Merge branch 'master' into fix/loopback-mcp-client-timeout

Author: swissmo

.claude/skills/bat-story-eval/SKILL.md

@@ -33,7 +33,7 @@ If `$ARGUMENTS` is `--help` or missing `--baseline`, show usage and stop:
 ### 0a. Compute Diff
 
 ```bash
-cd /home/julien/github/ha-mcp/worktree/uat-stories
+cd "$(dirname "$(git rev-parse --path-format=absolute --git-common-dir)")/worktree/uat-stories"
 git diff <baseline>..HEAD -- src/ha_mcp/ --stat
 git diff <baseline>..HEAD -- src/ha_mcp/ --name-only
 ```
@@ -112,7 +112,7 @@ For EACH agent, run all stories against the **baseline** version. One container
 ### 1a. Start container with first story
 
 ```bash
-cd /home/julien/github/ha-mcp/worktree/uat-stories
+cd "$(dirname "$(git rev-parse --path-format=absolute --git-common-dir)")/worktree/uat-stories"
 uv run python tests/uat/stories/run_story.py \
   catalog/<first_story>.yaml \
   --agents <agent> --keep-container \
@@ -370,4 +370,4 @@ Flag >5% total size increase (directly impacts token cost per turn).
 - Reuse containers: first story starts it (`--keep-container`), rest use `--ha-url`
 - Custom story YAMLs go to `/tmp/` (ephemeral); full details reported in Step 6
 - See "Metrics" section in Step 4 for primary vs secondary metric classification
-- The working directory MUST be `/home/julien/github/ha-mcp/worktree/uat-stories` for `uv run`
+- The working directory MUST be the `worktree/uat-stories` worktree root (where `pyproject.toml` lives) for `uv run`

.claude/skills/bat-story-eval/references/evaluation-protocol.md

@@ -32,7 +32,7 @@ uv run python tests/uat/stories/scripts/ha_query.py \
 Check the exit code first. `ha_query.py` exits non-zero when the agent CLI
 itself failed, and prints `[exit N]` (plus stderr, when there is any) after
 whatever text the CLI managed to produce — `[exit 124]` for a query that hung
-past its timeout. The one non-zero exit without a marker is `Error: <agent>
+past its timeout. The one non-zero exit without a marker is `Error: {agent}
 CLI not found`, which means the agent is not installed: fix the environment
 rather than re-running. A failed query is **not a measurement**: do not score
 it as any of the three outcomes below — re-run it, and if it keeps failing,

.github/workflows/_build-and-release.yml

@@ -51,7 +51,7 @@ jobs:
           python-version: '3.13'
 
       - name: Install uv
-        uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
+        uses: astral-sh/setup-uv@20cfd1bf945f4377ade1205e4dbc17946fc9a30d # v10.0.1
         with:
           version: "latest"
 

.github/workflows/addon-publish-dev.yml

@@ -107,7 +107,7 @@ jobs:
         submodules: true
 
     - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4
+      uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e # v4
 
     - name: Log in to GitHub Container Registry
       uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4

.github/workflows/addon-publish.yml

@@ -50,7 +50,7 @@ jobs:
         ref: ${{ inputs.version && format('v{0}', inputs.version) || github.sha }}
 
     - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4
+      uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e # v4
 
     - name: Log in to GitHub Container Registry
       uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4

.github/workflows/build-binary.yml

@@ -63,7 +63,7 @@ jobs:
           python-version: '3.13'
 
       - name: Install uv
-        uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
+        uses: astral-sh/setup-uv@20cfd1bf945f4377ade1205e4dbc17946fc9a30d # v10.0.1
         with:
           version: "latest"
 

.github/workflows/e2e-tests.yml

@@ -43,12 +43,12 @@ jobs:
         submodules: true
 
     - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4
+      uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e # v4
       with:
         cache-binary: true
 
     - name: Install uv
-      uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
+      uses: astral-sh/setup-uv@20cfd1bf945f4377ade1205e4dbc17946fc9a30d # v10.0.1
       with:
         version: "latest"
 
@@ -134,12 +134,12 @@ jobs:
         submodules: true
 
     - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4
+      uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e # v4
       with:
         cache-binary: true
 
     - name: Install uv
-      uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
+      uses: astral-sh/setup-uv@20cfd1bf945f4377ade1205e4dbc17946fc9a30d # v10.0.1
       with:
         version: "latest"
 
@@ -231,12 +231,12 @@ jobs:
         fi
 
     - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4
+      uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e # v4
       with:
         cache-binary: true
 
     - name: Install uv
-      uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
+      uses: astral-sh/setup-uv@20cfd1bf945f4377ade1205e4dbc17946fc9a30d # v10.0.1
       with:
         version: "latest"
 

.github/workflows/haos-e2e-embedded-tests.yml

@@ -228,7 +228,7 @@ jobs:
       # in conftest.py) — never on the cached base.
 
       - name: Install uv
-        uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
+        uses: astral-sh/setup-uv@20cfd1bf945f4377ade1205e4dbc17946fc9a30d # v10.0.1
         with:
           version: "latest"
 

.github/workflows/haos-e2e-inaddon-tests.yml

@@ -234,7 +234,7 @@ jobs:
       # gets cached.
 
       - name: Install uv
-        uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
+        uses: astral-sh/setup-uv@20cfd1bf945f4377ade1205e4dbc17946fc9a30d # v10.0.1
         with:
           version: "latest"
 

.github/workflows/haos-e2e-stdio-tests.yml

@@ -160,7 +160,7 @@ jobs:
       # race it with a second cache save.
 
       - name: Install uv
-        uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
+        uses: astral-sh/setup-uv@20cfd1bf945f4377ade1205e4dbc17946fc9a30d # v10.0.1
         with:
           version: "latest"