consideration in job definition (#32)
+- Platform-specific reload instructions in adapters (#31)
+- Version and changelog update policy to enforce version tracking on src changes
+- Added claude and copilot to CLA allowlist (#26)
+
+### Changed
+- Moved git diff logic into evaluate_policies.py for per-policy handling (#34)
+- Renamed `capture_work_tree.sh` to `capture_prompt_work_tree.sh` (#34)
+- Updated README with PyPI install instructions using pipx, uv, and pip (#22)
+- Updated deepwork_jobs job version to 0.2.0
+
+### Removed
+- `refine` step (replaced by `learn` command) (#27)
+- `get_changed_files.sh` hook (logic moved to Python policy evaluator) (#34)
+
 ## [0.1.0] - Initial Release
 
 Initial version.
 
+[0.1.1]: https://github.com/anthropics/deepwork/releases/tag/v0.1.1
 [0.1.0]: https://github.com/anthropics/deepwork/releases/tag/v0.1.0

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "deepwork"
-version = "0.1.0"
+version = "0.1.1"
 description = "Framework for enabling AI agents to perform complex, multi-step work tasks"
 readme = "README.md"
 requires-python = ">=3.11"