-
Notifications
You must be signed in to change notification settings - Fork 0
Comparing changes
Open a pull request
base repository: StackOneHQ/stackone-ai-python
base: stackone-ai-v2.3.1
head repository: StackOneHQ/stackone-ai-python
compare: stackone-ai-v2.4.0
- 9 commits
- 31 files changed
- 4 contributors
Commits on Jan 31, 2026
-
feat(skills): add just-commands skill with dynamic context injection (#…
…133) Add a new skill that uses Claude Code's dynamic context injection feature to embed the output of `just --list` at runtime. This replaces the static command list in CLAUDE.md with a reference to the skill. Benefits: - Commands stay in sync with justfile automatically - Reduces manual maintenance of CLAUDE.md - Demonstrates Claude Code's !`command` syntax for dynamic context
Configuration menu - View commit details
-
Copy full SHA for bf9f3fb - Browse repository at this point
Copy the full SHA bf9f3fbView commit details -
refactor(nix): remove flakeModule in favour of direct lib usage (#135)
Replace git-hooks.flakeModule and treefmt-nix.flakeModule imports with direct usage of treefmt-nix.lib.evalModule and git-hooks.lib.${system}.run. This approach is cleaner and avoids the implicit module system overhead while maintaining the same functionality: - treefmt formatting with nixfmt, ruff, and oxfmt - pre-commit hooks for gitleaks, treefmt, and ty - formatter output for nix fmtConfiguration menu - View commit details
-
Copy full SHA for c53a85d - Browse repository at this point
Copy the full SHA c53a85dView commit details
Commits on Feb 4, 2026
-
refactor(skills): migrate skills to agent-skills-nix (#137)
* refactor(skills): migrate skills to agent-skills-nix - Remove local skills directory from git tracking - Add agent-skills-nix and StackOneHQ/skills as flake inputs - Configure devShell to auto-install skills via symlink-tree - Update .gitignore to exclude Nix-managed skill directories - Update CLAUDE.md to document the new skills management approach Skills are now sourced from StackOneHQ/skills repository and automatically installed when entering `nix develop`. * chore(skills): add .agents/skills directory for Codex compatibility Add .agents/skills as a target for agent-skills-nix alongside .claude/skills. This directory is used by Codex and other coding agents.
Configuration menu - View commit details
-
Copy full SHA for fc98e07 - Browse repository at this point
Copy the full SHA fc98e07View commit details -
refactor(nix): simplify oxfmt includes to wildcard pattern (#138)
Replace explicit file extension list with wildcard pattern for oxfmt formatter configuration. The --no-error-on-unmatched-pattern flag handles unsupported file types gracefully, making the explicit list unnecessary.
Configuration menu - View commit details
-
Copy full SHA for 32e78d3 - Browse repository at this point
Copy the full SHA 32e78d3View commit details -
style: apply oxfmt formatting to TOML files (#139)
Apply consistent TOML formatting via treefmt/oxfmt: - Use 2-space indentation for arrays - Inline short arrays where appropriate
Configuration menu - View commit details
-
Copy full SHA for 2d1b315 - Browse repository at this point
Copy the full SHA 2d1b315View commit details
Commits on Feb 5, 2026
-
refactor(skills): use defaultLocalTargets from agent-skills-nix (#141)
- Replace manual localTargets definition with agentLib.defaultLocalTargets - Override only the structure to use symlink-tree instead of copy-tree - Update agent-skills-nix to latest version (2026-02-04) - Skills now install to both .agents/skills and .claude/skills
Configuration menu - View commit details
-
Copy full SHA for cd86010 - Browse repository at this point
Copy the full SHA cd86010View commit details
Commits on Feb 8, 2026
-
chore(direnv): watch uv.lock for automatic environment reload (#143)
Add `watch_file uv.lock` to `.envrc` so that direnv triggers a re-evaluation of the environment whenever the lockfile changes. This ensures dependencies stay in sync without manual `direnv reload`.
Configuration menu - View commit details
-
Copy full SHA for 576e2fb - Browse repository at this point
Copy the full SHA 576e2fbView commit details
Commits on Mar 6, 2026
-
feat(search): Semantic Tool Search (#149)
* Senamtic Search on action in Python AI SDK * Filter tools based on the SDK auth config and connector * Use the local benchmark from the ai-generations * Add Semantinc search bench mark with local benchmarks * Fix CI lint errors * Fix the lint in the benchmark file * Formalise the docs and code * Keep semantic search minimal in the README * Remove the old benchmark data * implement PR feedback suggestions from cubic * fix nullable in the semantic tool schema * limit override * handle per connector calls to avoid the guesswork * simplify utility_tools API by inferring semantic search from client presence * Benchmark update and PR suggestions * update the README gst * Note on the fetch tools for actions that user expect to discover * Update examples and improve the semantic seach * Fix ruff issues * Document the semantic search feature in the python files and example * Respect the backend results unless top_k specified explicitly, add python only crewAI example * move the crewAI tools conversation back in the example * CI Trigger * Fix unit tests with updated top_k behavior * Update PR with correct approach mentioned in the PR comments * Update example and remove unwated crewai examples * Remove the crewai reference from the README * fix(semantic-search): scope tool_search to user's linked connectors When utility_tools(semantic_client=...) is used, tool_search now searches only the connectors available in the fetched tools collection instead of the full StackOne catalog. This prevents agents from discovering tools they cannot execute. - Add available_connectors param to create_semantic_tool_search - Pass connectors from Tools.utility_tools() to scope searches - Update docs, examples, and README to reflect scoping - Add 4 new tests for scoping behavior Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Fix the Ruff CI issue * Add back creai intefration and test integration * Remove the sematic search example from the tools * Semantic Search * Cubic suggestions * Optinally support project_ids in the SDK search * Update the client to use PR suggested client and use min_similarity from the server * CI Fix * Implement PR sugggestions and use the search and execute tools as standard way * update example docs * Update SDK as per PR suggestions * Fix available connector early return * Fix semantic search creation in fetch tools * Fix semantic search creation in fetch tools revert back to lazy * get rid of the utility tools completely as discussed * Remove the reference of the semantic search * Fix CI and lint issues * Pass semantic Client to the toolset * Add the search modes for local, semantic and auto with example * Impement PR suggetion and add the salesforce example rather than hris. Brif document the search modes * Remove unified categoried from the README and docs * Remove the unified category reference from CLAUDE.md * Refactor duplicate use Stackone API url and update tests * Fix CI issues * CI Only: skip guard fix and the timeout handling * CI Only: skip guard fix and the timeout handling * CI Only: ruff E501 * refactor search to make it aligned to the defender and future * Fix CI * CI Only: Ruff fix on toolset.py * Fix ty checks * Add topk example and add search default ---------
Configuration menu - View commit details
-
Copy full SHA for ac76d1b - Browse repository at this point
Copy the full SHA ac76d1bView commit details -
chore(main): release stackone-ai 2.4.0 (#134)
* chore(main): release stackone-ai 2.4.0 * chore: update uv.lock --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for 78ac0cb - Browse repository at this point
Copy the full SHA 78ac0cbView commit details
This comparison is taking too long to generate.
Unfortunately it looks like we can’t render this comparison for you right now. It might be too big, or there might be something weird with your repository.
You can try running this command locally to see the comparison on your machine:
git diff stackone-ai-v2.3.1...stackone-ai-v2.4.0