fix(settings): reconcile admin toggle on partial cleanup failure and report errors

- In imagePreferences.js, distinguish pre-persistence failures from post-save cleanup failures using err.globalSaved and err.phase.

- In imagePreferences.js, notify listeners of global policy updates on partial success before propagating cleanup failure.

- In imageModels.js, retain the persisted target state on admin toggle when global persistence succeeds but cleanup fails.

- In imageModels.js, reconcile admin toggle with authoritative server state via readImagePreferences() after ambiguous or partial failures.

- In imageModels.js, report partial success accurately without suppressing preference cleanup error messages.

- Add regression coverage in test_settings_save_response_ok_js.py for cleanup HTTP 500, cleanup network rejection, successful cleanup, and failed global POST.

.github/workflows/ci.yml

@@ -76,7 +76,7 @@ jobs:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1  # v7.0.1
         with:
           persist-credentials: false
-      - uses: actions/setup-python@6d4fd22b20465ccc0f7354476588e8df7c9ca0e0  # v7.1.0
+      - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97  # v7.0.0
         with:
           python-version: "3.11"
       # Byte-compile sources — catches syntax errors without installing deps.
@@ -91,7 +91,7 @@ jobs:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1  # v7.0.1
         with:
           persist-credentials: false
-      - uses: actions/setup-node@949feb2413d6458794dcd2491c4babbbce0c15c1  # v7.1.0
+      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020  # v7.0.0
         with:
           node-version: "22.23.4"
       - run: npm ci --ignore-scripts --no-audit --no-fund
@@ -151,7 +151,7 @@ jobs:
             echo "docs_only=false" >> "$GITHUB_OUTPUT"
           fi
 
-      - uses: actions/setup-python@6d4fd22b20465ccc0f7354476588e8df7c9ca0e0  # v7.1.0
+      - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97  # v7.0.0
         if: steps.docs-check.outputs.docs_only != 'true'
         with:
           python-version: "3.11"
@@ -168,7 +168,7 @@ jobs:
 
       # uv resolves the same versions as pip but installs ~5x faster, and its
       # cache keeps each shard from re-downloading the whole requirement set.
-      - uses: astral-sh/setup-uv@68559e99cc807c1eb7e9238fd43a15bba460eec2  # v10.3.3
+      - uses: astral-sh/setup-uv@c18668ad3cf93ea998bef934396af7bb5c839dc7  # v10.2.0
         if: steps.docs-check.outputs.docs_only != 'true'
         with:
           version: "0.13.5"
@@ -181,7 +181,7 @@ jobs:
           uv pip install --system -r requirements.txt
           uv pip install --system "playwright==1.62.0"
         if: steps.docs-check.outputs.docs_only != 'true'
-      - uses: actions/setup-node@949feb2413d6458794dcd2491c4babbbce0c15c1  # v7.1.0
+      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020  # v7.0.0
         if: steps.docs-check.outputs.docs_only != 'true'
         with:
           node-version: "22.23.4"

.github/workflows/codeql.yml

@@ -31,11 +31,11 @@ jobs:
         with:
           persist-credentials: false
       - name: Initialize CodeQL
-        uses: github/codeql-action/init@9b3254085494b55a0f7c4c2b3d2d52cc712ce370  # v4.39.1
+        uses: github/codeql-action/init@ff2f1c621b7f889edc0d3c761ac2e6a3f8cdb0dd  # v4.37.7
         with:
           languages: ${{ matrix.language }}
           build-mode: none
       - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@9b3254085494b55a0f7c4c2b3d2d52cc712ce370  # v4.39.1
+        uses: github/codeql-action/analyze@ff2f1c621b7f889edc0d3c761ac2e6a3f8cdb0dd  # v4.37.7
         with:
           category: "/language:${{ matrix.language }}"

.github/workflows/container-scan.yml

@@ -42,7 +42,7 @@ jobs:
           persist-credentials: false
 
       - name: Lint Dockerfile
-        uses: hadolint/hadolint-action@06be81baf89a55ffd0e24b8f04a4185738dd3387  # v3.5.0
+        uses: hadolint/hadolint-action@2a66e89f53d0771bb131a7fa31f3136336094aa6  # v3.4.0
         with:
           dockerfile: Dockerfile
           # DL3008: pinning apt package versions is impractical on a -slim base

.github/workflows/container-trivy.yml

@@ -61,14 +61,14 @@ jobs:
           persist-credentials: false
 
       - name: Set up Buildx
-        uses: docker/setup-buildx-action@f87e5991a6d7451dcb8d9637bfbc97413f497069  # v4.4.1
+        uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e  # v4.3.0
         with:
           driver: docker
 
       # Build without pushing so a broken Dockerfile is caught here, and the
       # exact image we ship is what gets scanned.
       - name: Build image
-        uses: docker/build-push-action@c3c9e263c25d99ce0380d002d59b67737d91b0dc  # v7.4.0
+        uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a  # v7.3.0
         with:
           context: .
           push: false
@@ -107,12 +107,12 @@ jobs:
           persist-credentials: false
 
       - name: Set up Buildx
-        uses: docker/setup-buildx-action@f87e5991a6d7451dcb8d9637bfbc97413f497069  # v4.4.1
+        uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e  # v4.3.0
         with:
           driver: docker
 
       - name: Build image
-        uses: docker/build-push-action@c3c9e263c25d99ce0380d002d59b67737d91b0dc  # v7.4.0
+        uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a  # v7.3.0
         with:
           context: .
           push: false
@@ -133,7 +133,7 @@ jobs:
           TRIVY_DB_REPOSITORY: ghcr.io/aquasecurity/trivy-db:2
 
       - name: Upload Trivy results
-        uses: github/codeql-action/upload-sarif@9b3254085494b55a0f7c4c2b3d2d52cc712ce370  # v4.39.1
+        uses: github/codeql-action/upload-sarif@ff2f1c621b7f889edc0d3c761ac2e6a3f8cdb0dd  # v4.37.7
         with:
           sarif_file: trivy-results.sarif
           category: trivy-image

.github/workflows/dependency-review.yml

@@ -63,7 +63,7 @@ jobs:
           persist-credentials: false
 
       - name: Set up Python
-        uses: actions/setup-python@6d4fd22b20465ccc0f7354476588e8df7c9ca0e0  # v7.1.0
+        uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97  # v7.0.0
         with:
           python-version: '3.12'
 

.github/workflows/deploy-pages.yml

@@ -47,4 +47,4 @@ jobs:
     steps:
       - name: Deploy to GitHub Pages
         id: deployment
-        uses: actions/deploy-pages@368f82528645a54fb793d4d04e342629a3f51346  # v5.0.1
+        uses: actions/deploy-pages@cd2ce8fcbc39b97be8ca5fce6e763baed58fa128  # v5.0.0

.github/workflows/docker-publish.yml

@@ -55,16 +55,16 @@ jobs:
         shell: bash
         run: echo "IMAGE_NAME=${GITHUB_REPOSITORY,,}" >> "$GITHUB_ENV"
       - name: Set up Buildx
-        uses: docker/setup-buildx-action@f87e5991a6d7451dcb8d9637bfbc97413f497069  # v4.4.1
+        uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e  # v4.3.0
       - name: Log in to GHCR
-        uses: docker/login-action@81c6f93d4bc991e510b342a00b419b3bb4efc5c6  # v4.7.0
+        uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f  # v4.6.0
         with:
           registry: ${{ env.REGISTRY }}
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
       - name: Build and push by digest
         id: build
-        uses: docker/build-push-action@c3c9e263c25d99ce0380d002d59b67737d91b0dc  # v7.4.0
+        uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a  # v7.3.0
         with:
           context: .
           pull: true
@@ -78,7 +78,7 @@ jobs:
           digest="${{ steps.build.outputs.digest }}"
           touch "/tmp/digests/${digest#sha256:}"
       - name: Upload digest
-        uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9  # v7.0.2
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a  # v7.0.1
         with:
           name: digest-${{ matrix.arch }}
           path: /tmp/digests/*
@@ -107,15 +107,15 @@ jobs:
           echo "version=$v" >> "$GITHUB_OUTPUT"
           echo "short=${GITHUB_SHA::7}" >> "$GITHUB_OUTPUT"
       - name: Download digests
-        uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333  # v8.0.2
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c  # v8.0.1
         with:
           path: /tmp/digests
           pattern: digest-*
           merge-multiple: true
       - name: Set up Buildx
-        uses: docker/setup-buildx-action@f87e5991a6d7451dcb8d9637bfbc97413f497069  # v4.4.1
+        uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e  # v4.3.0
       - name: Log in to GHCR
-        uses: docker/login-action@81c6f93d4bc991e510b342a00b419b3bb4efc5c6  # v4.7.0
+        uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f  # v4.6.0
         with:
           registry: ${{ env.REGISTRY }}
           username: ${{ github.actor }}

.github/workflows/searxng-image.yml

@@ -62,9 +62,9 @@ jobs:
         env:
           SEARXNG_TEST_IMAGE: ${{ steps.image.outputs.image }}
         run: docker pull "$SEARXNG_TEST_IMAGE"
-      - uses: docker/setup-buildx-action@f87e5991a6d7451dcb8d9637bfbc97413f497069 # v4.4.1
+      - uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e # v4.3.0
       - name: Check unmodified upstream trust and actual entrypoint offline
-        uses: docker/build-push-action@c3c9e263c25d99ce0380d002d59b67737d91b0dc # v7.4.0
+        uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a # v7.3.0
         with:
           context: .
           file: docker/searxng/Dockerfile

.github/workflows/workflow-security.yml

@@ -66,7 +66,7 @@ jobs:
           persist-credentials: false
 
       - name: Set up Python
-        uses: actions/setup-python@6d4fd22b20465ccc0f7354476588e8df7c9ca0e0  # v7.1.0
+        uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97  # v7.0.0
         with:
           python-version: '3.12'
 

docker-compose.gpu-amd.yml

@@ -82,15 +82,13 @@ services:
       - ODYSSEUS_EDITOR_DRAFT_MAX_BYTES=${ODYSSEUS_EDITOR_DRAFT_MAX_BYTES:-268435456}
       - ODYSSEUS_STT_MAX_AUDIO_BYTES=${ODYSSEUS_STT_MAX_AUDIO_BYTES:-26214400}
       - ODYSSEUS_ICS_MAX_BYTES=${ODYSSEUS_ICS_MAX_BYTES:-10485760}
-      - ODYSSEUS_TTS_CACHE_MAX_BYTES=${ODYSSEUS_TTS_CACHE_MAX_BYTES:-524288000}
+      - ODYSSEUS_TTS_CACHE_MAX_BYTES=${ODYSSEUS_TTS_CACHE_MAX_BYTES}
       # Host workspace translation is opt-in. Keep the public compose file
       # user-neutral; configure these in a local .env or use the host-workspace
       # overlay with ODYSSEUS_HOST_WORKSPACE_DIR.
       - ODYSSEUS_WORKSPACE_HOST_ROOT=${ODYSSEUS_WORKSPACE_HOST_ROOT:-}
       - ODYSSEUS_WORKSPACE_CONTAINER_ROOT=${ODYSSEUS_WORKSPACE_CONTAINER_ROOT:-/workspace}
       - ODYSSEUS_WORKSPACE_DEFAULT=${ODYSSEUS_WORKSPACE_DEFAULT:-}
-      # Local first-token watchdog in seconds; 0 disables it. Empty keeps the code default (60s).
-      - ODYSSEUS_FIRST_TOKEN_TIMEOUT=${ODYSSEUS_FIRST_TOKEN_TIMEOUT:-}
       - DATA_BRAVE_API_KEY=${DATA_BRAVE_API_KEY:-}
       - GOOGLE_API_KEY=${GOOGLE_API_KEY:-}
       - GOOGLE_PSE_CX=${GOOGLE_PSE_CX:-}
@@ -167,7 +165,7 @@ services:
         /usr/local/searxng/.venv/bin/python /tmp/migrate-searxng-settings.py /etc/searxng/settings.yml || true
         exec /usr/local/searxng/entrypoint.sh
     ports:
-      - "127.0.0.1:${SEARXNG_HOST_PORT:-8080}:8080"
+      - "127.0.0.1:8080:8080"
     volumes:
       - searxng-data:/etc/searxng
       - ./config/searxng/settings.yml:/tmp/searxng-settings.yml.template:ro,z

docker-compose.gpu-nvidia.yml

@@ -81,15 +81,13 @@ services:
       - ODYSSEUS_EDITOR_DRAFT_MAX_BYTES=${ODYSSEUS_EDITOR_DRAFT_MAX_BYTES:-268435456}
       - ODYSSEUS_STT_MAX_AUDIO_BYTES=${ODYSSEUS_STT_MAX_AUDIO_BYTES:-26214400}
       - ODYSSEUS_ICS_MAX_BYTES=${ODYSSEUS_ICS_MAX_BYTES:-10485760}
-      - ODYSSEUS_TTS_CACHE_MAX_BYTES=${ODYSSEUS_TTS_CACHE_MAX_BYTES:-524288000}
+      - ODYSSEUS_TTS_CACHE_MAX_BYTES=${ODYSSEUS_TTS_CACHE_MAX_BYTES}
       # Host workspace translation is opt-in. Keep the public compose file
       # user-neutral; configure these in a local .env or use the host-workspace
       # overlay with ODYSSEUS_HOST_WORKSPACE_DIR.
       - ODYSSEUS_WORKSPACE_HOST_ROOT=${ODYSSEUS_WORKSPACE_HOST_ROOT:-}
       - ODYSSEUS_WORKSPACE_CONTAINER_ROOT=${ODYSSEUS_WORKSPACE_CONTAINER_ROOT:-/workspace}
       - ODYSSEUS_WORKSPACE_DEFAULT=${ODYSSEUS_WORKSPACE_DEFAULT:-}
-      # Local first-token watchdog in seconds; 0 disables it. Empty keeps the code default (60s).
-      - ODYSSEUS_FIRST_TOKEN_TIMEOUT=${ODYSSEUS_FIRST_TOKEN_TIMEOUT:-}
       - DATA_BRAVE_API_KEY=${DATA_BRAVE_API_KEY:-}
       - GOOGLE_API_KEY=${GOOGLE_API_KEY:-}
       - GOOGLE_PSE_CX=${GOOGLE_PSE_CX:-}
@@ -170,7 +168,7 @@ services:
         /usr/local/searxng/.venv/bin/python /tmp/migrate-searxng-settings.py /etc/searxng/settings.yml || true
         exec /usr/local/searxng/entrypoint.sh
     ports:
-      - "127.0.0.1:${SEARXNG_HOST_PORT:-8080}:8080"
+      - "127.0.0.1:8080:8080"
     volumes:
       - searxng-data:/etc/searxng
       - ./config/searxng/settings.yml:/tmp/searxng-settings.yml.template:ro,z

docker-compose.yml

@@ -70,15 +70,13 @@ services:
       - ODYSSEUS_EDITOR_DRAFT_MAX_BYTES=${ODYSSEUS_EDITOR_DRAFT_MAX_BYTES:-268435456}
       - ODYSSEUS_STT_MAX_AUDIO_BYTES=${ODYSSEUS_STT_MAX_AUDIO_BYTES:-26214400}
       - ODYSSEUS_ICS_MAX_BYTES=${ODYSSEUS_ICS_MAX_BYTES:-10485760}
-      - ODYSSEUS_TTS_CACHE_MAX_BYTES=${ODYSSEUS_TTS_CACHE_MAX_BYTES:-524288000}
+      - ODYSSEUS_TTS_CACHE_MAX_BYTES=${ODYSSEUS_TTS_CACHE_MAX_BYTES}
       # Host workspace translation is opt-in. Keep the public compose file
       # user-neutral; configure these in a local .env or use the host-workspace
       # overlay with ODYSSEUS_HOST_WORKSPACE_DIR.
       - ODYSSEUS_WORKSPACE_HOST_ROOT=${ODYSSEUS_WORKSPACE_HOST_ROOT:-}
       - ODYSSEUS_WORKSPACE_CONTAINER_ROOT=${ODYSSEUS_WORKSPACE_CONTAINER_ROOT:-/workspace}
       - ODYSSEUS_WORKSPACE_DEFAULT=${ODYSSEUS_WORKSPACE_DEFAULT:-}
-      # Local first-token watchdog in seconds; 0 disables it. Empty keeps the code default (60s).
-      - ODYSSEUS_FIRST_TOKEN_TIMEOUT=${ODYSSEUS_FIRST_TOKEN_TIMEOUT:-}
       - DATA_BRAVE_API_KEY=${DATA_BRAVE_API_KEY:-}
       - GOOGLE_API_KEY=${GOOGLE_API_KEY:-}
       - GOOGLE_PSE_CX=${GOOGLE_PSE_CX:-}
@@ -148,7 +146,7 @@ services:
         /usr/local/searxng/.venv/bin/python /tmp/migrate-searxng-settings.py /etc/searxng/settings.yml || true
         exec /usr/local/searxng/entrypoint.sh
     ports:
-      - "127.0.0.1:${SEARXNG_HOST_PORT:-8080}:8080"
+      - "127.0.0.1:8080:8080"
     volumes:
       - searxng-data:/etc/searxng
       - ./config/searxng/settings.yml:/tmp/searxng-settings.yml.template:ro,z

docker/build-realesrgan-wheels.sh

@@ -31,43 +31,21 @@ for spec in $SPECS; do
   name="${spec%%==*}"
   ver="${spec##*==}"
   # pip download builds metadata (and trips the same bug), so fetch the raw
-  # sdist URL from the PyPI JSON API instead.  Use curl with retries to
+  # sdist URL from the PyPI JSON API instead.
-  # survive transient TLS / network failures that urllib cannot recover from.
+  url="$(python - "$name" "$ver" <<'PY'
-  metadata="${name}-${ver}.json"
+import json, sys, urllib.request
-  curl --fail --silent --show-error --location \
+name, ver = sys.argv[1], sys.argv[2]
-    --retry 8 \
+data = json.load(urllib.request.urlopen(f"https://pypi.org/pypi/{name}/{ver}/json"))
-    --retry-delay 3 \
+for f in data["urls"]:
-    --retry-max-time 120 \
+    if f["packagetype"] == "sdist":
-    --retry-all-errors \
+        print(f["url"]); break
-    "https://pypi.org/pypi/${name}/${ver}/json" \
-    -o "$metadata"
-
-  url="$(python - "$metadata" <<'PY'
-import json, sys
-
-with open(sys.argv[1], encoding="utf-8") as f:
-    data = json.load(f)
-
-for item in data["urls"]:
-    if item["packagetype"] == "sdist":
-        print(item["url"])
-        break
 else:
-    raise SystemExit("no sdist found")
+    sys.exit(f"no sdist found for {name}=={ver}")
 PY
-  )"
+)"
-  rm -f "$metadata"
-
   echo ">> fetching ${name} ${ver}: ${url}"
-  curl --fail --silent --show-error --location \
+  curl -fsSL "$url" -o "${name}.tar.gz"
-    --retry 8 \
-    --retry-delay 3 \
-    --retry-max-time 120 \
-    --retry-all-errors \
-    "$url" \
-    -o "${name}.tar.gz"
   tar xzf "${name}.tar.gz"
-  rm -f "${name}.tar.gz"
 done
 
 echo ">> patching get_version()"

routes/chat_routes.py

@@ -1901,7 +1901,7 @@ def _ts_or_zero(value) -> float:
 
 
 def _recover_empty_session_model(sess, session_id: str, owner: str | None = None) -> bool:
-    """Recover sess.model from the endpoint's visible cached and pinned models.
+    """Re-populate sess.model from the matching endpoint's cached models.
 
     Covers the window between endpoint setup and the first chat send: the
     picker showed a model in the dropdown but the session record never got
@@ -1965,9 +1965,6 @@ def _recover_empty_session_model(sess, session_id: str, owner: str | None = None
                 visible = _visible_models(cached, getattr(ep, "hidden_models", None))
             except Exception:
                 visible = cached
-        if not is_chatgpt_subscription:
-            from src.endpoint_resolver import _endpoint_enabled_models
-            visible = _endpoint_enabled_models(ep)
         if current_model and current_model in {str(item).strip() for item in visible}:
             return False
         if is_chatgpt_subscription:
@@ -3926,19 +3923,6 @@ def setup_chat_routes(
             if ctx.preprocessed.attachment_meta:
                 yield f"data: {json.dumps({'type': 'attachments', 'data': ctx.preprocessed.attachment_meta})}\n\n"
 
-            # Give the page the saved user message's id. Only the reply's id
-            # was sent back, so a message sent in the open page had none and
-            # a later regenerate/edit of it could not cut the chat by id.
-            try:
-                _last_user_msg = next((m for m in reversed(getattr(sess, "history", None) or [])
-                                       if getattr(m, "role", None) == "user"), None)
-                _user_db_id = ((getattr(_last_user_msg, "metadata", None) or {}).get("_db_id")
-                               if _last_user_msg is not None else None)
-                if _user_db_id:
-                    yield f"data: {json.dumps({'type': 'user_message_saved', 'id': _user_db_id})}\n\n"
-            except Exception:
-                pass
-
             # Announce any docs auto-created during preprocess (e.g. fillable
             # PDF → editable markdown) so the editor pane switches to them
             # before the model starts streaming.

routes/cookbook_helpers.py

@@ -1491,20 +1491,6 @@ def _diagnose_serve_output(text: str) -> dict | None:
             "Port is already in use.",
             [{"label": "retry on port 8001", "op": "replace", "flag": "--port", "value": "8001"}],
         ),
-        (
-            # PyPI torch/vLLM wheels now target CUDA 13, which needs driver 580+.
-            # torch: "The NVIDIA driver on your system is too old (found version 12080)";
-            # vLLM kernels: "CUDA driver version is insufficient for CUDA runtime version".
-            r"NVIDIA driver on your system is too old|CUDA driver version is insufficient",
-            "The installed PyTorch/vLLM build needs a newer NVIDIA driver than this server has.",
-            [
-                {
-                    "label": "install builds for the driver's CUDA version, e.g. vLLM's +cu129 wheel from its GitHub release with uv pip install … --torch-backend cu129",
-                    "op": "manual",
-                },
-                {"label": "or update the NVIDIA driver (CUDA 13 builds need driver 580 or newer)", "op": "manual"},
-            ],
-        ),
         (
             r"No CUDA GPUs are available|no GPU.*found|CUDA_VISIBLE_DEVICES.*invalid",
             "No GPUs are visible to the serve process.",

routes/cookbook_routes.py

@@ -468,6 +468,175 @@ def setup_cookbook_routes() -> APIRouter:
                     task["payload"].pop("hf_token", None)
         return state
 
+    def _diagnose_serve_output(text: str) -> dict | None:
+        """Server-side mirror of the Cookbook UI's common serve diagnoses.
+
+        The browser uses cookbook-diagnosis.js for clickable fixes. This gives
+        the agent/tool path the same structured signal so it can retry with an
+        adjusted command instead of guessing from raw tmux output.
+        """
+        if not text:
+            return None
+        tail = text[-6000:]
+        patterns = [
+            (
+                r"No available memory for the cache blocks|Available KV cache memory:.*-",
+                "No GPU memory left for KV cache after loading model.",
+                [
+                    {"label": "retry with GPU memory utilization 0.95", "op": "replace", "flag": "--gpu-memory-utilization", "value": "0.95"},
+                    {"label": "retry with context 2048", "op": "replace", "flag": "--max-model-len", "value": "2048"},
+                ],
+            ),
+            (
+                r"CUDA out of memory|torch\.cuda\.OutOfMemoryError|CUDA error: out of memory|warming up sampler|max_num_seqs.*gpu_memory_utilization",
+                "GPU ran out of memory during startup or warmup.",
+                [
+                    {"label": "retry with context 4096", "op": "replace", "flag": "--max-model-len", "value": "4096"},
+                    {"label": "retry with GPU memory utilization 0.80", "op": "replace", "flag": "--gpu-memory-utilization", "value": "0.80"},
+                    {"label": "retry with --enforce-eager", "op": "append", "arg": "--enforce-eager"},
+                ],
+            ),
+            (
+                r"not divisib|must be divisible|attention heads.*divisible",
+                "Tensor parallel size is incompatible with the model.",
+                [
+                    {"label": "retry with tensor parallel size 1", "op": "replace", "flag": "--tensor-parallel-size", "value": "1"},
+                    {"label": "retry with tensor parallel size 2", "op": "replace", "flag": "--tensor-parallel-size", "value": "2"},
+                ],
+            ),
+            (
+                r"KV cache.*too (small|large)|max_model_len.*exceeds|maximum.*context",
+                "Context length is too large for available GPU memory.",
+                [
+                    {"label": "retry with context 8192", "op": "replace", "flag": "--max-model-len", "value": "8192"},
+                    {"label": "retry with context 4096", "op": "replace", "flag": "--max-model-len", "value": "4096"},
+                ],
+            ),
+            (
+                r"enable-auto-tool-choice requires --tool-call-parser",
+                "Auto tool choice requires an explicit tool call parser.",
+                [{"label": "retry with Hermes tool parser", "op": "append", "arg": "--tool-call-parser hermes"}],
+            ),
+            (
+                r"Please pass.*trust.remote.code=True|contains custom code which must be executed to correctly load|does not recognize this architecture|model type.*but Transformers does not",
+                "Model requires custom code or newer model support.",
+                [{"label": "retry with --trust-remote-code", "op": "append", "arg": "--trust-remote-code"}],
+            ),
+            (
+                r"Either a revision or a version must be specified|transformers\.integrations\.hub_kernels|kernels/layer",
+                "vLLM/Transformers kernel package mismatch.",
+                [{"label": "update vLLM, Transformers, and kernels on this server", "op": "dependency", "package": "vllm transformers kernels"}],
+            ),
+            (
+                r"Address already in use|bind.*address.*in use",
+                "Port is already in use.",
+                [{"label": "retry on port 8001", "op": "replace", "flag": "--port", "value": "8001"}],
+            ),
+            (
+                r"No CUDA GPUs are available|no GPU.*found|CUDA_VISIBLE_DEVICES.*invalid",
+                "No GPUs are visible to the serve process.",
+                [{"label": "clear Cookbook GPU selection or choose available GPUs", "op": "settings", "field": "gpus", "value": ""}],
+            ),
+            (
+                r"Failed to infer device type|NVML Shared Library Not Found|No module named 'amdsmi'|platform is not available",
+                "vLLM could not find a supported GPU (CUDA or ROCm). "
+                "This machine may have integrated or unsupported graphics only.",
+                [
+                    {"label": "switch to llama.cpp (CPU/Metal, works without a discrete GPU)", "op": "manual"},
+                    {"label": "switch to Ollama (CPU/Metal, works without a discrete GPU)", "op": "manual"},
+                ],
+            ),
+            (
+                r"vllm.*command not found|No module named vllm|ERROR: vLLM is not installed",
+                "vLLM is not installed or not in PATH on this server.",
+                [{"label": "install vLLM in Cookbook Dependencies", "op": "dependency", "package": "vllm"}],
+            ),
+            (
+                r"sgl_kernel[\s\S]*(Python\.h|libnuma\.so\.1|common_ops|libnvrtc\.so)|"
+                r"(Python\.h|libnuma\.so\.1|common_ops|libnvrtc\.so)[\s\S]*sgl_kernel|"
+                r"Could not load any common_ops library|"
+                r"Please ensure sgl_kernel is properly installed",
+                "SGLang native kernel/runtime is missing or mismatched on this server.",
+                [
+                    {"label": "repair sglang-kernel in this Python environment", "op": "dependency", "package": "sglang-kernel"},
+                    {"label": "if libnvrtc is still missing, install the matching CUDA/NVRTC runtime on this host", "op": "manual"},
+                ],
+            ),
+            (
+                r"sglang.*command not found|No module named sglang|SGLang is not installed",
+                "SGLang is not installed or not in PATH on this server.",
+                [{"label": "install SGLang in Cookbook Dependencies", "op": "dependency", "package": "sglang[all]"}],
+            ),
+            (
+                r"No module named ['\"]?mlx_lm|mlx_lm.*command not found|MLX is not installed|MLX LM is not installed",
+                "MLX LM is not installed on this server.",
+                [{"label": "install mlx-lm in Cookbook Dependencies", "op": "dependency", "package": "mlx-lm"}],
+            ),
+            (
+                r"OmniGen2Pipeline|module diffusers has no attribute .*Pipeline|custom_pipeline=.*failed",
+                "This image model uses a custom Diffusers pipeline that the launch environment does not know yet.",
+                [{"label": "update Diffusers image dependencies", "op": "dependency", "package": "diffusers transformers accelerate"}],
+            ),
+            (
+                r"Unable to quantize model of type <class ['\"]mlx_lm\.models\.switch_layers\.QuantizedSwitchLinear['\"]>|QuantizedSwitchLinear",
+                "MLX-LM tried to quantize an already-quantized DeepSeek switch layer.",
+                [
+                    {"label": "relaunch from the cached local Hugging Face snapshot path on this Mac", "op": "manual"},
+                    {"label": "Odysseus now rewrites MLX repo-id launches to a cached snapshot when one exists", "op": "manual"},
+                ],
+            ),
+            # System build deps come BEFORE the generic llama.cpp catch-all
+            # so cmake / build-essential / git missing → a specific OS-package
+            # remediation instead of "install llama-cpp-python[server]" (which
+            # itself fails to compile when cmake is absent).
+            (
+                r"cmake: command not found|cmake.*not found.*[Cc]ould not",
+                "cmake is required to build llama.cpp from source but isn't installed on this server.",
+                [{"label": "install build deps for llama.cpp (apt: cmake build-essential git / pacman: cmake base-devel git / dnf: cmake gcc-c++ make git / brew: cmake git)", "op": "dependency", "package": "llama-cpp-python[server]"}],
+            ),
+            (
+                r"^(make|g\+\+|gcc): command not found|Could not find C\+\+ compiler",
+                "A C/C++ compiler (build-essential) is required to build llama.cpp from source.",
+                [{"label": "install build deps for llama.cpp on this server", "op": "dependency", "package": "llama-cpp-python[server]"}],
+            ),
+            (
+                r"^git: command not found",
+                "git is required to clone the llama.cpp source tree.",
+                [{"label": "install build deps for llama.cpp on this server", "op": "dependency", "package": "llama-cpp-python[server]"}],
+            ),
+            (
+                r"llama-server.*command not found|llama\.cpp.*not found|No module named.*llama_cpp|No module named 'starlette_context'",
+                "llama.cpp / llama-cpp-python dependencies are missing.",
+                [{"label": "install llama.cpp dependencies or llama-cpp-python[server]", "op": "dependency", "package": "llama-cpp-python[server]"}],
+            ),
+            (
+                r"No GGUF found on this host|no \.gguf file|No GGUF file found",
+                "No GGUF file found for this model on this host. The llama.cpp backend needs a .gguf file.",
+                [{"label": "download a GGUF build of this model (repo name usually ends in -GGUF, file like Q4_K_M.gguf)", "op": "manual"}],
+            ),
+            (
+                r"No module named 'torch'|No module named torch|No module named 'torchvision'|No module named torchvision|No module named 'diffusers'|No module named diffusers|No module named 'scipy'|No module named scipy|install scipy if you want to use beta sigmas|requires the Torchvision library",
+                "Diffusion serving requires PyTorch, Torchvision, Diffusers, Accelerate, and SciPy.",
+                [{"label": "install Diffusers image deps in Cookbook Dependencies", "op": "dependency", "package": "diffusers[torch] torchvision accelerate scipy python-multipart"}],
+            ),
+            (
+                r"403 Forbidden|401 Unauthorized|Access to model.*is restricted|gated repo|not in the authorized list|awaiting a review",
+                "Model access is gated or unauthorized.",
+                [{"label": "set HF token and request model access on HuggingFace", "op": "manual"}],
+            ),
+        ]
+        for pattern, message, suggestions in patterns:
+            if re.search(pattern, tail, re.I):
+                return {"message": message, "suggestions": suggestions}
+        if re.search(r"Traceback \(most recent call last\)", tail, re.I) and not re.search(
+            r"Application startup complete|GET /v1/|Uvicorn running on", tail, re.I
+        ):
+            return {
+                "message": "Python traceback detected during serve startup.",
+                "suggestions": [{"label": "inspect traceback and retry with adjusted backend/settings", "op": "manual"}],
+            }
+        return None
+
     def _state_for_client(state):
         """Return cookbook state without raw secrets for browser clients."""
         _strip_task_secrets(state)
@@ -3761,7 +3930,7 @@ def setup_cookbook_routes() -> APIRouter:
                     return {"ok": False, "files": [], "error": f"HF API HTTP {resp.status_code}"}
                 data = resp.json()
         except Exception:
-            logger.exception("HF GGUF file scan failed for %s", repo_id)
+            logger.exception("HF GGUF file scan failed for %s", repo)
             return {"ok": False, "files": [], "error": "HF API request failed"}
         files = [
             str(s.get("rfilename") or "")
@@ -4277,9 +4446,7 @@ def setup_cookbook_routes() -> APIRouter:
                 # fills the visible tail. Without this, output_tail ends up
                 # as just "Locale: C / Ubuntu_Odysseus ❯" and the agent
                 # can't diagnose the actual error.
-                # -J joins lines tmux wrapped at the pane width, so an error
+                capture_cmd = ssh_base + [remote, _remote_tmux_command("capture-pane", "-t", session_id, "-p", "-S", "-500")]
-                # split mid-word still matches the serve diagnosis patterns.
-                capture_cmd = ssh_base + [remote, _remote_tmux_command("capture-pane", "-t", session_id, "-p", "-J", "-S", "-500")]
             elif IS_WINDOWS:
                 # LOCAL Windows task: launched as a detached process (no tmux).
                 # Liveness comes from the <session>.pid file, output from the
@@ -4288,7 +4455,7 @@ def setup_cookbook_routes() -> APIRouter:
                 capture_cmd = None
             else:
                 check_cmd = ["tmux", "has-session", "-t", session_id]
-                capture_cmd = ["tmux", "capture-pane", "-t", session_id, "-p", "-J", "-S", "-500"]
+                capture_cmd = ["tmux", "capture-pane", "-t", session_id, "-p", "-S", "-500"]
 
             local_win_task = (not remote) and IS_WINDOWS
 

routes/document/document_routes.py

@@ -16,7 +16,6 @@ from core.database import SessionLocal, Document, DocumentVersion
 from core.database import Session as DbSession
 from src.auth_helpers import get_current_user, _auth_disabled
 from src.constants import MAIL_ATTACHMENTS_DIR
-from src.session_search import _escape_like
 from src.upload_handler import reserve_upload_references
 
 logger = logging.getLogger(__name__)
@@ -572,10 +571,9 @@ def setup_document_routes(session_manager, upload_handler=None) -> APIRouter:
             # match docs containing both words regardless of position/order.
             if search:
                 for tok in search.split():
-                    term = f"%{_escape_like(tok)}%"
+                    term = f"%{tok}%"
                     q = q.filter(
-                        Document.title.ilike(term, escape="\\")
+                        Document.title.ilike(term) | Document.current_content.ilike(term)
-                        | Document.current_content.ilike(term, escape="\\")
                     )
 
             # Language filter. "pdf" is a display language derived from the
@@ -814,13 +812,10 @@ def setup_document_routes(session_manager, upload_handler=None) -> APIRouter:
                     ext = _ext.get(doc.language or "text", ".txt")
                     base = (doc.title or "document").strip() or "document"
                     base = re.sub(r"[^\w\-. ]+", "", base)[:60].strip() or doc.id
-                    has_ext = base.lower().endswith(ext)
+                    name = base if "." in base else base + ext
-                    stem = base[:-len(ext)] if has_ext else base
-                    suffix = base[-len(ext):] if has_ext else ext
-                    name = stem + suffix
                     i = 1
                     while name in used:
-                        name = f"{stem}-{i}{suffix}"
+                        name = f"{base}-{i}" + ("" if "." in base else ext)
                         i += 1
                     used.add(name)
                     content = doc.current_content or ""

routes/gallery/gallery_routes.py

@@ -18,7 +18,6 @@ from fastapi import APIRouter, HTTPException, Query, Request
 from core.database import SessionLocal, GalleryImage, GalleryAlbum, ModelEndpoint
 from core.database import Session as DbSession
 from src.auth_helpers import get_current_user, owner_filter, require_privilege
-from src.session_search import escape_like_pattern
 from src.upload_limits import (
     read_upload_limited,
     GALLERY_UPLOAD_MAX_BYTES,
@@ -324,23 +323,6 @@ def _b64_bytes(value: str, *, label: str = "image") -> bytes:
         raise HTTPException(400, f"Invalid {label}") from exc
 
 
-async def _json_object(request: Request) -> dict:
-    try:
-        data = await request.json()
-    except ValueError:
-        raise HTTPException(400, "Invalid JSON body")
-    if not isinstance(data, dict):
-        raise HTTPException(400, "JSON object body required")
-    return data
-
-
-async def _image_ids(request: Request) -> list:
-    ids = (await _json_object(request)).get("image_ids", [])
-    if not isinstance(ids, list) or not all(isinstance(i, str) for i in ids):
-        raise HTTPException(400, "image_ids must be a list of image ids")
-    return ids
-
-
 def _pil_image_to_b64(img, *, fmt: str = "PNG") -> str:
     buf = io.BytesIO()
     img.save(buf, format=fmt)
@@ -1221,18 +1203,15 @@ def setup_gallery_routes() -> APIRouter:
             )
             q = _owner_filter(q, user)
 
-            # Per-term AND search: a single `%foo bar%` LIKE only matched the
+            # Search filter (prompt + tags + ai_tags)
-            # exact phrase, so "red car" missed "a car that is red".
-            # LIKE wildcards are escaped per token.
             if search:
+                term = f"%{search}%"
                 from sqlalchemy import or_
-                for tok in search.split():
+                q = q.filter(or_(
-                    term = f"%{escape_like_pattern(tok)}%"
+                    GalleryImage.prompt.ilike(term),
-                    q = q.filter(or_(
+                    GalleryImage.tags.ilike(term),
-                        GalleryImage.prompt.ilike(term, escape="\\"),
+                    GalleryImage.ai_tags.ilike(term),
-                        GalleryImage.tags.ilike(term, escape="\\"),
+                ))
-                        GalleryImage.ai_tags.ilike(term, escape="\\"),
-                    ))
 
             # Tag filter. The UI stacks multiple tag pills by passing them
             # comma-separated — each tag adds a separate AND-filter so the
@@ -1243,10 +1222,9 @@ def setup_gallery_routes() -> APIRouter:
                 for one in (t.strip() for t in tag.split(",")):
                     if not one:
                         continue
-                    safe_tag = f"%{escape_like_pattern(one)}%"
                     q = q.filter(_or(
-                        GalleryImage.tags.ilike(safe_tag, escape="\\"),
+                        GalleryImage.tags.ilike(f"%{one}%"),
-                        GalleryImage.ai_tags.ilike(safe_tag, escape="\\"),
+                        GalleryImage.ai_tags.ilike(f"%{one}%"),
                     ))
 
             # Model filter
@@ -3014,22 +2992,14 @@ def setup_gallery_routes() -> APIRouter:
     @router.put("/api/gallery/albums/{album_id}")
     async def update_album(request: Request, album_id: str):
         user = get_current_user(request)
-        data = await _json_object(request)
+        data = await request.json()
-        name = data.get("name")
-        if name is not None:
-            if not isinstance(name, str) or not name.strip():
-                raise HTTPException(400, "Album name required")
-            name = name.strip()
-        description = data.get("description")
-        if description is not None and not isinstance(description, str):
-            raise HTTPException(400, "Album description must be a string")
         db = SessionLocal()
         try:
             album = _get_or_404_album(db, album_id, user)
-            if name is not None:
+            if data.get("name") is not None:
-                album.name = name
+                album.name = data["name"]
-            if description is not None:
+            if data.get("description") is not None:
-                album.description = description
+                album.description = data["description"]
             if data.get("cover_id") is not None:
                 cover_id = data["cover_id"] or None
                 if cover_id:
@@ -3059,7 +3029,8 @@ def setup_gallery_routes() -> APIRouter:
     @router.post("/api/gallery/albums/{album_id}/add")
     async def add_to_album(request: Request, album_id: str):
         user = get_current_user(request)
-        ids = await _image_ids(request)
+        data = await request.json()
+        ids = data.get("image_ids", [])
         db = SessionLocal()
         try:
             _get_or_404_album(db, album_id, user)
@@ -3076,7 +3047,8 @@ def setup_gallery_routes() -> APIRouter:
     @router.post("/api/gallery/albums/{album_id}/remove")
     async def remove_from_album(request: Request, album_id: str):
         user = get_current_user(request)
-        ids = await _image_ids(request)
+        data = await request.json()
+        ids = data.get("image_ids", [])
         db = SessionLocal()
         try:
             _get_or_404_album(db, album_id, user)

routes/history/history_routes.py

@@ -825,23 +825,6 @@ def setup_history_routes(session_manager, upload_handler=None) -> APIRouter:
         try:
             body = await request.json()
             keep_count = body.get("keep_count", 0)
-            # A message id is exact; keep_count from the client counts only the
-            # messages loaded in the page. before_msg_id forks before that
-            # message, through_msg_id includes it.
-            before_msg_id = str(body.get("before_msg_id") or "").strip()
-            through_msg_id = str(body.get("through_msg_id") or "").strip()
-            if before_msg_id or through_msg_id:
-                db = SessionLocal()
-                try:
-                    all_db_messages = db.query(DbChatMessage).filter(
-                        DbChatMessage.session_id == session_id
-                    ).order_by(DbChatMessage.timestamp).all()
-                finally:
-                    db.close()
-                resolved = _keep_count_before_message(all_db_messages, before_msg_id or through_msg_id)
-                if resolved is None:
-                    raise HTTPException(404, "Message not found")
-                keep_count = resolved + (0 if before_msg_id else 1)
 
             # Get the source session. keep_count indexes into source.history,
             # so this must go through get_session — reading the cache directly

routes/model_routes.py

@@ -659,7 +659,7 @@ _NON_CHAT_CONTAINS = (
     "gliner", "riva", "-parse", "-embedqa", "-nemoretriever",
     "topic-control", "calibration",
     "ai-synthetic-video", "cosmos-reason2",
-    "bge", "llama-guard", "-embed", "rerank",
+    "bge", "llama-guard",
 )
 _NON_CHAT_EXACT_PREFIXES = (
     "gpt-audio",  # gpt-audio, gpt-audio-mini etc. (not gpt-4o-audio-preview which is chat)
@@ -2846,12 +2846,11 @@ def setup_model_routes(model_discovery):
                 return {"endpoint_id": "", "endpoint_url": "", "model": ""}
             base = _normalize_base(ep.base_url)
             chat_url = build_chat_url(base)
-            if model and not _is_chat_model(model):
-                model = ""
             if not model and (getattr(ep, "cached_models", None) or getattr(ep, "pinned_models", None)):
                 try:
                     visible = _visible_models(ep.cached_models, getattr(ep, "hidden_models", None), getattr(ep, "pinned_models", None))
-                    model = next((mid for mid in visible if _is_chat_model(mid)), "")
+                    if visible:
+                        model = visible[0]
                 except Exception:
                     pass
             return {"endpoint_id": ep.id, "endpoint_url": chat_url, "model": model}

routes/research/research_routes.py

@@ -183,7 +183,6 @@ def _resolve_endpoint_runtime(ep, owner=None, model: Optional[str] = None):
     OAuth tokens in ProviderAuthSession, so ep.api_key is intentionally empty.
     """
     from src.endpoint_resolver import (
-        _endpoint_enabled_models,
         build_chat_url,
         build_headers,
         resolve_endpoint_runtime as resolve_model_endpoint_runtime,
@@ -198,7 +197,7 @@ def _resolve_endpoint_runtime(ep, owner=None, model: Optional[str] = None):
     ep_model = (model or "").strip()
     if not ep_model:
         try:
-            models = _endpoint_enabled_models(ep)
+            models = json.loads(ep.cached_models) if ep.cached_models else []
             if models:
                 ep_model = _first_chat_model(models)
         except Exception:
@@ -825,13 +824,23 @@ def setup_research_routes(research_handler, session_manager=None) -> APIRouter:
         if not ep_url or not ep_model:
             # Last resort: this user's enabled endpoint, plus legacy shared rows.
             from src.database import SessionLocal
+            from src.endpoint_resolver import normalize_base, build_chat_url, build_headers
             db = SessionLocal()
             try:
                 ep = _owned_enabled_endpoint(db, user)
                 if ep:
-                    resolved = _resolve_endpoint_runtime(ep, owner=user)
+                    base = normalize_base(ep.base_url)
-                    if resolved:
+                    fallback_url = build_chat_url(base)
-                        _merge(*resolved)
+                    fallback_headers = build_headers(ep.api_key, base)
+                    fallback_model = ""
+                    if ep.cached_models:
+                        try:
+                            models = json.loads(ep.cached_models)
+                            if models:
+                                fallback_model = _first_chat_model(models)
+                        except Exception:
+                            pass
+                    _merge(fallback_url, fallback_model, fallback_headers)
             finally:
                 db.close()
 

routes/skills_routes.py

@@ -15,7 +15,6 @@ import httpx
 from fastapi import APIRouter, HTTPException, Request
 from pydantic import BaseModel, Field
 
-from services.memory.skill_format import slugify
 from services.memory.skills import SkillsManager
 from src.auth_helpers import get_current_user
 from services.skills import evaluation as _evaluation
@@ -837,10 +836,6 @@ def setup_skills_routes(skills_manager: SkillsManager) -> APIRouter:
         updates = body.dict(exclude_none=True)
         if not updates:
             return {"ok": True}
-        if "name" in updates:
-            new_name = slugify(updates["name"] or match.get("name"))
-            if new_name != match.get("name") and skills_manager.has_skill(new_name, owner=user):
-                raise HTTPException(409, f"A skill named '{new_name}' already exists")
         ok = skills_manager.update_skill(match.get("name"), updates, owner=user)
         if not ok:
             raise HTTPException(404, "Skill not found")

routes/task/task_routes.py

@@ -289,15 +289,15 @@ def _resolve_run_endpoint(db, task: ScheduledTask, run: TaskRun) -> str:
 
     try:
         from core.database import ModelEndpoint
-        from src.auth_helpers import owner_filter
+        eps = db.query(ModelEndpoint).filter(ModelEndpoint.is_enabled == True).all()
-        from src.endpoint_resolver import _endpoint_enabled_models
-
-        eps = owner_filter(
-            db.query(ModelEndpoint).filter(ModelEndpoint.is_enabled == True),
-            ModelEndpoint, getattr(task, "owner", None),
-        ).all()
         for ep in eps:
-            if model in _endpoint_enabled_models(ep):
+            cached = []
+            if ep.cached_models:
+                try:
+                    cached = json.loads(ep.cached_models) or []
+                except Exception:
+                    cached = []
+            if model in cached:
                 return ep.base_url or ""
     except Exception:
         pass

services/memory/skill_format.py

@@ -130,15 +130,10 @@ def _parse_scalar(raw: str, *, string_only: bool = False) -> Any:
 def _split_top_level(s: str, sep: str) -> List[str]:
     """Split `s` on `sep` ignoring separators inside [] or quotes."""
     out, buf, depth, quote = [], [], 0, None
-    escaped = False
     for ch in s:
         if quote:
             buf.append(ch)
-            if escaped:
+            if ch == quote:
-                escaped = False
-            elif ch == "\\" and quote == '"':
-                escaped = True
-            elif ch == quote:
                 quote = None
             continue
         if ch in ("'", '"'):

services/memory/skills.py

@@ -500,19 +500,6 @@ class SkillsManager:
         sk.path = self._skill_file(cat, nm)
         return sk.to_dict()
 
-    def has_skill(self, name: str, owner: Optional[str] = None) -> bool:
-        """Whether `owner` already has a skill called `name`, in any category.
-
-        Update and delete find a skill by name within its owner, so two of
-        one owner's skills sharing a name would make them act on whichever
-        file is walked first.
-        """
-        for path in self._iter_skill_files():
-            sk = self._read_skill(path)
-            if sk and sk.name == name and (sk.owner or "") == (owner or ""):
-                return True
-        return False
-
     def update_skill(self, skill_id: str, updates: Dict, owner: Optional[str] = None) -> bool:
         """`skill_id` is the slug name. Allows updating any field plus
         renames if `name` changes (file is moved on disk).
@@ -564,9 +551,6 @@ class SkillsManager:
             # Rename
             new_name = slugify(updates.get("name") or sk.name)
             if new_name != sk.name:
-                if self.has_skill(new_name, owner=owner):
-                    logger.warning(f"Skill rename target name in use: {new_name}")
-                    return False
                 sk.name = new_name
 
             # Write to potentially new path

src/agent_loop.py

@@ -24193,14 +24193,11 @@ async def stream_agent_loop(
                 budget_is_explicit,
                 hard_max=hard_max,
             )
-            if 0 < candidate_context <= 8192:
+            if candidate_context <= 8192:
                 # Small local servers often tokenize chat wrappers and tool
                 # results much more generously than our rough estimator. Keep
                 # substantial headroom for those wrappers and generation so a
                 # follow-up tool round cannot exceed the server's n_ctx.
-                # 0 means the window is unknown, which already gets the
-                # conservative default budget; clamping it as well cut every
-                # request to 1200 tokens and dropped open documents (#6678).
                 effective_budget = min(
                     effective_budget,
                     max(1200, int(candidate_context * 0.40)),
@@ -27836,25 +27833,16 @@ async def stream_agent_loop(
                                 if _streamed_tool_markup or _streamed_tool_markup_starts(_delta_text):
                                     _streamed_tool_markup += _delta_text
                                     if not _streamed_tool_markup_complete(_streamed_tool_markup):
-                                        if _streamed_tool_markup_starts(_streamed_tool_markup):
+                                        continue
-                                            continue
+                                    _visible_markup_tail = strip_tool_blocks(
-                                        # False alarm: a bare "<" (e.g. ``x < 2``) looked like
+                                        _streamed_tool_markup,
-                                        # a tag prefix, but the buffer can no longer become a
+                                        skip_fenced=True,
-                                        # tool tag. Release it as prose instead of holding the
+                                    ).strip()
-                                        # rest of the answer forever.
+                                    _streamed_tool_markup = ""
-                                        _delta_text = _streamed_tool_markup
+                                    if not _visible_markup_tail:
-                                        _streamed_tool_markup = ""
+                                        continue
-                                        data["delta"] = _delta_text
+                                    _delta_text = _visible_markup_tail
-                                    else:
+                                    data["delta"] = _delta_text
-                                        _visible_markup_tail = strip_tool_blocks(
-                                            _streamed_tool_markup,
-                                            skip_fenced=True,
-                                        ).strip()
-                                        _streamed_tool_markup = ""
-                                        if not _visible_markup_tail:
-                                            continue
-                                        _delta_text = _visible_markup_tail
-                                        data["delta"] = _delta_text
                             full_response += _delta_text
                         if not _suppress_unavailable_web_delta:
                             _qwen_buffered_route = bool(

src/builtin_actions.py

@@ -10,7 +10,7 @@ import os
 import json
 import re
 import time
-from datetime import datetime, timezone
+from datetime import datetime
 from typing import Tuple
 
 from src.auth_helpers import owner_filter
@@ -1957,23 +1957,6 @@ async def action_learn_sender_signatures(owner: str, **kwargs) -> Tuple[str, boo
         return str(e), False
 
 
-def _daily_brief_utc_boundary(local_dt, tz=None):
-    """Convert a local wall-clock boundary using the offset at that boundary."""
-    if local_dt.tzinfo is None and tz is not None:
-        local_dt = local_dt.replace(tzinfo=tz)
-    return local_dt.astimezone(timezone.utc).replace(tzinfo=None)
-
-
-def _daily_brief_local_start(event, tz=None):
-    """Keep date-only/floating rows local; convert only stored UTC instants."""
-    start = event.dtstart
-    if event.is_utc and not event.all_day:
-        if start.tzinfo is None:
-            start = start.replace(tzinfo=timezone.utc)
-        return start.astimezone(tz).replace(tzinfo=None)
-    return start
-
-
 async def action_daily_brief(owner: str, **kwargs) -> Tuple[str, bool]:
     """Build a short morning digest: today's calendar events, unread email count
     + top-N senders/subjects, active todos."""
@@ -1983,13 +1966,10 @@ async def action_daily_brief(owner: str, **kwargs) -> Tuple[str, bool]:
 
         from core.database import SessionLocal, CalendarEvent, CalendarCal, Note
         from routes.email_helpers import _imap_connect, _decode_header
-        from sqlalchemy import and_, or_
 
         # ----- Calendar: today's events -----
         today = _dt.now().replace(hour=0, minute=0, second=0, microsecond=0)
         tomorrow = today + _td(days=1)
-        utc_today = _daily_brief_utc_boundary(today)
-        utc_tomorrow = _daily_brief_utc_boundary(tomorrow)
         # v2 review HIGH-12: gate the OR-null branch on single-user
         # (unconfigured) deploys only. In a multi-user deploy, one
         # user's daily brief must not include another user's notes or
@@ -2002,25 +1982,13 @@ async def action_daily_brief(owner: str, **kwargs) -> Tuple[str, bool]:
         db = SessionLocal()
         try:
             ev_q = db.query(CalendarEvent).join(CalendarCal).filter(
-                or_(
+                CalendarEvent.dtstart < tomorrow,
-                    and_(
+                CalendarEvent.dtend > today,
-                        CalendarEvent.is_utc.is_(True),
-                        CalendarEvent.all_day.is_not(True),
-                        CalendarEvent.dtstart < utc_tomorrow,
-                        CalendarEvent.dtend > utc_today,
-                    ),
-                    and_(
-                        or_(CalendarEvent.is_utc.is_not(True), CalendarEvent.all_day.is_(True)),
-                        CalendarEvent.dtstart < tomorrow,
-                        CalendarEvent.dtend > today,
-                    ),
-                ),
                 CalendarEvent.status != "cancelled",
             )
             if owner:
                 ev_q = owner_filter(ev_q, CalendarCal, owner, include_shared=_allow_null)
-            events = ev_q.all()
+            events = ev_q.order_by(CalendarEvent.dtstart).all()
-            events.sort(key=_daily_brief_local_start)
             # ----- Notes: pinned + non-archived todos with at least one undone item -----
             n_q = db.query(Note).filter(Note.archived == False)  # noqa: E712
             if owner:
@@ -2090,7 +2058,7 @@ async def action_daily_brief(owner: str, **kwargs) -> Tuple[str, bool]:
         if events:
             plain.append("Calendar:")
             for e in events:
-                t = _daily_brief_local_start(e).strftime("%H:%M") if not e.all_day else "all day"
+                t = e.dtstart.strftime("%H:%M") if not e.all_day else "all day"
                 loc = f" @ {e.location}" if e.location else ""
                 plain.append(f"  {t}  {e.summary}{loc}")
             plain.append("")

src/chat_handler.py

@@ -282,13 +282,7 @@ class ChatHandler:
                                     _sync_upload_vision_to_gallery(file_info, owner, vl_desc)
                                 except Exception:
                                     pass
-                        enhanced_message = f"{enhanced_message}\n\n[Image: {file_info['name']}]\n"
+                        enhanced_message = f"{enhanced_message}\n\n[Image: {file_info['name']}]\n{vl_desc}"
-                        if vl_desc:
-                            # A separate vision call wrote this, but the chat model sees
-                            # one message and answers the prose as if the user wrote it
-                            # (#5573). Label it below the marker line — the client strips
-                            # the block by matching `[Image: <name>]\n`.
-                            enhanced_message += f"[Image description — context only, not part of the user's message]:\n{vl_desc}"
                         # Surface the description to the client live so it renders as a
                         # collapsible "image description" on the user bubble (not just
                         # after a refresh that re-parses the stored message).

src/document_processor.py

@@ -142,10 +142,7 @@ def _process_pdf(
                         with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as tmp:
                             temp_img_path = tmp.name
                         try:
-                            image = img.image
+                            img.image.save(temp_img_path, "PNG")  # pypdf -> PIL image
-                            if image.mode == "CMYK":
-                                image = image.convert("RGB")
-                            image.save(temp_img_path, "PNG")
                             ocr_text = analyze_image_with_vl(temp_img_path, owner=owner)
                             if ocr_text and "unavailable" not in ocr_text.lower():
                                 pdf_text += f"\n\n[Page {page_num + 1} image {img_index + 1} text]: {ocr_text}"

src/service_health.py

@@ -76,23 +76,9 @@ _ERROR_DETAIL = {
     "auth_or_protocol_error": "authentication or protocol error",
     "no_models": "endpoint returned no models",
     "no_host": "no host configured",
-    "config_source_error": "configuration source could not be read",
     "error": "probe failed",
 }
 
-# Config/inventory source behind each network subsystem. `_gather_inputs()`
-# fails soft, so a source that could not be read hands its probe an empty
-# inventory — indistinguishable from "nothing configured", which every probe
-# answers with `disabled`. The collector therefore reports the source failure
-# instead of running a probe whose verdict would be a lie.
-CONFIG_SOURCE_ERROR = "config_source_error"
-_SUBSYSTEM_SOURCE = {
-    "searxng": "settings",
-    "ntfy": "integrations",
-    "email": "accounts",
-    "providers": "endpoints",
-}
-
 
 def _svc(name: str, status: str, detail: str, **meta: Any) -> Dict[str, Any]:
     return {"name": name, "status": status, "detail": detail, "meta": dict(meta)}
@@ -425,33 +411,26 @@ def _gather_inputs() -> Dict[str, Any]:
     """Pull live config/account/endpoint lists from the app's data sources.
 
     Each lookup fails soft: a broken source yields an empty/neutral value so a
-    single failure can't take down the whole health report. The failure is also
+    single failure can't take down the whole health report.
-    *recorded* under `failed` (source -> controlled category), because the empty
-    value alone cannot be told apart from a source that loaded and is genuinely
-    empty — and the probes read empty as `disabled`.
     """
     settings: Dict[str, Any] = {}
     integrations: List[Dict[str, Any]] = []
     accounts: List[Dict[str, Any]] = []
     endpoints: List[Dict[str, Any]] = []
-    failed: Dict[str, str] = {}
     try:
         from src.settings import load_settings
         settings = load_settings() or {}
     except Exception as e:
-        failed["settings"] = _classify_error(e)
         logger.debug(f"service_health: settings load failed: {e}")
     try:
         from src.integrations import load_integrations
         integrations = load_integrations() or []
     except Exception as e:
-        failed["integrations"] = _classify_error(e)
         logger.debug(f"service_health: integrations load failed: {e}")
     try:
         from routes.email_helpers import _list_email_accounts
         accounts = _list_email_accounts() or []
     except Exception as e:
-        failed["accounts"] = _classify_error(e)
         logger.debug(f"service_health: email accounts load failed: {e}")
     try:
         from core.database import SessionLocal, ModelEndpoint
@@ -464,10 +443,9 @@ def _gather_inputs() -> Dict[str, Any]:
         finally:
             db.close()
     except Exception as e:
-        failed["endpoints"] = _classify_error(e)
         logger.debug(f"service_health: endpoint load failed: {e}")
     return {"settings": settings, "integrations": integrations,
-            "accounts": accounts, "endpoints": endpoints, "failed": failed}
+            "accounts": accounts, "endpoints": endpoints}
 
 
 async def _run_subsystem(name: str, fn: Callable, *args: Any) -> Dict[str, Any]:
@@ -486,24 +464,6 @@ async def _run_subsystem(name: str, fn: Callable, *args: Any) -> Dict[str, Any]:
         return _svc(name, DOWN, _detail_for(category), error=category)
 
 
-async def _source_unavailable(name: str, source: str,
-                              category: str) -> Dict[str, Any]:
-    """Controlled entry for a subsystem whose config source could not be read.
-
-    Deliberately not `disabled`: the configured state is *unknown*, not known to
-    be off. `degraded` rather than `down` because the failure is in reading the
-    inventory, not a probe that reached the subsystem and failed — but it still
-    carries non-zero severity, so a report containing one can never roll up to
-    `ok`. `meta` names the source and the controlled category of the underlying
-    exception; never its text.
-    """
-    return _svc(name, DEGRADED,
-                f"Could not read configuration "
-                f"({_detail_for(CONFIG_SOURCE_ERROR)}).",
-                error=CONFIG_SOURCE_ERROR, source=source,
-                source_error=category)
-
-
 async def collect_service_health(rag_manager: Any = None,
                                  memory_vector: Any = None) -> Dict[str, Any]:
     """Run every probe and return {overall, services, timestamp}.
@@ -512,10 +472,6 @@ async def collect_service_health(rag_manager: Any = None,
     four network subsystems run concurrently, each under `_SUBSYSTEM_DEADLINE`,
     with an overall `_AGGREGATE_DEADLINE` backstop. Per-item probes inside
     providers/email are themselves bounded by `_FANOUT_BUDGET`.
-
-    A subsystem whose config/inventory source failed to load is reported via
-    `_source_unavailable()` instead of being probed with an empty inventory,
-    which every probe would otherwise report as `disabled`.
     """
     from datetime import datetime, timezone
 
@@ -526,23 +482,12 @@ async def collect_service_health(rag_manager: Any = None,
     chroma = chromadb_health(rag_manager, memory_vector)
 
     names = ["searxng", "ntfy", "email", "providers"]
-    probes = {
+    coros = [
-        "searxng": (searxng_health, (settings,)),
+        _run_subsystem("searxng", searxng_health, settings),
-        "ntfy": (ntfy_health, (inputs["integrations"], settings)),
+        _run_subsystem("ntfy", ntfy_health, inputs["integrations"], settings),
-        "email": (email_health, (inputs["accounts"],)),
+        _run_subsystem("email", email_health, inputs["accounts"]),
-        "providers": (providers_health, (inputs["endpoints"],)),
+        _run_subsystem("providers", providers_health, inputs["endpoints"]),
-    }
+    ]
-    # A subsystem whose inventory could not be read is reported as such. The
-    # others are still probed normally — one broken source degrades one entry.
-    failed = inputs.get("failed") or {}
-    coros = []
-    for name in names:
-        source = _SUBSYSTEM_SOURCE[name]
-        if source in failed:
-            coros.append(_source_unavailable(name, source, failed[source]))
-        else:
-            fn, args = probes[name]
-            coros.append(_run_subsystem(name, fn, *args))
     try:
         results = await asyncio.wait_for(asyncio.gather(*coros),
                                          timeout=_AGGREGATE_DEADLINE)

src/session_search.py

@@ -57,17 +57,8 @@ def _message_to_context(msg: DBChatMessage) -> dict[str, Any]:
     }
 
 
-def escape_like_pattern(value: str) -> str:
-    """Escape SQL LIKE wildcards (``%``, ``_``) and the escape char itself.
-
-    Public shared helper for building ``ilike(f"%{...}%", escape="\\\\")``
-    patterns from user input. Must escape backslash first.
-    """
-    return value.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_")
-
-
 def _escape_like(value: str) -> str:
-    return escape_like_pattern(value)
+    return value.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_")
 
 
 def _snippet(content: str, query: str, radius: int = 60) -> str:
@@ -76,34 +67,15 @@ def _snippet(content: str, query: str, radius: int = 60) -> str:
     if not query:
         return content[: radius * 2]
 
-    match_start = -1
+    idx = content.lower().find(query.lower())
-    match_length = 0
+    if idx == -1:
-    lowered_content = content.lower()
-    for candidate in _query_terms(query):
-        idx = lowered_content.find(candidate.lower())
-        if idx != -1 and (match_start == -1 or idx < match_start):
-            match_start = idx
-            match_length = len(candidate)
-
-    if match_start == -1:
         return content[: radius * 2]
 
-    start = max(0, match_start - radius)
+    start = max(0, idx - radius)
-    end = min(len(content), match_start + match_length + radius)
+    end = min(len(content), idx + len(query) + radius)
     return ("..." if start > 0 else "") + content[start:end] + ("..." if end < len(content) else "")
 
 
-def _query_terms(query: str) -> list[str]:
-    """Return meaningful quoted phrases and tokens in user-entered order."""
-    terms: list[str] = []
-    for match in re.finditer(r'"([^"]+)"|[\w][\w._-]*', query, flags=re.UNICODE):
-        term = match.group(1) if match.group(1) is not None else match.group(0).strip("._-")
-        term = term.strip()
-        if term:
-            terms.append(term)
-    return terms
-
-
 def _sanitize_fts_query(query: str) -> str | None:
     """Convert free text into a conservative FTS5 MATCH query.
 

static/js/chat.js

@@ -336,9 +336,6 @@ import { invalidateSettings } from './appConfig.js';
   let _sendInFlight = false;   // covers the window from click → streaming start
   let _displayOverride = null; // Override visible user bubble text (hides injected prompts)
   let _hideUserBubble = false; // Skip user bubble entirely (e.g. continue after stop)
-  // The user bubble a regenerate keeps on screen. Its resubmitted message is
-  // a new DB row, so the saved id is attached here.
-  let _regenKeptUserBubble = null;
   let _contextHeaderSeq = 0;
   let _contextHeaderData = null;
   let _contextHeaderBound = false;
@@ -4998,15 +4995,6 @@ import { invalidateSettings } from './appConfig.js';
                   refreshChatContextHeader('metrics');
                 }
 
-              } else if (json.type === 'user_message_saved') {
-                // The user bubble gets its DB id too, so regenerating or
-                // editing it later cuts the chat by id, not page position.
-                if (!_isBg && json.id) {
-                  if (_userMsgEl) _userMsgEl.dataset.dbId = json.id;
-                  else if (_regenKeptUserBubble) _regenKeptUserBubble.dataset.dbId = json.id;
-                  _regenKeptUserBubble = null;
-                }
-
               } else if (json.type === 'message_saved') {
                 // Wire the persisted DB id onto the just-streamed bubble so it
                 // can be edited/deleted immediately, without reloading the chat.
@@ -7248,22 +7236,6 @@ import { invalidateSettings } from './appConfig.js';
   /**
    * Edit a user message: show an input, truncate to before it, resubmit the edited text.
    */
-  // Recover attached file IDs from rendered user bubbles, including older
-  // image previews that were rendered before data-file-id was stamped.
-  function _userMessageAttachmentIds(msgElement) {
-    if (!msgElement) return [];
-    const els = msgElement.querySelectorAll('[data-file-id]');
-    const ids = Array.from(els).map(el => el.dataset.fileId).filter(Boolean);
-    if (!ids.length) {
-      const images = msgElement.querySelectorAll('.attach-image-preview img, .attach-card img');
-      for (const image of images) {
-        const match = (image.getAttribute('src') || '').match(/\/api\/upload\/([A-Za-z0-9_\-]+)/);
-        if (match && match[1] && !ids.includes(match[1])) ids.push(match[1]);
-      }
-    }
-    return ids;
-  }
-
   export async function editUserMessage(userMsgElement) {
     const box = document.getElementById('chat-history');
     const allMsgs = Array.from(box.querySelectorAll('.msg'));
@@ -7311,49 +7283,23 @@ import { invalidateSettings } from './appConfig.js';
       e.stopPropagation();
       const newText = editor.value.trim();
       if (!newText) return;
-      const editAttachmentIds = _userMessageAttachmentIds(userMsgElement);
 
       const sessionId = sessionModule.getCurrentSessionId();
       if (!sessionId) return;
 
-      // Everything after the original reply to this message would also be
-      // destroyed. Cancelling leaves the editor open with the draft intact.
-      const extraCount = allMsgs.length - msgIndex - 2;
-      const choice = await _confirmTruncateIfDestructive(extraCount, 'edit');
-      if (!choice) return;
-      if (choice === 'fork') {
-        // Branch just before this user turn and send the edit there; this
-        // chat keeps the original message and everything after it.
-        try {
-          await _forkAndSend(msgIndex, userMsgElement.dataset.dbId || '', newText, editAttachmentIds);
-          bodyEl.innerHTML = originalHTML;
-        } catch (err) {
-          console.error('Fork failed:', err);
-          if (uiModule) uiModule.showError('Fork failed: ' + err.message);
-        }
-        return;
-      }
-
       const keepCount = msgIndex;
-      // Cut at the message's database id: msgIndex counts only the messages
-      // loaded in the page, so it is too small when older history has not
-      // been scrolled in yet.
-      const editBeforeId = userMsgElement.dataset.dbId || '';
       try {
-        const editTruncate = await fetch(`${API_BASE}/api/session/${sessionId}/truncate`, {
+        await fetch(`${API_BASE}/api/session/${sessionId}/truncate`, {
           method: 'POST',
           headers: { 'Content-Type': 'application/json' },
-          body: JSON.stringify(editBeforeId ? { before_msg_id: editBeforeId } : { keep_count: keepCount })
+          body: JSON.stringify({ keep_count: keepCount })
         });
-        if (!editTruncate.ok) throw new Error('Server error ' + editTruncate.status);
 
         // Remove DOM elements from msgIndex onward
         for (let i = allMsgs.length - 1; i >= msgIndex; i--) {
           allMsgs[i].remove();
         }
 
-        // The edited user turn still refers to its original attachments.
-        _pendingRegenAttachments = editAttachmentIds;
         // Submit the edited text
         const messageInput = uiModule.el('message');
         messageInput.value = newText;
@@ -7377,59 +7323,6 @@ import { invalidateSettings } from './appConfig.js';
     });
   }
 
-  // Regenerate, resend and edit permanently delete (server-side truncate)
-  // everything after the point clicked. Ask first unless nothing comes after
-  // it (extraCount 0), offering a fork that leaves this chat untouched.
-  // Resolves to 'proceed', 'fork', or null (cancelled).
-  const _TRUNCATE_ACTIONS = {
-    regenerate: { lead: 'Regenerating here', confirmText: 'Delete and regenerate' },
-    resend: { lead: 'Resending this message', confirmText: 'Delete and resend' },
-    edit: { lead: 'Sending this edit', confirmText: 'Delete and send' },
-  };
-  async function _confirmTruncateIfDestructive(extraCount, action = 'regenerate') {
-    if (extraCount <= 0) return 'proceed';
-    const { lead, confirmText } = _TRUNCATE_ACTIONS[action] || _TRUNCATE_ACTIONS.regenerate;
-    const result = await uiModule.styledConfirm(
-      `${lead} will also permanently delete the ${extraCount} ` +
-      `message${extraCount === 1 ? '' : 's'} after it. This can't be undone. ` +
-      `Fork from here keeps this chat as it is and continues in a new one instead.`,
-      { confirmText, alternateText: 'Fork from here', cancelText: 'Cancel', danger: true }
-    );
-    if (result === 'alternate') return 'fork';
-    return result ? 'proceed' : null;
-  }
-
-  // Copy the first `keepCount` messages of the current chat into a new chat
-  // and switch to it. Returns the new session id; throws on failure so callers
-  // that replay an action in the fork can stop before sending anything.
-  // Fork by message id when the element has one (before it, or through it);
-  // keepCount is only a fallback, since it counts loaded messages only.
-  async function _forkSessionAt(keepCount, beforeMsgId = '', throughMsgId = '') {
-    const sessionId = sessionModule.getCurrentSessionId();
-    if (!sessionId) throw new Error('No active chat');
-    const res = await fetch(`${API_BASE}/api/session/${sessionId}/fork`, {
-      method: 'POST',
-      headers: { 'Content-Type': 'application/json' },
-      body: JSON.stringify({ keep_count: keepCount,
-        ...(beforeMsgId ? { before_msg_id: beforeMsgId } : throughMsgId ? { through_msg_id: throughMsgId } : {}) }),
-    });
-    if (!res.ok) throw new Error(await res.text());
-    const data = await res.json();
-    await sessionModule.loadSessions();
-    await sessionModule.selectSession(data.id);
-    if (uiModule) uiModule.showToast(`Forked → ${data.name}`);
-    return data.id;
-  }
-
-  // Fork before a user message and send `text` there; this chat is untouched.
-  // `attachments` (if given) are re-sent only once the fork has succeeded.
-  async function _forkAndSend(keepCount, beforeMsgId, text, attachments) {
-    await _forkSessionAt(keepCount, beforeMsgId);
-    if (attachments !== undefined) _pendingRegenAttachments = attachments;
-    uiModule.el('message').value = text;
-    document.querySelector('.send-btn')?.click();
-  }
-
   /**
    * Resend a user message. By default this replaces from the selected user turn
    * so failed attempts do not remain in model context or SFT traces. Callers can
@@ -7451,7 +7344,18 @@ import { invalidateSettings } from './appConfig.js';
     let text = (userMsgElement.dataset.raw || (bodyEl ? bodyEl.textContent : '') || '').trim();
     text = text.replace(/\s*\[\d+ attachment\(s\)\]$/, '');
 
-    const _ids = _userMessageAttachmentIds(userMsgElement);
+    // Collect file_ids attached to this user message so the resend re-carries
+    // the photos / docs (and the chat handler picks up the user-edited OCR
+    // text cached server-side under those file ids).
+    const _attachEls = userMsgElement.querySelectorAll('[data-file-id]');
+    let _ids = Array.from(_attachEls).map(el => el.dataset.fileId).filter(Boolean);
+    if (!_ids.length) {
+      const _imgs = userMsgElement.querySelectorAll('.attach-image-preview img, .attach-card img');
+      for (const _im of _imgs) {
+        const _m = (_im.getAttribute('src') || '').match(/\/api\/upload\/([A-Za-z0-9_\-]+)/);
+        if (_m && _m[1] && !_ids.includes(_m[1])) _ids.push(_m[1]);
+      }
+    }
 
     // Rescue: legacy bubbles may have stored the filename as the message
     // content (artifact of earlier broken resends). Don't re-send that as
@@ -7474,18 +7378,6 @@ import { invalidateSettings } from './appConfig.js';
 
     try {
       if (replaceFromHere) {
-        // Everything strictly after the immediate AI reply to this user
-        // message would also be destroyed — that's the part a click on
-        // Resend / "Regenerate message" doesn't expect to lose.
-        const extraCount = allMsgs.length - msgIndex - 2;
-        const choice = await _confirmTruncateIfDestructive(extraCount, 'resend');
-        if (!choice) return;
-        if (choice === 'fork') {
-          // Branch just before this user turn and send it again there; this
-          // chat keeps every message.
-          await _forkAndSend(msgIndex, userMsgElement.dataset.dbId || '', text, _ids);
-          return;
-        }
         // Resend/regenerate trims history to this point before resubmitting so
         // the replacement request is the only copy the backend sees.
         const keepCount = msgIndex;
@@ -7550,14 +7442,25 @@ import { invalidateSettings } from './appConfig.js';
       return;
     }
 
-    // Everything strictly after the AI reply being regenerated would also
+    // Collect any file_ids attached to the original user message so the
-    // be destroyed — that's the part a click on "Regenerate from here"
+    // regenerated send re-uses them. Without this the AI is regenerated on
-    // doesn't expect to lose.
+    // text alone — photos (and the user-edited OCR text cached server-side
-    const extraCount = allMsgs.length - aiIndex - 1;
+    // under that file_id) would be silently dropped.
-    const choice = await _confirmTruncateIfDestructive(extraCount, 'regenerate');
+    const _attachEls = userMsgEl ? userMsgEl.querySelectorAll('[data-file-id]') : [];
-    if (!choice) return;
+    let _regenIds = Array.from(_attachEls).map(el => el.dataset.fileId).filter(Boolean);
-
+    // Fallback for bubbles rendered before the data-file-id stamp landed:
-    const _regenIds = _userMessageAttachmentIds(userMsgEl);
+    // sniff the file id straight out of any `.attach-image-preview img`
+    // src URLs (matches /api/upload/<id>). Otherwise an older bubble would
+    // regen with zero attachments and the photo would be lost from the
+    // resulting message even though the file still exists on disk.
+    if (!_regenIds.length && userMsgEl) {
+      const _imgs = userMsgEl.querySelectorAll('.attach-image-preview img, .attach-card img');
+      for (const _im of _imgs) {
+        const _m = (_im.getAttribute('src') || '').match(/\/api\/upload\/([A-Za-z0-9_\-]+)/);
+        if (_m && _m[1] && !_regenIds.includes(_m[1])) _regenIds.push(_m[1]);
+      }
+    }
+    _pendingRegenAttachments = _regenIds;
 
     // Rescue: earlier-version regens (before the dataset.raw fix) stored the
     // photo's filename as the user-message content. On a follow-up regen,
@@ -7566,7 +7469,7 @@ import { invalidateSettings } from './appConfig.js';
     // an image file". If userText is just a bare image filename and we have
     // attachments, drop it so the OCR text (or the image bytes for vision
     // models) is what the model actually sees.
-    if (userText && _regenIds.length &&
+    if (userText && _pendingRegenAttachments.length &&
         /^[^\n\r]{1,200}\.(png|jpe?g|gif|webp|svg|bmp|heic|heif)$/i.test(userText.trim())) {
       userText = '';
     }
@@ -7574,7 +7477,7 @@ import { invalidateSettings } from './appConfig.js';
     // A photo-only message has empty user text — regen must still proceed,
     // because the attachments themselves are the message. Bail only if there
     // is no text AND no attachments to send.
-    if (!userText && !_regenIds.length) {
+    if (!userText && !_pendingRegenAttachments.length) {
       if (uiModule) uiModule.showError('Nothing to regenerate — the user message has no text and no attachments');
       return;
     }
@@ -7582,20 +7485,6 @@ import { invalidateSettings } from './appConfig.js';
     const sessionId = sessionModule.getCurrentSessionId();
     if (!sessionId) return;
 
-    if (choice === 'fork') {
-      // Branch just before the user turn and send it again there, so the new
-      // chat gets a fresh reply to the same message; this chat keeps every
-      // message. No variants or hidden bubble: the fork starts without them.
-      try {
-        await _forkAndSend(userIndex, (userMsgEl && userMsgEl.dataset.dbId) || '', userText, _regenIds);
-      } catch (err) {
-        if (_pendingRegenAttachments === _regenIds) _pendingRegenAttachments = null;
-        console.error('Fork failed:', err);
-        if (uiModule) uiModule.showError('Fork failed: ' + err.message);
-      }
-      return;
-    }
-
     // Save current response as a variant
     const oldRaw = aiMsgElement.dataset.raw || aiMsgElement.querySelector('.body')?.textContent || '';
     const oldHtml = aiMsgElement.querySelector('.body')?.innerHTML || '';
@@ -7607,19 +7496,13 @@ import { invalidateSettings } from './appConfig.js';
     }
 
     const keepCount = userIndex;
-    // Same as resend: cut at the user message's database id, because
-    // userIndex counts only the messages loaded in the page.
-    const regenBeforeId = (userMsgEl && userMsgEl.dataset.dbId) || '';
 
     try {
-      const regenTruncate = await fetch(`${API_BASE}/api/session/${sessionId}/truncate`, {
+      await fetch(`${API_BASE}/api/session/${sessionId}/truncate`, {
         method: 'POST',
         headers: { 'Content-Type': 'application/json' },
-        body: JSON.stringify(regenBeforeId ? { before_msg_id: regenBeforeId } : { keep_count: keepCount })
+        body: JSON.stringify({ keep_count: keepCount })
       });
-      // A refused cut (e.g. a stale id) must not stack a second reply.
-      if (!regenTruncate.ok) throw new Error('Server error ' + regenTruncate.status);
-      _pendingRegenAttachments = _regenIds;
 
       // Keep the original user bubble, but remove every rendered trace after
       // it, including agent-thread tool history between the user and AI bubble.
@@ -7636,14 +7519,12 @@ import { invalidateSettings } from './appConfig.js';
       _pendingVariantLabel = 'regen';
 
       _hideUserBubble = true;
-      _regenKeptUserBubble = userMsgEl;
       const messageInput = uiModule.el('message');
       messageInput.value = userText;
       const submitBtn = document.querySelector('.send-btn');
       if (submitBtn) submitBtn.click();
 
     } catch (err) {
-      if (_pendingRegenAttachments === _regenIds) _pendingRegenAttachments = null;
       console.error('Regenerate failed:', err);
       if (uiModule) uiModule.showError('Regenerate failed: ' + err.message);
     }
@@ -7655,8 +7536,6 @@ import { invalidateSettings } from './appConfig.js';
   // File-ids carried over from the original user message during a regen, so
   // photos / OCR overrides survive into the new send. Consumed once.
   let _pendingRegenAttachments = null;
-  // Read-only view for tests.
-  export function _pendingRegenAttachmentIds() { return _pendingRegenAttachments; }
 
   /**
    * Called after streaming completes to attach variant navigation if this was a regen.
@@ -7796,8 +7675,20 @@ import { invalidateSettings } from './appConfig.js';
     const sessionId = sessionModule.getCurrentSessionId();
     if (!sessionId) return;
 
+    const keepCount = aiIndex + 1;
+
     try {
-      await _forkSessionAt(aiIndex + 1, '', aiMsgElement.dataset.dbId || '');
+      const res = await fetch(`${API_BASE}/api/session/${sessionId}/fork`, {
+        method: 'POST',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify({ keep_count: keepCount }),
+      });
+      if (!res.ok) throw new Error(await res.text());
+      const data = await res.json();
+
+      await sessionModule.loadSessions();
+      await sessionModule.selectSession(data.id);
+      if (uiModule) uiModule.showToast(`Forked → ${data.name}`);
     } catch (err) {
       console.error('Fork failed:', err);
       if (uiModule) uiModule.showError('Fork failed: ' + err.message);

tests/test_agent_render_ownership.py

@@ -10,7 +10,7 @@ import unittest
 
 
 path = Path(__file__).resolve().parents[1] / "routes/chat_routes.py"
-tree = ast.parse(path.read_text(encoding="utf-8"))
+tree = ast.parse(path.read_text())
 node = next(n for n in tree.body if isinstance(n, ast.ClassDef) and n.name == "_AgentRenderState")
 namespace = {}
 exec(compile(ast.Module(body=[node], type_ignores=[]), str(path), "exec"), namespace)

tests/test_agent_unknown_context_budget.py

@@ -1,71 +0,0 @@
-"""An unknown context window must not be budgeted like a tiny local server (#6678).
-
-``budget_context_for_model`` returns 0 when the endpoint does not prove its
-window, and ``compute_input_token_budget`` answers 0 with the conservative
-default budget. The agent loop's small-server clamp (``<= 8192``) also caught
-0 and cut the request to 1200 tokens, so an open document or earlier context
-of a few thousand tokens was trimmed away before the model saw it.
-"""
-import inspect
-import json
-
-import pytest
-
-DONE = 'data: [DONE]\n\n'
-MARKER = 'NIGHTJAR-7'
-# ~3000 estimated tokens: over the old 1200 clamp, under the 6000 default.
-CONTEXT = ''.join(
-    f'## Project-{n}\nOwner: team {n}. Status: active. Notes: routine maintenance '
-    'and quarterly review scheduled for every workstream in this registry.\n\n'
-    for n in range(60)
-) + f'## Project-Alpha\nAlias: {MARKER}\n'
-
-
-def _event(payload):
-    return 'data: ' + json.dumps(payload) + '\n\n'
-
-
-async def _first_request(monkeypatch, tmp_path, context_window):
-    import src.agent_loop as al
-    from tests.test_agent_runtime_context import _patch_fake_skills
-    _patch_fake_skills(monkeypatch)
-    monkeypatch.setattr('src.tool_index.get_tool_index', lambda: None)
-    monkeypatch.setattr('src.model_context.budget_context_for_model',
-                        lambda *args, **kwargs: context_window)
-    seen = []
-
-    async def provider(candidates, messages, **kwargs):
-        # Like llm_core: the per-candidate factory shapes and trims the request.
-        url, model, headers = candidates[0][:3]
-        request = kwargs['candidate_request_factory'](0, url, model, headers)
-        if inspect.isawaitable(request):
-            request = await request
-        seen.append((request or {}).get('messages', messages))
-        yield _event({'delta': 'ok'})
-        yield DONE
-
-    monkeypatch.setattr(al, 'stream_llm_with_fallback', provider)
-    history = [
-        {'role': 'user', 'content': 'Keep this registry for later:\n\n' + CONTEXT},
-        {'role': 'assistant', 'content': 'Saved.'},
-        {'role': 'user', 'content': 'What is the alias of Project-Alpha?'},
-    ]
-    async for _ in al.stream_agent_loop('http://127.0.0.1:9/v1', 'model', history,
-                                        max_rounds=1, workspace=str(tmp_path)):
-        pass
-    assert seen, 'the provider was never called'
-    return json.dumps(seen[0])
-
-
-@pytest.mark.asyncio
-async def test_unknown_context_window_keeps_earlier_context(monkeypatch, tmp_path):
-    request = await _first_request(monkeypatch, tmp_path, 0)
-    assert MARKER in request
-
-
-@pytest.mark.asyncio
-async def test_known_small_window_is_still_clamped(monkeypatch, tmp_path):
-    # The clamp exists for small local servers whose window is known (n_ctx
-    # 2048 here); it must keep protecting them.
-    request = await _first_request(monkeypatch, tmp_path, 2048)
-    assert MARKER not in request

tests/test_background_chat_completion_ui_static.py

@@ -3,8 +3,8 @@ from tests.helpers.stylesheets import app_css
 
 
 ROOT = Path(__file__).resolve().parents[1]
-CHAT = (ROOT / "static/js/chat.js").read_text(encoding="utf-8")
+CHAT = (ROOT / "static/js/chat.js").read_text()
-SESSIONS = (ROOT / "static/js/sessions.js").read_text(encoding="utf-8")
+SESSIONS = (ROOT / "static/js/sessions.js").read_text()
 CSS = app_css()
 
 

tests/test_chat_ttft_timer_static.py

@@ -2,8 +2,8 @@ from pathlib import Path
 
 
 ROOT = Path(__file__).resolve().parents[1]
-CHAT = (ROOT / "static/js/chat.js").read_text(encoding="utf-8")
+CHAT = (ROOT / "static/js/chat.js").read_text()
-RENDERER = (ROOT / "static/js/chatRenderer.js").read_text(encoding="utf-8")
+RENDERER = (ROOT / "static/js/chatRenderer.js").read_text()
 
 
 def test_processing_indicator_shows_live_ttft_timer():

tests/test_compose_env_defaults.py

@@ -1,28 +0,0 @@
-"""Every variable a shipped compose file forwards must carry a default.
-
-A bare ``${VAR}`` makes ``docker compose`` print "variable is not set" on every
-command for a default ``.env`` (#6619), which greets fresh installs with a
-warning that looks like a misconfiguration.
-"""
-
-import re
-from pathlib import Path
-
-import pytest
-
-ROOT = Path(__file__).resolve().parents[1]
-COMPOSE_FILES = sorted(ROOT.glob("docker-compose*.yml")) + sorted((ROOT / "docker").glob("*.yml"))
-
-# ${VAR} with no ``:-``/``-``/``:?``/``?`` modifier.
-BARE_VAR = re.compile(r"\$\{([A-Za-z_][A-Za-z0-9_]*)\}")
-
-
-@pytest.mark.parametrize("path", COMPOSE_FILES, ids=lambda p: p.relative_to(ROOT).as_posix())
-def test_compose_variables_have_defaults(path):
-    bare = [
-        f"{path.name}:{lineno}: ${{{name}}}"
-        for lineno, line in enumerate(path.read_text(encoding="utf-8").splitlines(), 1)
-        if not line.lstrip().startswith("#")
-        for name in BARE_VAR.findall(line)
-    ]
-    assert not bare, "compose variables without a default:\n" + "\n".join(bare)

tests/test_cookbook_error_feedback.py

@@ -70,63 +70,3 @@ def test_no_gguf_found_pattern():
     result = _diagnose_serve_output(out)
     assert result is not None
     assert "GGUF" in result["message"]
-
-
-def test_cookbook_routes_uses_shared_diagnosis_helper():
-    # /api/cookbook/tasks/status must use the maintained helper. A nested copy in
-    # cookbook_routes.py shadowed the import and silently drifted (missing the
-    # ModelOpt, mflux and MLX bridge diagnoses).
-    import ast
-    from pathlib import Path
-
-    source = (Path(__file__).resolve().parents[1] / "routes" / "cookbook_routes.py").read_text(encoding="utf-8")
-    local_defs = [
-        node.lineno
-        for node in ast.walk(ast.parse(source))
-        if isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef)) and node.name == "_diagnose_serve_output"
-    ]
-    assert local_defs == []
-
-
-def test_modelopt_lm_head_checkpoint_returns_diagnosis():
-    out = "ValueError: There is no module or parameter named 'lm_head.input_scale' in Qwen3ForCausalLM"
-    result = _diagnose_serve_output(out)
-    assert result is not None
-    assert "ModelOpt" in result["message"]
-
-
-def test_nvidia_driver_too_old_for_torch_returns_diagnosis():
-    # vLLM 0.31 from PyPI ships torch cu130; on driver 570 (CUDA 12.8) the engine dies here.
-    out = (
-        "(EngineCore pid=1) ERROR [core.py:1433]     self.driver_worker.init_device()\n"
-        "(EngineCore pid=1) ERROR [core.py:1433] RuntimeError: The NVIDIA driver on your system is too old "
-        "(found version 12080). Please update your GPU driver by downloading and installing a new version\n"
-        "Traceback (most recent call last):\n"
-        "RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {}\n"
-    )
-    result = _diagnose_serve_output(out)
-    assert result is not None
-    assert "driver" in result["message"].lower()
-    assert any("cu129" in s["label"] for s in result["suggestions"])
-
-
-def test_cuda_runtime_newer_than_driver_returns_diagnosis():
-    # torch switched to cu128 but the vLLM wheel's own kernels still need CUDA 13.
-    out = (
-        "RuntimeError: get_cuda_view_from_cpu_tensor, /workspace/csrc/libtorch_stable/cuda_view.cu:38, "
-        "cudaHostGetDevicePointer failed: CUDA driver version is insufficient for CUDA runtime version\n"
-        "Traceback (most recent call last):\n"
-    )
-    result = _diagnose_serve_output(out)
-    assert result is not None
-    assert "driver" in result["message"].lower()
-
-
-def test_tasks_status_capture_joins_wrapped_tmux_lines():
-    # tmux wraps at the pane width (often mid-word), which hid errors like
-    # "insufficie|nt for CUDA runtime version" from the diagnosis patterns.
-    from pathlib import Path
-
-    source = (Path(__file__).resolve().parents[1] / "routes" / "cookbook_routes.py").read_text(encoding="utf-8")
-    assert '_remote_tmux_command("capture-pane", "-t", session_id, "-p", "-J", "-S", "-500")' in source
-    assert '["tmux", "capture-pane", "-t", session_id, "-p", "-J", "-S", "-500"]' in source

tests/test_cookbook_hf_gguf_files.py

@@ -1,62 +0,0 @@
-import pytest
-import httpx
-from unittest.mock import patch, AsyncMock
-from fastapi import FastAPI
-from fastapi.testclient import TestClient
-
-from routes.cookbook_routes import setup_cookbook_routes
-from src.auth_helpers import require_user
-
-app = FastAPI()
-router = setup_cookbook_routes()
-app.include_router(router)
-app.dependency_overrides[require_user] = lambda: "test_user"
-
-client = TestClient(app)
-
-
-def test_hf_gguf_files_success():
-    mock_resp = httpx.Response(
-        200,
-        json={
-            "siblings": [
-                {"rfilename": "model-q4_k_m.gguf"},
-                {"rfilename": "model-q8_0.gguf"},
-                {"rfilename": "README.md"},
-            ]
-        },
-        request=httpx.Request("GET", "https://huggingface.co/api/models/TheBloke/Llama-2-7B-GGUF"),
-    )
-
-    with patch("httpx.AsyncClient.get", new_callable=AsyncMock, return_value=mock_resp):
-        response = client.get("/api/cookbook/hf-gguf-files?repo_id=TheBloke/Llama-2-7B-GGUF")
-        assert response.status_code == 200
-        data = response.json()
-        assert data["ok"] is True
-        assert data["repo_id"] == "TheBloke/Llama-2-7B-GGUF"
-        assert data["files"] == ["model-q4_k_m.gguf", "model-q8_0.gguf"]
-
-
-def test_hf_gguf_files_http_error():
-    mock_resp = httpx.Response(
-        404,
-        json={"error": "Model not found"},
-        request=httpx.Request("GET", "https://huggingface.co/api/models/invalid/repo"),
-    )
-
-    with patch("httpx.AsyncClient.get", new_callable=AsyncMock, return_value=mock_resp):
-        response = client.get("/api/cookbook/hf-gguf-files?repo_id=invalid/repo")
-        assert response.status_code == 200
-        data = response.json()
-        assert data["ok"] is False
-        assert "HF API HTTP 404" in data["error"]
-
-
-def test_hf_gguf_files_exception_handling():
-    with patch("httpx.AsyncClient.get", new_callable=AsyncMock, side_effect=httpx.ConnectError("Network unreachable")):
-        response = client.get("/api/cookbook/hf-gguf-files?repo_id=TheBloke/Llama-2-7B-GGUF")
-        # Should gracefully return JSON error payload, not raise NameError / 500
-        assert response.status_code == 200
-        data = response.json()
-        assert data["ok"] is False
-        assert data["error"] == "HF API request failed"

tests/test_daily_brief_local_calendar.py

@@ -1,103 +0,0 @@
-"""Daily brief must query and display each calendar storage kind in local time."""
-import asyncio
-import os
-import time
-from contextlib import contextmanager
-from datetime import datetime, timedelta, timezone
-from types import SimpleNamespace
-from zoneinfo import ZoneInfo
-
-import pytest
-from sqlalchemy import create_engine
-from sqlalchemy.orm import sessionmaker
-from sqlalchemy.pool import StaticPool
-
-from core import database
-from src import builtin_actions
-
-
-@contextmanager
-def system_timezone(name):
-    previous = os.environ.get('TZ')
-    os.environ['TZ'] = name
-    time.tzset()
-    try:
-        yield
-    finally:
-        if previous is None:
-            os.environ.pop('TZ', None)
-        else:
-            os.environ['TZ'] = previous
-        time.tzset()
-
-
-@pytest.mark.skipif(not hasattr(time, 'tzset'), reason='requires changing the process local timezone')
-@pytest.mark.parametrize('zone', ['Europe/Berlin', 'America/Los_Angeles'])
-def test_daily_brief_selects_local_day_and_orders_mixed_storage(monkeypatch, zone):
-    engine = create_engine('sqlite://', poolclass=StaticPool)
-    for model in [database.CalendarCal, database.CalendarEvent, database.Note]:
-        model.__table__.create(engine)
-    sessions = sessionmaker(bind=engine)
-    monkeypatch.setattr(database, 'SessionLocal', sessions)
-    from core.auth import AuthManager
-    monkeypatch.setattr(AuthManager, 'is_configured', property(lambda self: True))
-    from routes import email_helpers
-    def no_email(*args):
-        raise RuntimeError('No email account in this calendar-only test')
-    monkeypatch.setattr(email_helpers, '_imap_connect', no_email)
-    try:
-        with system_timezone(zone):
-            today = datetime.now().replace(hour=0, minute=0, second=0, microsecond=0)
-            def utc(value):
-                return value.astimezone(timezone.utc).replace(tzinfo=None)
-            with sessions() as db:
-                for owner in ['alice', 'bob', None]:
-                    db.add(database.CalendarCal(id=owner or 'shared', owner=owner, name=owner or 'shared'))
-                db.flush()
-                def add(uid, start, end, *, utc_row=False, all_day=False, owner='alice', status='confirmed'):
-                    db.add(database.CalendarEvent(uid=uid, calendar_id=owner or 'shared', summary=uid,
-                        dtstart=utc(start) if utc_row and not all_day else start,
-                        dtend=utc(end) if utc_row and not all_day else end,
-                        is_utc=utc_row, all_day=all_day, status=status))
-                add('early', today+timedelta(minutes=30), today+timedelta(hours=1), utc_row=True)
-                add('utc-ten', today+timedelta(hours=10), today+timedelta(hours=11), utc_row=True)
-                add('local-nine', today+timedelta(hours=9), today+timedelta(hours=10))
-                add('all-day', today, today+timedelta(days=1), utc_row=True, all_day=True)
-                add('next-day', today+timedelta(days=1,minutes=30), today+timedelta(days=1,hours=1), utc_row=True)
-                add('ended', today-timedelta(hours=1), today, utc_row=True)
-                add('cancelled', today+timedelta(hours=12), today+timedelta(hours=13), utc_row=True, status='cancelled')
-                add('foreign', today+timedelta(hours=12), today+timedelta(hours=13), utc_row=True, owner='bob')
-                add('unowned', today+timedelta(hours=12), today+timedelta(hours=13), owner=None)
-                db.commit()
-            text, success = asyncio.run(builtin_actions.action_daily_brief('alice'))
-            assert success, text
-            lines = ['all day  all-day', '00:30  early', '09:00  local-nine', '10:00  utc-ten']
-            assert all(line in text for line in lines), text
-            assert [text.index(line) for line in lines] == sorted(text.index(line) for line in lines), text
-            for excluded in ['next-day', 'ended', 'cancelled', 'foreign', 'unowned']:
-                assert excluded not in text, text
-    finally:
-        engine.dispose()
-
-
-@pytest.mark.parametrize('day, hours', [('2026-03-29', 23), ('2026-10-25', 25)])
-def test_utc_day_window_uses_offset_at_each_boundary(day, hours):
-    start = datetime.fromisoformat(day)
-    zone = ZoneInfo('Europe/Berlin')
-    begin = builtin_actions._daily_brief_utc_boundary(start, zone)
-    end = builtin_actions._daily_brief_utc_boundary(start+timedelta(days=1), zone)
-    assert end-begin == timedelta(hours=hours)
-    if hasattr(time, 'tzset'):
-        with system_timezone('Europe/Berlin'):
-            assert builtin_actions._daily_brief_utc_boundary(start) == begin
-            assert builtin_actions._daily_brief_utc_boundary(start+timedelta(days=1)) == end
-
-
-@pytest.mark.parametrize('utc_row, all_day, expected', [
-    (True, False, datetime(2026, 6, 1, 10)),
-    (False, False, datetime(2026, 6, 1, 8)),
-    (True, True, datetime(2026, 6, 1, 8)),
-])
-def test_local_start_preserves_floating_and_date_only_values(utc_row, all_day, expected):
-    event = SimpleNamespace(dtstart=datetime(2026,6,1,8), is_utc=utc_row, all_day=all_day)
-    assert builtin_actions._daily_brief_local_start(event, ZoneInfo('Europe/Berlin')) == expected

tests/test_default_chat_model_filter.py

@@ -1,86 +0,0 @@
-"""Issue #2137: never preselect an embedding or other non-chat model."""
-
-import json
-from types import SimpleNamespace
-
-import pytest
-from fastapi import FastAPI
-from fastapi.testclient import TestClient
-
-from core.database import ModelEndpoint
-from routes import model_routes, prefs_routes
-from tests.helpers.database import disposable_database
-
-
-@pytest.fixture
-def defaults_api(monkeypatch, tmp_path):
-    defaults = {}
-    with disposable_database(tmp_path) as factory:
-        monkeypatch.setattr(model_routes, "SessionLocal", factory)
-        monkeypatch.setattr(model_routes, "_load_settings", lambda: {})
-        monkeypatch.setattr(prefs_routes, "_load_for_user", lambda owner: defaults)
-        app = FastAPI()
-        app.state.auth_manager = SimpleNamespace(is_admin=lambda owner: False)
-
-        @app.middleware("http")
-        async def owner(request, call_next):
-            request.state.current_user = "alice"
-            return await call_next(request)
-
-        app.include_router(model_routes.setup_model_routes(model_discovery=None))
-        with TestClient(app) as client:
-            yield client, factory, defaults
-
-
-def _endpoint(factory, *, cached=(), pinned=(), hidden=(), owner="alice", endpoint_id="ep"):
-    with factory() as db:
-        db.add(ModelEndpoint(
-            id=endpoint_id, name="Fixture", base_url="http://model.invalid/v1", owner=owner,
-            is_enabled=True, cached_models=json.dumps(cached),
-            pinned_models=json.dumps(pinned), hidden_models=json.dumps(hidden),
-        ))
-        db.commit()
-
-
-@pytest.mark.parametrize("non_chat", [
-    "text-embedding-3-small", "nomic-embed-text:latest", "jina-reranker-v2-base",
-    "tts-1", "whisper-1", "gpt-image-1",
-])
-def test_automatic_default_skips_non_chat_models(defaults_api, non_chat):
-    client, factory, _ = defaults_api
-    _endpoint(factory, cached=[non_chat, "chat-model"])
-    assert client.get("/api/default-chat").json()["model"] == "chat-model"
-
-
-def test_non_chat_saved_default_falls_back_to_visible_pinned_chat(defaults_api):
-    client, factory, defaults = defaults_api
-    _endpoint(factory, cached=["text-embedding-3-small", "hidden-chat"],
-              pinned=["jina-reranker-v2-base", "pinned-chat"], hidden=["hidden-chat"])
-    defaults.update(default_endpoint_id="ep", default_model="text-embedding-3-small")
-    assert client.get("/api/default-chat").json()["model"] == "pinned-chat"
-
-
-def test_no_chat_candidate_leaves_model_empty(defaults_api):
-    client, factory, defaults = defaults_api
-    _endpoint(factory, cached=["text-embedding-3-small", "hidden-chat"],
-              pinned=["jina-reranker-v2-base"], hidden=["hidden-chat"])
-    defaults.update(default_endpoint_id="ep", default_model="text-embedding-3-small")
-    result = client.get("/api/default-chat").json()
-    assert result == {"endpoint_id": "ep", "endpoint_url": "http://model.invalid/v1/chat/completions", "model": ""}
-
-
-def test_valid_explicit_model_survives_stale_catalog(defaults_api):
-    client, factory, defaults = defaults_api
-    _endpoint(factory, cached=["text-embedding-3-small", "other-chat"])
-    defaults.update(default_endpoint_id="ep", default_model="my-custom-chat")
-    assert client.get("/api/default-chat").json()["model"] == "my-custom-chat"
-
-
-def test_model_filter_preserves_owner_scope(defaults_api):
-    client, factory, defaults = defaults_api
-    _endpoint(factory, owner="bob", endpoint_id="bobs-endpoint", cached=["bobs-chat"])
-    _endpoint(factory, cached=["text-embedding-3-small", "alices-chat"])
-    defaults.update(default_endpoint_id="bobs-endpoint")
-    result = client.get("/api/default-chat").json()
-    assert result["endpoint_id"] == "ep"
-    assert result["model"] == "alices-chat"

tests/test_docker_devops_hardening.py

@@ -67,14 +67,6 @@ def test_compose_files_forward_companion_base_url():
         assert "COMPANION_BASE_URL" in _compose_env_names(path), path.name
 
 
-def test_compose_files_forward_first_token_timeout():
-    # The local first-event watchdog (src/llm_core.py) reads this from the
-    # process environment, so a Docker install can only reach it when the
-    # compose files forward it from the host .env.
-    for path in COMPOSE_FILES:
-        assert "ODYSSEUS_FIRST_TOKEN_TIMEOUT" in _compose_env_names(path), path.name
-
-
 def test_default_compose_files_do_not_mount_host_docker_socket():
     for path in COMPOSE_FILES:
         text = path.read_text(encoding="utf-8")

tests/test_document_export_zip_filenames.py

@@ -1,96 +0,0 @@
-"""ZIP exports keep language extensions and place collision suffixes before them."""
-import io
-import zipfile
-
-import pytest
-from fastapi import FastAPI, Request
-from fastapi.testclient import TestClient
-from sqlalchemy import create_engine
-from sqlalchemy.orm import sessionmaker
-
-from core.database import Base, Document
-from routes.document import document_routes
-
-
-@pytest.fixture
-def exports(tmp_path, monkeypatch):
-    engine = create_engine(f"sqlite:///{tmp_path / 'documents.db'}", connect_args={"check_same_thread": False})
-    Base.metadata.create_all(engine)
-    factory = sessionmaker(bind=engine)
-    monkeypatch.setattr(document_routes, "SessionLocal", factory)
-    monkeypatch.setenv("AUTH_ENABLED", "true")
-    app = FastAPI()
-
-    @app.middleware("http")
-    async def fixture_user(request: Request, call_next):
-        request.state.current_user = "alice"
-        return await call_next(request)
-
-    app.include_router(document_routes.setup_document_routes(None))
-
-    def add(doc_id, title, language, content="body\n", owner="alice"):
-        with factory() as db:
-            db.add(Document(id=doc_id, title=title, language=language,
-                            current_content=content, owner=owner, is_active=True))
-            db.commit()
-
-    with TestClient(app) as client:
-        yield client, add
-    engine.dispose()
-
-
-@pytest.mark.parametrize("title,language,filename", [
-    ("config.local", "python", "config.local.py"),
-    ("report.v2", "markdown", "report.v2.md"),
-    ("data.2024", "json", "data.2024.json"),
-    ("module.ts", "typescript", "module.ts"),
-    ("SCRIPT.PY", "python", "SCRIPT.PY"),
-    ("résumé.v2", "text", "résumé.v2.txt"),
-    ("unknown.v2", "unknown", "unknown.v2.txt"),
-    ("draft", None, "draft.txt"),
-    ("project/report.v2", "markdown", "projectreport.v2.md"),
-])
-def test_export_uses_the_language_extension_even_for_dotted_titles(exports, title, language, filename):
-    client, add = exports
-    body = "Original text: α\n"
-    add("doc", title, language, body)
-    response = client.post("/api/documents/export-zip", json={"ids": ["doc"]})
-    assert response.status_code == 200
-    assert response.headers["content-type"] == "application/zip"
-    with zipfile.ZipFile(io.BytesIO(response.content)) as archive:
-        assert archive.namelist() == [filename]
-        assert archive.read(filename).decode() == body
-
-
-@pytest.mark.parametrize("title", ["config.local", "config.local.py"])
-def test_duplicate_names_keep_the_extension_at_the_end(exports, title):
-    client, add = exports
-    for i in range(3):
-        add(str(i), title, "python", f"body {i}")
-    response = client.post("/api/documents/export-zip", json={"ids": ["0", "1", "2"]})
-    assert response.status_code == 200
-    with zipfile.ZipFile(io.BytesIO(response.content)) as archive:
-        assert set(archive.namelist()) == {"config.local.py", "config.local-1.py", "config.local-2.py"}
-        assert {archive.read(name).decode() for name in archive.namelist()} == {"body 0", "body 1", "body 2"}
-
-
-def test_added_extension_collides_safely_with_an_existing_extension(exports):
-    client, add = exports
-    add("a", "report.v2", "markdown", "first")
-    add("b", "report.v2.md", "markdown", "second")
-    response = client.post("/api/documents/export-zip", json={"ids": ["a", "b"]})
-    assert response.status_code == 200
-    with zipfile.ZipFile(io.BytesIO(response.content)) as archive:
-        assert set(archive.namelist()) == {"report.v2.md", "report.v2-1.md"}
-        assert {archive.read(name) for name in archive.namelist()} == {b"first", b"second"}
-
-
-def test_foreign_documents_are_still_excluded_and_email_body_is_preserved(exports):
-    client, add = exports
-    add("owned", "reply.v2", "email", "Subject: Hello\n---\nBody")
-    add("foreign", "private", "python", "secret", owner="bob")
-    response = client.post("/api/documents/export-zip", json={"ids": ["owned", "foreign"]})
-    assert response.status_code == 200
-    with zipfile.ZipFile(io.BytesIO(response.content)) as archive:
-        assert archive.namelist() == ["reply.v2.eml"]
-        assert archive.read("reply.v2.eml") == b"Subject: Hello\r\n\r\nBody"

tests/test_document_library_literal_search.py

@@ -1,74 +0,0 @@
-"""Literal punctuation in library queries must not become SQL wildcards."""
-
-from types import SimpleNamespace
-from unittest.mock import MagicMock
-
-import pytest
-
-from core.database import Document
-from routes.document import document_routes
-from tests.helpers.database import disposable_database
-
-
-CASES = [
-    ("100%", "100% complete", "1000 complete"),
-    ("a_b", "a_b", "axb"),
-    ("%", "price 10%", "price 100"),
-    ("_", "a_b", "axb"),
-    (r"path\notes", r"path\notes", "pathnotes"),
-    (r"path\_tag", r"path\_tag", r"path\Xtag"),
-    ("50%_done", "50%_done", "500Xdone"),
-    ("can't", "can't stop", "cannot stop"),
-    ("mixed case", "Case ordered Mixed", "Mixed without"),
-]
-
-
-@pytest.mark.parametrize("column", ["title", "current_content"])
-@pytest.mark.parametrize("query,literal,lookalike", CASES)
-@pytest.mark.asyncio
-async def test_library_search_matches_literal_tokens(tmp_path, monkeypatch, column, query, literal, lookalike):
-    with disposable_database(tmp_path) as factory:
-        monkeypatch.setattr(document_routes, "SessionLocal", factory)
-        with factory() as db:
-            for doc_id, text, owner, active, archived in [
-                ("literal", literal, "alice", True, False),
-                ("lookalike", lookalike, "alice", True, False),
-                ("foreign", literal, "bob", True, False),
-                ("inactive", literal, "alice", False, False),
-                ("archived", literal, "alice", True, True),
-            ]:
-                fields = {"title": "Document", "current_content": "Body", column: text}
-                db.add(Document(id=doc_id, owner=owner, is_active=active, archived=archived,
-                                language="text", version_count=1, **fields))
-            db.commit()
-        router = document_routes.setup_document_routes(MagicMock())
-        endpoint = next(r.endpoint for r in router.routes if r.path == "/api/documents/library")
-        request = SimpleNamespace(state=SimpleNamespace(current_user="alice"))
-        result = await endpoint(request, search=query, language=None, sort="recent", offset=0, limit=20, archived=False)
-        assert result["total"] == 1
-        assert [row["id"] for row in result["documents"]] == ["literal"]
-        archived = await endpoint(request, search=query, language=None, sort="recent", offset=0, limit=20, archived=True)
-        assert [row["id"] for row in archived["documents"]] == ["archived"]
-
-
-@pytest.mark.asyncio
-async def test_literal_search_keeps_cross_field_and_pagination_behavior(tmp_path, monkeypatch):
-    with disposable_database(tmp_path) as factory:
-        monkeypatch.setattr(document_routes, "SessionLocal", factory)
-        with factory() as db:
-            for doc_id, title, content in [
-                ("first", "100% ready", "done"),
-                ("second", "done", "100% ready"),
-                ("lookalike", "1000 ready", "done"),
-                ("missing-term", "100% ready", "waiting"),
-            ]:
-                db.add(Document(id=doc_id, owner="alice", title=title, current_content=content,
-                                is_active=True, archived=False, language="text", version_count=1))
-            db.commit()
-        router = document_routes.setup_document_routes(MagicMock())
-        endpoint = next(r.endpoint for r in router.routes if r.path == "/api/documents/library")
-        request = SimpleNamespace(state=SimpleNamespace(current_user="alice"))
-        results = [await endpoint(request, search="100% done", language="text", sort="alpha",
-                                  offset=offset, limit=1, archived=False) for offset in [0, 1]]
-        assert all(result["total"] == 2 for result in results)
-        assert {row["id"] for result in results for row in result["documents"]} == {"first", "second"}

tests/test_effect_journal_persistence.py

@@ -41,8 +41,7 @@ def test_claim_is_fsynced_to_disk_before_returning(tmp_path, target, monkeypatch
     on_disk = records(log.path)
     assert [r["type"] for r in on_disk] == ["claim"]
     assert fx.EffectClaim.from_dict(on_disk[0]["record"]) == made
-    if os.name != "nt":  # Windows has no POSIX permission bits: os.open's 0o600 is not reflected in st_mode
+    assert oct(log.path.stat().st_mode & 0o777) == "0o600"
-        assert oct(log.path.stat().st_mode & 0o777) == "0o600"
 
 
 def test_claim_persistence_failure_raises_and_records_nothing(tmp_path, target):

tests/test_fork_session_metadata.py

@@ -90,42 +90,3 @@ def test_fork_does_not_corrupt_source_message_metadata(monkeypatch):
     # ...and the source session's _db_id values are untouched.
     assert source.history[0].metadata["_db_id"] == "src-0"
     assert source.history[1].metadata["_db_id"] == "src-1"
-
-
-def _fork_with(monkeypatch, body, db_ids):
-    """Fork a 4-message source whose DB rows have the given ids."""
-    monkeypatch.setattr(mod, "_verify_session_owner", lambda *a, **k: None)
-    source = _FakeSession(name="Long chat")
-    for i, role in enumerate(["user", "assistant", "user", "assistant"]):
-        source.history.append(ChatMessage(role=role, content=f"m{i}", metadata={"_db_id": db_ids[i]}))
-    manager = _FakeSessionManager(source)
-    rows = [SimpleNamespace(id=i) for i in db_ids]
-
-    class _Query:
-        def filter(self, *a): return self
-        def order_by(self, *a): return self
-        def all(self): return rows
-
-    class _DB:
-        def query(self, *a): return _Query()
-        def close(self): pass
-
-    monkeypatch.setattr(mod, "SessionLocal", lambda: _DB())
-    router = mod.setup_history_routes(manager)
-
-    class _Req:
-        async def json(self): return body
-
-    asyncio.run(_fork_handler(router)(_Req(), "src-id"))
-    return [m.content for m in manager.created.history]
-
-
-def test_fork_before_a_message_id_ignores_a_stale_keep_count(monkeypatch):
-    copied = _fork_with(monkeypatch, {"before_msg_id": "c", "keep_count": 0}, ["a", "b", "c", "d"])
-    assert copied == ["m0", "m1"]
-
-
-def test_fork_through_a_message_id_includes_it(monkeypatch):
-    copied = _fork_with(monkeypatch, {"through_msg_id": "b", "keep_count": 0}, ["a", "b", "c", "d"])
-    assert copied == ["m0", "m1"]
-

tests/test_gallery_album_input.py

@@ -1,49 +0,0 @@
-import asyncio
-
-import pytest
-from fastapi import HTTPException
-
-import routes.gallery_routes as gallery
-
-
-def route(path, method):
-    return next(r for r in gallery.setup_gallery_routes().routes if r.path == path and method in r.methods)
-
-
-def call(path, method, monkeypatch, body):
-    monkeypatch.setattr(gallery, 'get_current_user', lambda request: 'alice')
-
-    class Request:
-        async def json(self):
-            return body
-
-    return asyncio.run(route(path, method).endpoint(Request(), 'album-1'))
-
-
-@pytest.mark.parametrize('body', [
-    {'name': ''},
-    {'name': '   '},
-    {'name': 123},
-    {'name': ['x']},
-    {'description': {'a': 1}},
-    [1],
-])
-def test_album_update_rejects_bad_input(body, monkeypatch):
-    with pytest.raises(HTTPException) as exc:
-        call('/api/gallery/albums/{album_id}', 'PUT', monkeypatch, body)
-    assert exc.value.status_code == 400
-
-
-@pytest.mark.parametrize('op', ['add', 'remove'])
-@pytest.mark.parametrize('body', [
-    {'image_ids': 'abc'},
-    {'image_ids': 5},
-    {'image_ids': None},
-    {'image_ids': [{'a': 1}]},
-    {'image_ids': ['ok', 1]},
-    [1],
-])
-def test_album_image_ids_must_be_a_list_of_strings(op, body, monkeypatch):
-    with pytest.raises(HTTPException) as exc:
-        call(f'/api/gallery/albums/{{album_id}}/{op}', 'POST', monkeypatch, body)
-    assert exc.value.status_code == 400

tests/test_gallery_search_multiword.py

@@ -1,135 +0,0 @@
-"""Regression for #2123 (gallery part): library search must match multi-word
-queries in any order and treat % / _ literally.
-
-Old code built a single ``%{search}%`` LIKE over prompt/tags/ai_tags, so
-"red car" missed "a car that is red", and a literal "%" matched every row.
-"""
-
-import uuid
-
-from fastapi import FastAPI
-from fastapi.testclient import TestClient
-from sqlalchemy import create_engine
-from sqlalchemy.orm import sessionmaker
-from sqlalchemy.pool import NullPool
-
-import core.database as cdb
-from core.database import GalleryImage
-import routes.gallery_routes as gallery_routes
-
-
-def _client_with_gallery(monkeypatch, tmp_path):
-    engine = create_engine(
-        f"sqlite:///{tmp_path / 'gallery_search.db'}",
-        connect_args={"check_same_thread": False},
-        poolclass=NullPool,
-    )
-    cdb.Base.metadata.create_all(engine)
-    session_factory = sessionmaker(bind=engine, autoflush=False, autocommit=False)
-    monkeypatch.setattr(gallery_routes, "SessionLocal", session_factory)
-
-    db = session_factory()
-    try:
-        db.add_all(
-            [
-                GalleryImage(
-                    id="img-red-car",
-                    filename=f"{uuid.uuid4().hex}.png",
-                    prompt="a car that is red",
-                    model="model-a",
-                    tags="",
-                    ai_tags="",
-                    is_active=True,
-                    file_size=10,
-                ),
-                GalleryImage(
-                    id="img-boat",
-                    filename=f"{uuid.uuid4().hex}.png",
-                    prompt="blue boat on the lake",
-                    model="model-a",
-                    tags="",
-                    ai_tags="",
-                    is_active=True,
-                    file_size=10,
-                ),
-                GalleryImage(
-                    id="img-percent",
-                    filename=f"{uuid.uuid4().hex}.png",
-                    prompt="100% cotton shirt",
-                    model="model-a",
-                    tags="sale_2024",
-                    ai_tags="",
-                    is_active=True,
-                    file_size=10,
-                ),
-                GalleryImage(
-                    id="img-backslash",
-                    filename=f"{uuid.uuid4().hex}.png",
-                    prompt=r"C:\photos\sunset",
-                    model="model-a",
-                    tags="",
-                    ai_tags="",
-                    is_active=True,
-                    file_size=10,
-                ),
-            ]
-        )
-        db.commit()
-    finally:
-        db.close()
-
-    app = FastAPI()
-    app.include_router(gallery_routes.setup_gallery_routes())
-    return TestClient(app)
-
-
-def test_gallery_search_matches_words_in_any_order(monkeypatch, tmp_path):
-    monkeypatch.setenv("AUTH_ENABLED", "false")
-    client = _client_with_gallery(monkeypatch, tmp_path)
-
-    body = client.get("/api/gallery/library", params={"search": "red car"}).json()
-    ids = {item["id"] for item in body["items"]}
-    assert "img-red-car" in ids
-    assert "img-boat" not in ids
-
-
-def test_gallery_search_escapes_percent_wildcard(monkeypatch, tmp_path):
-    monkeypatch.setenv("AUTH_ENABLED", "false")
-    client = _client_with_gallery(monkeypatch, tmp_path)
-
-    body = client.get("/api/gallery/library", params={"search": "%"}).json()
-    ids = {item["id"] for item in body["items"]}
-    assert ids == {"img-percent"}
-
-
-def test_gallery_search_escapes_underscore_wildcard(monkeypatch, tmp_path):
-    monkeypatch.setenv("AUTH_ENABLED", "false")
-    client = _client_with_gallery(monkeypatch, tmp_path)
-
-    # Only img-percent has a literal underscore (in tags "sale_2024").
-    # Unescaped, "_" matches any single char so every row matches.
-    body = client.get("/api/gallery/library", params={"search": "_"}).json()
-    ids = {item["id"] for item in body["items"]}
-    assert ids == {"img-percent"}
-
-
-def test_gallery_search_escapes_backslash(monkeypatch, tmp_path):
-    monkeypatch.setenv("AUTH_ENABLED", "false")
-    client = _client_with_gallery(monkeypatch, tmp_path)
-
-    # Only img-backslash has a literal backslash. The escape char itself
-    # must survive escaping instead of escaping the surrounding wildcards.
-    body = client.get("/api/gallery/library", params={"search": "\\"}).json()
-    ids = {item["id"] for item in body["items"]}
-    assert ids == {"img-backslash"}
-
-
-def test_gallery_tag_filter_escapes_wildcards(monkeypatch, tmp_path):
-    monkeypatch.setenv("AUTH_ENABLED", "false")
-    client = _client_with_gallery(monkeypatch, tmp_path)
-
-    # Unescaped, "%" / "_" match every row; escaped, only literal matches.
-    assert client.get("/api/gallery/library", params={"tag": "%"}).json()["items"] == []
-
-    body = client.get("/api/gallery/library", params={"tag": "_"}).json()
-    assert {item["id"] for item in body["items"]} == {"img-percent"}

tests/test_interrupted_resume_label_static.py

@@ -4,11 +4,11 @@ from tests.helpers.stylesheets import app_css
 
 
 ROOT = Path(__file__).resolve().parents[1]
-CHAT = (ROOT / "static/js/chat.js").read_text(encoding="utf-8")
+CHAT = (ROOT / "static/js/chat.js").read_text()
-RENDERER = (ROOT / "static/js/chatRenderer.js").read_text(encoding="utf-8")
+RENDERER = (ROOT / "static/js/chatRenderer.js").read_text()
 STYLE = app_css()
-APP = (ROOT / "static/app.js").read_text(encoding="utf-8")
+APP = (ROOT / "static/app.js").read_text()
-INDEX = (ROOT / "static/index.html").read_text(encoding="utf-8")
+INDEX = (ROOT / "static/index.html").read_text()
 
 
 def test_live_interruption_controls_have_visible_resume_labels():

tests/test_pdf_cmyk_image_analysis.py

@@ -1,98 +0,0 @@
-"""Actual embedded PDF images must reach vision as a decodable PNG."""
-from pathlib import Path
-
-from PIL import Image
-from pypdf import PdfReader, PdfWriter
-from pypdf.generic import DecodedStreamObject, DictionaryObject, NameObject, NumberObject
-import pytest
-
-from src import document_processor as dp
-
-
-def make_pdf(tmp_path, mode):
-    colors = {"CMYK": (0, 255, 255, 0), "RGB": (255, 0, 0), "L": 127}
-    path = tmp_path / (mode + ".pdf")
-    image = Image.new(mode, (128, 96), colors[mode])
-    if mode == "CMYK":
-        # A raw DeviceCMYK XObject avoids JPEG/Adobe inversion differences in
-        # Pillow-generated PDFs; the extracted color samples are unambiguous.
-        writer = PdfWriter()
-        page = writer.add_blank_page(width=128, height=96)
-        stream = DecodedStreamObject()
-        stream.set_data(image.tobytes())
-        stream.update({NameObject(key): value for key, value in {
-            "/Type": NameObject("/XObject"), "/Subtype": NameObject("/Image"),
-            "/ColorSpace": NameObject("/DeviceCMYK"), "/BitsPerComponent": NumberObject(8),
-            "/Width": NumberObject(128), "/Height": NumberObject(96),
-        }.items()})
-        page[NameObject("/Resources")] = DictionaryObject({NameObject("/XObject"):
-            DictionaryObject({NameObject("/Im0"): writer._add_object(stream)})})
-        content = DecodedStreamObject()
-        content.set_data(b"q 128 0 0 96 0 0 cm /Im0 Do Q")
-        page[NameObject("/Contents")] = writer._add_object(content)
-        writer.write(path)
-    else:
-        image.save(path, "PDF")
-    assert PdfReader(path).pages[0].images[0].image.mode == mode
-    return path
-
-
-@pytest.mark.parametrize("mode,expected", [("CMYK", "RGB"), ("RGB", "RGB"), ("L", "L")])
-def test_pdf_image_reaches_vision_with_owner_and_png_pixels(tmp_path, monkeypatch, mode, expected):
-    pdf = make_pdf(tmp_path, mode)
-    calls = []
-    def analyze(path, owner=None):
-        with Image.open(path) as image:
-            image.load()
-            assert image.format == "PNG" and image.mode == expected
-            assert image.size == (128, 96)
-            if mode == "CMYK":
-                red, green, blue = image.getpixel((64, 48))
-                assert red > 250 and green < 5 and blue < 5
-            calls.append((Path(path), owner))
-        return "Synthetic OCR result"
-    monkeypatch.setattr(dp, "analyze_image_with_vl", analyze)
-    output = dp._process_pdf(str(pdf), owner="alice")
-    assert "[Page 1 image 1 text]: Synthetic OCR result" in output
-    assert len(calls) == 1 and calls[0][1] == "alice"
-    assert not calls[0][0].exists(), "Temporary PNG must be removed after analysis"
-    assert PdfReader(pdf).pages[0].images[0].image.mode == mode, "Source PDF is unchanged"
-
-
-def test_mixed_pdf_keeps_images_on_both_pages(tmp_path, monkeypatch):
-    writer = PdfWriter()
-    for mode in ("CMYK", "RGB"):
-        writer.append(str(make_pdf(tmp_path, mode)))
-    pdf = tmp_path / "mixed.pdf"
-    writer.write(pdf)
-    calls = []
-    def analyze(path, owner=None):
-        with Image.open(path) as image:
-            image.load()
-            calls.append(image.mode)
-        return "Image content"
-    monkeypatch.setattr(dp, "analyze_image_with_vl", analyze)
-    output = dp._process_pdf(str(pdf), owner="alice")
-    assert calls == ["RGB", "RGB"]
-    assert "Page 1 image 1 text" in output and "Page 2 image 1 text" in output
-
-
-def test_text_only_extraction_does_not_enable_vision(tmp_path, monkeypatch):
-    pdf = make_pdf(tmp_path, "CMYK")
-    def unexpected(*args, **kwargs):
-        pytest.fail("Text-only extraction must not call vision")
-    monkeypatch.setattr(dp, "analyze_image_with_vl", unexpected)
-    assert "no readable content" in dp.extract_local_document(str(pdf), owner="alice")
-
-
-def test_vision_failure_still_removes_converted_png(tmp_path, monkeypatch):
-    pdf = make_pdf(tmp_path, "CMYK")
-    paths = []
-    def unavailable(path, owner=None):
-        paths.append(Path(path))
-        with Image.open(path) as image:
-            assert image.mode == "RGB" and image.format == "PNG"
-        raise RuntimeError("Synthetic unavailable vision endpoint")
-    monkeypatch.setattr(dp, "analyze_image_with_vl", unavailable)
-    assert "no readable content" in dp._process_pdf(str(pdf), owner="alice")
-    assert len(paths) == 1 and not paths[0].exists()

tests/test_pinned_model_route_selection.py

@@ -1,108 +0,0 @@
-"""Route defaults must use manually pinned IDs without widening ownership."""
-
-import json
-from types import SimpleNamespace
-
-import pytest
-from sqlalchemy import create_engine
-from sqlalchemy.orm import sessionmaker
-
-import core.database as cdb
-import routes.chat_routes as chat
-from routes.task.task_routes import _resolve_run_endpoint
-from routes.research.research_routes import _resolve_endpoint_runtime
-
-
-@pytest.fixture
-def database(monkeypatch):
-    engine = create_engine("sqlite:///:memory:")
-    cdb.Base.metadata.create_all(engine)
-    factory = sessionmaker(bind=engine)
-    monkeypatch.setattr(chat, "SessionLocal", factory)
-    with factory() as db:
-        yield db
-    engine.dispose()
-
-
-def endpoint(db, eid="owned", *, owner="alice", cached=(), pinned=("pinned-chat",), hidden=()):
-    row = cdb.ModelEndpoint(
-        id=eid, name=eid, owner=owner, is_enabled=True,
-        base_url=f"https://{eid}.example.test/v1", api_key=None,
-        cached_models=json.dumps(cached), pinned_models=json.dumps(pinned),
-        hidden_models=json.dumps(hidden),
-    )
-    db.add(row)
-    db.commit()
-    return row
-
-
-@pytest.mark.parametrize("cached", [(), ("hidden-chat",)])
-def test_empty_session_recovers_a_visible_pinned_model(database, cached):
-    ep = endpoint(database, cached=cached, hidden=("hidden-chat",))
-    database.add(cdb.Session(id="chat", name="Chat", owner="alice", model="", endpoint_url=ep.base_url, endpoint_id=ep.id))
-    database.commit()
-    session = SimpleNamespace(model="", endpoint_url=ep.base_url, endpoint_id=ep.id)
-
-    assert chat._recover_empty_session_model(session, "chat", "alice") is True
-    assert session.model == "pinned-chat"
-    database.expire_all()
-    assert database.get(cdb.Session, "chat").model == "pinned-chat"
-
-
-def test_empty_session_does_not_recover_a_hidden_pin(database):
-    ep = endpoint(database, hidden=("pinned-chat",))
-    session = SimpleNamespace(model="", endpoint_url=ep.base_url, endpoint_id=ep.id)
-    assert chat._recover_empty_session_model(session, "missing", "alice") is False
-    assert session.model == ""
-
-
-def test_subscription_recovery_still_requires_its_live_catalog(database):
-    ep = endpoint(database)
-    ep.base_url = "https://chatgpt.com/backend-api/codex"
-    database.commit()
-    session = SimpleNamespace(model="", endpoint_url=ep.base_url, endpoint_id=ep.id)
-    assert chat._recover_empty_session_model(session, "missing", "alice") is False
-    assert session.model == ""
-
-
-def test_task_run_reopens_against_its_owners_pinned_endpoint(database):
-    endpoint(database, "foreign", owner="bob", cached=("pinned-chat",))
-    own = endpoint(database)
-    task = SimpleNamespace(owner="alice", endpoint_url="", session_id=None, model="pinned-chat")
-    assert _resolve_run_endpoint(database, task, SimpleNamespace(model="pinned-chat")) == own.base_url
-
-
-@pytest.mark.parametrize("owner", ["alice", None])
-def test_task_run_can_find_visible_pins_on_owned_or_shared_endpoints(database, owner):
-    ep = endpoint(database, owner=owner)
-    task = SimpleNamespace(owner="alice", endpoint_url="", session_id=None, model="pinned-chat")
-    assert _resolve_run_endpoint(database, task, SimpleNamespace(model=None)) == ep.base_url
-
-
-def test_task_run_does_not_autoselect_a_hidden_pin(database):
-    endpoint(database, hidden=("pinned-chat",))
-    task = SimpleNamespace(owner="alice", endpoint_url="", session_id=None, model="pinned-chat")
-    assert _resolve_run_endpoint(database, task, SimpleNamespace(model="pinned-chat")) == ""
-
-
-@pytest.mark.parametrize("cached", [(), ("hidden-chat",)])
-def test_research_default_uses_the_visible_pinned_id(database, cached):
-    ep = endpoint(database, cached=cached, hidden=("hidden-chat",))
-    assert _resolve_endpoint_runtime(ep, owner="alice") == (
-        ep.base_url + "/chat/completions", "pinned-chat", {},
-    )
-
-
-def test_research_default_does_not_autoselect_a_hidden_pin(database):
-    ep = endpoint(database, hidden=("pinned-chat",))
-    assert _resolve_endpoint_runtime(ep, owner="alice") is None
-
-
-def test_research_explicit_model_selection_is_preserved(database):
-    ep = endpoint(database, cached=("cached-chat",))
-    assert _resolve_endpoint_runtime(ep, owner="alice", model="explicit-chat")[1] == "explicit-chat"
-
-
-def test_research_cached_default_keeps_priority_over_pins(database):
-    ep = endpoint(database, cached=("cached-chat",))
-    assert _resolve_endpoint_runtime(ep, owner="alice")[1] == "cached-chat"

tests/test_preview_execution_evidence.py

@@ -1,6 +1,5 @@
 """Execution outcomes must reach the model, not just the tool-event UI."""
 import json
-import os
 
 import pytest
 
@@ -8,7 +7,6 @@ from src.agent_tools.subprocess_tools import BashTool
 from src.clean_agent_preview import preview_tool_result_text
 
 
-@pytest.mark.skipif(os.name == "nt", reason="POSIX-only: enforcing containment (bubblewrap/process group) needed to run native bash; Windows windows_tree gives wall-clock only")
 @pytest.mark.asyncio
 async def test_failed_shell_retains_exit_status_and_both_streams_for_followup(tmp_path):
     from tests.process_resource_helpers import launch_authority

tests/test_production_external_bridge.py

@@ -3,7 +3,6 @@
 P2-2 invariant: external bridge execution != local containment.
 """
 import asyncio
-import os
 from types import SimpleNamespace
 from unittest.mock import patch
 
@@ -181,7 +180,6 @@ async def test_external_record_does_not_grant_authority(tmp_path):
         await containment.run(grant, "id")
 
 
-@pytest.mark.skipif(os.name == "nt", reason="POSIX-only: enforcing containment (bubblewrap/process group) needed to run native bash; Windows windows_tree gives wall-clock only")
 @pytest.mark.asyncio
 async def test_native_local_bash_python_behavior_unchanged(tmp_path, monkeypatch):
     """4. Native local Bash/Python behavior is unchanged."""

tests/test_queued_message_merge_static.py

@@ -2,7 +2,7 @@ from pathlib import Path
 
 
 ROOT = Path(__file__).resolve().parents[1]
-CHAT = (ROOT / "static/js/chat.js").read_text(encoding="utf-8")
+CHAT = (ROOT / "static/js/chat.js").read_text()
 
 
 def test_queued_stack_is_consumed_as_one_ordered_message():

tests/test_regenerate_truncate_warning_js.py

@@ -1,541 +0,0 @@
-"""Executable regression for the "regenerate" data-loss warning.
-
-`regenerateFrom` (the per-message regenerate footer button), `resendUserMessage`
-(footer Resend and the vision editor's "Regenerate message" button) and
-`editUserMessage` (sending an edited user message) all permanently delete
-every message after the point clicked via POST /api/session/{id}/truncate —
-a real, unrecoverable server-side delete. Using any of them on anything but
-the very last exchange used to do this with no warning at all; a mis-click
-could silently erase an entire conversation. This drives the real chat.js
-functions under Node, confirming:
-
-  1. Regenerating the *last* exchange (nothing after it) never prompts and
-     truncates directly — the everyday case must not gain friction.
-  2. Regenerating anything earlier prompts first, with the correct count of
-     messages that would be destroyed in the message text.
-  3. Cancelling the prompt aborts before any network call — nothing is
-     deleted.
-  4. Confirming the prompt proceeds with the correct `keep_count`.
-  5. Choosing "Fork from here" deletes nothing: it forks the chat just
-     before the user turn and replays the action (same text, or the edited
-     text) in the new chat instead.
-
-All three entry points are exercised the same way since they wrap the same
-destructive operation.
-
-Unlike test_pr6020_browser_review_regressions.py's `_chat_smoke_source`
-(which appends extra code to a copy of chat.js's own source — fine for
-defining an extra exported function, since ES module static imports are
-hoisted and evaluated before any top-level code regardless of where in the
-file it appears), this harness needs its global stubs (document, fetch,
-etc.) in place *before* chat.js's own import tree evaluates, since some of
-those transitive dependencies touch browser globals at their own module top
-level. So this loads chat.js via a real dynamic `import()` of its actual
-file, in a small wrapper script that sets the stubs up first as plain
-synchronous statements — dynamic `import()` runs in program order, unlike a
-static `import` declaration.
-"""
-import json
-import re
-import shutil
-import subprocess
-from pathlib import Path
-
-import pytest
-
-_REPO = Path(__file__).resolve().parents[1]
-_JS_DIR = _REPO / "static" / "js"
-_HAS_NODE = shutil.which("node") is not None
-
-
-def _versioned_js_uri(entry_js: Path, target_name: str) -> str:
-    """file:// URI for target_name with the same cache-busting query string
-    entry_js's own import of it uses. ES modules cache by full URL, so
-    importing 'ui.js' here while chat.js imports 'ui.js?v=X' yields two module
-    instances, and patching uiMod here would never reach chat.js."""
-    src = entry_js.read_text(encoding="utf-8")
-    m = re.search(rf"from ['\"]\./{re.escape(target_name)}(\?[^'\"]*)?['\"]", src)
-    suffix = (m.group(1) or "") if m else ""
-    return (entry_js.parent / target_name).resolve().as_uri() + suffix
-
-
-def _run_node(source: str) -> dict:
-    proc = subprocess.run(
-        ["node", "--input-type=module"],
-        input=source,
-        capture_output=True,
-        text=True,
-        cwd=_REPO,
-        timeout=30,
-    )
-    assert proc.returncode == 0, proc.stderr
-    return json.loads(proc.stdout.strip().splitlines()[-1])
-
-
-_HARNESS_PREAMBLE = """
-      globalThis.window = globalThis;
-      Object.defineProperty(globalThis, "navigator", { value: { platform: "" }, writable: true, configurable: true });
-      globalThis.addEventListener = () => {};
-      globalThis.removeEventListener = () => {};
-      globalThis.dispatchEvent = () => {};
-      globalThis.requestAnimationFrame = () => 0;
-      globalThis.cancelAnimationFrame = () => {};
-      globalThis.localStorage = { getItem() { return null; }, setItem() {}, removeItem() {} };
-      globalThis.location = {};
-      globalThis.history = {};
-      globalThis.MutationObserver = class { observe() {} };
-      globalThis.CustomEvent = class {};
-      globalThis.Storage = class {};
-
-      const fetchCalls = [];
-      globalThis.fetch = async (url, opts) => {
-        fetchCalls.push({ url, body: opts && opts.body ? JSON.parse(opts.body) : null });
-        const data = url.includes('/fork') ? { id: 'forked-session', name: 'Forked chat' } : {};
-        // A test can make the server refuse the cut (e.g. a stale message id).
-        const ok = !(url.includes('/truncate') && globalThis.__refuseTruncate);
-        return { ok, status: ok ? 200 : 404, json: async () => data, text: async () => '', headers: { get() { return null; } } };
-      };
-
-      class Element {
-        constructor() {
-          this.children = [];
-          this.classList = { add() {}, remove() {}, toggle() {}, contains: () => false };
-          this.style = { setProperty() {} };
-          this.dataset = {};
-          this._listeners = {};
-          this._html = '';
-        }
-        get innerHTML() { return this._html; }
-        set innerHTML(v) { this._html = v; this.children = []; }
-        querySelector() { return null; }
-        querySelectorAll() { return []; }
-        appendChild(child) { this.children.push(child); return child; }
-        addEventListener(type, fn) { (this._listeners[type] ||= []).push(fn); }
-        removeEventListener() {}
-        focus() {}
-        // Fire a listener and wait for it — the edit Send handler is async.
-        fire(type) {
-          const ev = { stopPropagation() {}, preventDefault() {} };
-          return Promise.all((this._listeners[type] || []).map(fn => fn(ev)));
-        }
-      }
-      class HTMLInputElement extends Element {
-        get value() { return this._value || ''; }
-        set value(v) { this._value = v; }
-      }
-      globalThis.HTMLInputElement = HTMLInputElement;
-
-      // A minimal .msg-list DOM: `msgs` is an ordered array of
-      // { role: 'user'|'ai' } describing one conversation. Each entry
-      // becomes a fake message element good enough for regenerateFrom /
-      // resendUserMessage's own traversal (classList.contains, .dataset,
-      // querySelector('.body'), querySelectorAll('[data-file-id]')).
-      function buildMsgEls(msgs) {
-        return msgs.map((m, i) => {
-          const body = new Element();
-          body.textContent = m === 'user' ? `question ${i}` : `answer ${i}`;
-          body.innerHTML = body.textContent;
-          return {
-            classList: { contains: (c) => c === (m === 'user' ? 'msg-user' : 'msg-ai') },
-            dataset: { raw: m === 'user' ? `question ${i}` : '' },
-            querySelector: (sel) => sel === '.body' ? body : null,
-            querySelectorAll: () => [],
-            nextSibling: null,
-            remove() {},
-          };
-        });
-      }
-
-      const sendClicks = [];
-      const messageInputEl = new HTMLInputElement();
-      const sendBtnEl = { click: () => sendClicks.push(messageInputEl.value) };
-
-      globalThis.document = {
-        body: new Element(),
-        head: new Element(),
-        documentElement: new Element(),
-        getElementById(id) {
-          if (id === 'message') return messageInputEl;
-          if (id === 'chat-history') return this._box;
-          return null;
-        },
-        querySelector(sel) { return sel === '.send-btn' ? sendBtnEl : null; },
-        querySelectorAll() { return []; },
-        createElement(tag) { return tag === 'input' ? new HTMLInputElement() : new Element(); },
-        createTextNode(text) { return { textContent: text }; },
-        addEventListener() {},
-        removeEventListener() {},
-      };
-"""
-
-
-def _scenario_script(func_call_js: str, roles: list, target_index: int, confirm_resolution, then_js: str = "", db_ids: bool = False, refuse_truncate: bool = False, file_ids: dict | None = None) -> str:
-    # Globals are stubbed above as plain synchronous statements *before* the
-    # dynamic import()s below run — unlike a static `import` declaration,
-    # dynamic import() executes in program order, so chat.js's transitive
-    # dependency tree only evaluates once the stubs are already in place.
-    script = _HARNESS_PREAMBLE
-    script += f"""
-      const chat = await import({json.dumps((_JS_DIR / "chat.js").resolve().as_uri())});
-      const {{ default: uiMod }} = await import({json.dumps(_versioned_js_uri(_JS_DIR / "chat.js", "ui.js"))});
-      const {{ default: sessionMod }} = await import({json.dumps(_versioned_js_uri(_JS_DIR / "chat.js", "sessions.js"))});
-
-      let currentSession = 'test-session';
-      const selectedSessions = [];
-      sessionMod.getCurrentSessionId = () => currentSession;
-      sessionMod.loadSessions = async () => {{}};
-      sessionMod.selectSession = async (id) => {{ selectedSessions.push(id); currentSession = id; }};
-
-      const confirmCalls = [];
-      uiMod.styledConfirm = async (message, opts) => {{
-        confirmCalls.push({{ message, opts }});
-        return {json.dumps(confirm_resolution)};
-      }};
-      uiMod.showError = () => {{}};
-      uiMod.showToast = () => {{}};
-
-      globalThis.__refuseTruncate = {json.dumps(refuse_truncate)};
-      const msgs = buildMsgEls({json.dumps(roles)});
-      // Persisted messages carry their database id; the page may have loaded
-      // only the newest of them, so ids (not positions) identify a message.
-      if ({json.dumps(db_ids)}) msgs.forEach((m, i) => {{ m.dataset.dbId = `db-${{i + 40}}`; }});
-      // Attach uploaded files ({{ index: file_id }}) the way rendered bubbles do.
-      for (const [i, fileId] of Object.entries({json.dumps(file_ids or {})})) {{
-        msgs[i].querySelectorAll = (sel) => sel === '[data-file-id]' ? [{{ dataset: {{ fileId }} }}] : [];
-      }}
-      // Record the attachments queued for each send as the button is clicked.
-      const sentAttachments = [];
-      sendBtnEl.click = () => {{ sendClicks.push(messageInputEl.value); sentAttachments.push(chat._pendingRegenAttachmentIds()); }};
-      const box = {{ querySelectorAll: () => msgs, _isBox: true }};
-      globalThis.document._box = box;
-      const target = msgs[{target_index}];
-
-      await {func_call_js};
-      {then_js}
-
-      const forkCall = fetchCalls.find(c => c.url.includes('/fork'));
-      console.log(JSON.stringify({{
-        confirmShown: confirmCalls.length > 0,
-        confirmMessage: confirmCalls.length ? confirmCalls[0].message : null,
-        confirmOpts: confirmCalls.length ? confirmCalls[0].opts : null,
-        truncateCalled: fetchCalls.some(c => c.url.includes('/truncate')),
-        truncateKeepCount: (fetchCalls.find(c => c.url.includes('/truncate')) || {{}}).body?.keep_count ?? null,
-        forkCalled: Boolean(forkCall),
-        forkUrl: forkCall ? forkCall.url : null,
-        forkKeepCount: forkCall ? forkCall.body.keep_count : null,
-        forkBody: forkCall ? forkCall.body : null,
-        truncateBody: (fetchCalls.find(c => c.url.includes('/truncate')) || {{}}).body || null,
-        selectedSessions,
-        sendClicks,
-        sentAttachments,
-        pendingAttachments: chat._pendingRegenAttachmentIds(),
-      }}));
-      process.exit(0);
-    """
-    return script
-
-
-# ---------------------------------------------------------------------------
-# regenerateFrom (main chat footer "Regenerate from here" button)
-# ---------------------------------------------------------------------------
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_regenerate_from_last_message_skips_prompt_and_truncates():
-    roles = ["user", "ai"]  # target (index 1) IS the last message
-    script = _scenario_script("chat.regenerateFrom(target)", roles, 1, confirm_resolution=True)
-    result = _run_node(script)
-    assert result["confirmShown"] is False
-    assert result["truncateCalled"] is True
-    assert result["truncateKeepCount"] == 0  # keep everything before the user turn (index 0)
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_regenerate_from_earlier_message_prompts_with_correct_count():
-    roles = ["user", "ai", "user", "ai", "user", "ai"]  # target (index 1) has 4 messages after it
-    script = _scenario_script("chat.regenerateFrom(target)", roles, 1, confirm_resolution=True)
-    result = _run_node(script)
-    assert result["confirmShown"] is True
-    assert "4 messages" in result["confirmMessage"]
-    assert result["truncateCalled"] is True
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_regenerate_from_earlier_message_cancel_aborts_without_truncating():
-    roles = ["user", "ai", "user", "ai"]
-    script = _scenario_script("chat.regenerateFrom(target)", roles, 1, confirm_resolution=False)
-    result = _run_node(script)
-    assert result["confirmShown"] is True
-    assert result["truncateCalled"] is False
-
-
-# ---------------------------------------------------------------------------
-# resendUserMessage(..., { replaceFromHere: true }) (vision editor "Regenerate message")
-# ---------------------------------------------------------------------------
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_resend_replace_from_here_last_pair_skips_prompt():
-    roles = ["user", "ai"]  # target (index 0) is the user turn of the last pair
-    script = _scenario_script(
-        "chat.resendUserMessage(target, { replaceFromHere: true })", roles, 0, confirm_resolution=True,
-    )
-    result = _run_node(script)
-    assert result["confirmShown"] is False
-    assert result["truncateCalled"] is True
-    assert result["truncateKeepCount"] == 0
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_resend_replace_from_here_earlier_pair_prompts_with_correct_count():
-    roles = ["user", "ai", "user", "ai", "user", "ai"]  # target (index 0) has 4 messages after its own pair
-    script = _scenario_script(
-        "chat.resendUserMessage(target, { replaceFromHere: true })", roles, 0, confirm_resolution=True,
-    )
-    result = _run_node(script)
-    assert result["confirmShown"] is True
-    assert "4 messages" in result["confirmMessage"]
-    assert result["truncateCalled"] is True
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_resend_replace_from_here_cancel_aborts_without_truncating():
-    roles = ["user", "ai", "user", "ai"]
-    script = _scenario_script(
-        "chat.resendUserMessage(target, { replaceFromHere: true })", roles, 0, confirm_resolution=False,
-    )
-    result = _run_node(script)
-    assert result["confirmShown"] is True
-    assert result["truncateCalled"] is False
-
-
-# ---------------------------------------------------------------------------
-# resendUserMessage(el) with no options (footer "Resend message")
-# ---------------------------------------------------------------------------
-# `dev` made plain resend replace-by-default (see
-# test_resend_message_nondestructive.py): no options means replaceFromHere,
-# so the footer Resend button now truncates everything after the clicked
-# turn too, and gets the same warning. Append-only resend must be explicit.
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_resend_default_earlier_pair_prompts_with_correct_count():
-    roles = ["user", "ai", "user", "ai", "user", "ai"]
-    script = _scenario_script("chat.resendUserMessage(target)", roles, 0, confirm_resolution=True)
-    result = _run_node(script)
-    assert result["confirmShown"] is True
-    assert "4 messages" in result["confirmMessage"]
-    assert result["truncateCalled"] is True
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_resend_append_only_never_truncates_or_prompts():
-    roles = ["user", "ai", "user", "ai"]
-    script = _scenario_script("chat.resendUserMessage(target, { append: true })", roles, 0, confirm_resolution=True)
-    result = _run_node(script)
-    assert result["confirmShown"] is False
-    assert result["truncateCalled"] is False
-
-
-# ---------------------------------------------------------------------------
-# editUserMessage (the pencil edit button, then Send)
-# ---------------------------------------------------------------------------
-# The edit Send handler is wired up inside editUserMessage, so these open the
-# editor, type into it, and click the editor's own Send button.
-
-_EDIT_AND_SEND = """
-      const _body = target.querySelector('.body');
-      const [_editor, _btnRow] = _body.children;
-      _editor.value = 'edited question';
-      await _btnRow.children[0].fire('click');
-"""
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_edit_last_message_skips_prompt_and_truncates():
-    roles = ["user", "ai"]
-    script = _scenario_script("chat.editUserMessage(target)", roles, 0, True, _EDIT_AND_SEND)
-    result = _run_node(script)
-    assert result["confirmShown"] is False
-    assert result["truncateCalled"] is True
-    assert result["truncateKeepCount"] == 0
-    assert result["sendClicks"] == ["edited question"]
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_edit_earlier_message_prompts_with_correct_count():
-    roles = ["user", "ai", "user", "ai", "user", "ai"]  # target (index 2) has 2 messages after its own pair
-    script = _scenario_script("chat.editUserMessage(target)", roles, 2, True, _EDIT_AND_SEND)
-    result = _run_node(script)
-    assert result["confirmShown"] is True
-    assert "2 messages" in result["confirmMessage"]
-    assert result["confirmOpts"]["confirmText"] == "Delete and send"
-    assert result["truncateCalled"] is True
-    assert result["truncateKeepCount"] == 2
-    assert result["sendClicks"] == ["edited question"]
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_edit_earlier_message_cancel_aborts_without_truncating_or_sending():
-    roles = ["user", "ai", "user", "ai"]
-    script = _scenario_script("chat.editUserMessage(target)", roles, 0, False, _EDIT_AND_SEND)
-    result = _run_node(script)
-    assert result["confirmShown"] is True
-    assert result["truncateCalled"] is False
-    assert result["sendClicks"] == []
-
-
-# ---------------------------------------------------------------------------
-# "Fork from here" — the prompt's alternate choice
-# ---------------------------------------------------------------------------
-# styledConfirm resolves to 'alternate' for its third button. Forking must
-# not truncate anything; it forks just before the user turn (so the new chat
-# ends where the action starts), switches to the fork, and replays there.
-
-def _assert_forked_instead(result, keep_count, sent_text):
-    assert result["confirmShown"] is True
-    assert result["confirmOpts"]["alternateText"] == "Fork from here"
-    assert result["truncateCalled"] is False
-    assert result["forkCalled"] is True
-    assert "/api/session/test-session/fork" in result["forkUrl"]
-    assert result["forkKeepCount"] == keep_count
-    assert result["selectedSessions"] == ["forked-session"]
-    assert result["sendClicks"] == [sent_text]
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_regenerate_fork_choice_forks_before_user_turn_and_resends():
-    roles = ["user", "ai", "user", "ai", "user", "ai"]
-    script = _scenario_script("chat.regenerateFrom(target)", roles, 3, "alternate")
-    _assert_forked_instead(_run_node(script), keep_count=2, sent_text="question 2")
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_resend_fork_choice_forks_before_user_turn_and_resends():
-    roles = ["user", "ai", "user", "ai", "user", "ai"]
-    script = _scenario_script("chat.resendUserMessage(target)", roles, 2, "alternate")
-    _assert_forked_instead(_run_node(script), keep_count=2, sent_text="question 2")
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_edit_fork_choice_forks_before_user_turn_and_sends_edit():
-    roles = ["user", "ai", "user", "ai", "user", "ai"]
-    script = _scenario_script("chat.editUserMessage(target)", roles, 2, "alternate", _EDIT_AND_SEND)
-    _assert_forked_instead(_run_node(script), keep_count=2, sent_text="edited question")
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_regenerate_fork_choice_keeps_the_user_message_attachments():
-    roles = ["user", "ai", "user", "ai", "user", "ai"]
-    script = _scenario_script("chat.regenerateFrom(target)", roles, 3, "alternate", file_ids={2: "file-abc"})
-    result = _run_node(script)
-    _assert_forked_instead(result, keep_count=2, sent_text="question 2")
-    assert result["sentAttachments"] == [["file-abc"]]
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_resend_fork_choice_keeps_the_user_message_attachments():
-    roles = ["user", "ai", "user", "ai", "user", "ai"]
-    script = _scenario_script("chat.resendUserMessage(target)", roles, 2, "alternate", file_ids={2: "file-abc"})
-    result = _run_node(script)
-    _assert_forked_instead(result, keep_count=2, sent_text="question 2")
-    assert result["sentAttachments"] == [["file-abc"]]
-
-
-# ---------------------------------------------------------------------------
-# Cutting by message id
-# ---------------------------------------------------------------------------
-# A long chat loads only its newest messages until the user scrolls up, so a
-# position counted in the page is smaller than the real one. Truncating by
-# that position deleted real messages above the clicked one. Every action
-# sends the clicked message's database id when it has one.
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_regenerate_truncates_before_the_user_message_by_id():
-    roles = ["user", "ai", "user", "ai"]
-    script = _scenario_script("chat.regenerateFrom(target)", roles, 3, True, db_ids=True)
-    result = _run_node(script)
-    assert result["truncateBody"] == {"before_msg_id": "db-42"}
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_resend_truncates_before_the_user_message_by_id():
-    roles = ["user", "ai", "user", "ai"]
-    script = _scenario_script("chat.resendUserMessage(target)", roles, 2, True, db_ids=True)
-    result = _run_node(script)
-    assert result["truncateBody"] == {"before_msg_id": "db-42"}
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_edit_truncates_before_the_user_message_by_id():
-    roles = ["user", "ai", "user", "ai"]
-    script = _scenario_script("chat.editUserMessage(target)", roles, 2, True, _EDIT_AND_SEND, db_ids=True)
-    result = _run_node(script)
-    assert result["truncateBody"] == {"before_msg_id": "db-42"}
-    assert result["sendClicks"] == ["edited question"]
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_fork_choice_forks_before_the_user_message_by_id():
-    roles = ["user", "ai", "user", "ai", "user", "ai"]
-    script = _scenario_script("chat.regenerateFrom(target)", roles, 3, "alternate", db_ids=True)
-    result = _run_node(script)
-    assert result["truncateCalled"] is False
-    assert result["forkBody"]["before_msg_id"] == "db-42"
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_fork_conversation_forks_through_the_reply_by_id():
-    roles = ["user", "ai", "user", "ai"]
-    script = _scenario_script("chat.forkFrom(target)", roles, 1, True, db_ids=True)
-    result = _run_node(script)
-    assert result["forkBody"]["through_msg_id"] == "db-41"
-
-
-# A refused cut (the server can't find the message id, e.g. one a previous
-# regenerate already deleted) must stop the action. Sending anyway stacked a
-# second reply under the same message.
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_regenerate_stops_when_the_server_refuses_the_cut():
-    roles = ["user", "ai"]
-    script = _scenario_script("chat.regenerateFrom(target)", roles, 1, True, db_ids=True, refuse_truncate=True)
-    result = _run_node(script)
-    assert result["truncateCalled"] is True
-    assert result["sendClicks"] == []
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_edit_stops_when_the_server_refuses_the_cut():
-    roles = ["user", "ai"]
-    script = _scenario_script("chat.editUserMessage(target)", roles, 0, True, _EDIT_AND_SEND, db_ids=True, refuse_truncate=True)
-    result = _run_node(script)
-    assert result["truncateCalled"] is True
-    assert result["sendClicks"] == []
-
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_edit_fork_choice_keeps_original_attachments():
-    roles = ["user", "ai", "user", "ai", "user", "ai"]
-    script = _scenario_script("chat.editUserMessage(target)", roles, 2, "alternate", _EDIT_AND_SEND, file_ids={2: "file-abc"})
-    result = _run_node(script)
-    _assert_forked_instead(result, keep_count=2, sent_text="edited question")
-    assert result["sentAttachments"] == [["file-abc"]]
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_edit_destructive_resend_keeps_original_attachments():
-    roles = ["user", "ai", "user", "ai"]
-    script = _scenario_script("chat.editUserMessage(target)", roles, 2, True, _EDIT_AND_SEND, file_ids={2: "file-abc"})
-    result = _run_node(script)
-    assert result["truncateCalled"] is True
-    assert result["sentAttachments"] == [["file-abc"]]
-
-
-@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
-def test_refused_regenerate_does_not_leak_queued_attachments():
-    roles = ["user", "ai"]
-    script = _scenario_script("chat.regenerateFrom(target)", roles, 1, True, db_ids=True,
-                              refuse_truncate=True, file_ids={0: "file-abc"})
-    result = _run_node(script)
-    assert result["truncateCalled"] is True
-    assert result["sendClicks"] == []
-    assert result["pendingAttachments"] is None

tests/test_review_regressions.py

@@ -2,7 +2,6 @@
 
 import importlib
 import json
-import os
 import sys
 import types
 from types import SimpleNamespace
@@ -1203,7 +1202,7 @@ async def test_write_file_inline_json_args(monkeypatch):
     for b in blocks:
         await _execute_without_run_context(execute_tool_block, b, owner="admin", workspace="/tmp")
 
-    assert captured.get("path") in ("/tmp/wf.txt", os.path.abspath("/tmp/wf.txt")), (
+    assert captured.get("path") == "/tmp/wf.txt", (
         f"write_file did not decode inline JSON args; got path {captured.get('path')!r}"
     )
 

tests/test_service_health_collect.py

@@ -137,170 +137,3 @@ def test_collect_aggregate_deadline_yields_controlled_result(monkeypatch):
     net = [s for s in out["services"] if s["name"] != "chromadb"]
     assert all(s["status"] == sh.DOWN and s["meta"].get("error") == "timeout"
                for s in net)
-
-
-# ── Discovery failure is not "disabled" (#6154) ──
-#
-# `_gather_inputs()` fails soft to an empty inventory, and every probe reads an
-# empty inventory as `disabled`. Without a record of *why* it is empty, a broken
-# integrations file / email store / endpoint DB is reported as an intentionally
-# unconfigured subsystem — and, with the rest disabled, `overall: "ok"`.
-
-def _boom(*_a, **_k):
-    raise RuntimeError("secret-bearing detail: postgres://u:p@db/x")
-
-
-def test_gather_inputs_records_each_failed_source(monkeypatch):
-    import core.database
-    import routes.email_helpers
-    import src.integrations
-    import src.settings
-
-    monkeypatch.setattr(src.settings, "load_settings", lambda: {"a": 1})
-    monkeypatch.setattr(src.integrations, "load_integrations", _boom)
-    monkeypatch.setattr(routes.email_helpers, "_list_email_accounts", _boom)
-    monkeypatch.setattr(core.database, "SessionLocal", _boom)
-
-    out = sh._gather_inputs()
-    assert out["settings"] == {"a": 1}
-    assert set(out["failed"]) == {"integrations", "accounts", "endpoints"}
-    # Controlled categories only — never the exception text.
-    assert set(out["failed"].values()) <= set(sh._ERROR_DETAIL)
-    assert "postgres" not in repr(out)
-
-
-def test_gather_inputs_reports_no_failures_when_sources_load(monkeypatch):
-    import core.database
-    import routes.email_helpers
-    import src.integrations
-    import src.settings
-
-    class _DB:
-        def query(self, *_a):
-            return self
-
-        def filter(self, *_a):
-            return self
-
-        def all(self):
-            return []
-
-        def close(self):
-            pass
-
-    monkeypatch.setattr(src.settings, "load_settings", lambda: {})
-    monkeypatch.setattr(src.integrations, "load_integrations", lambda: [])
-    monkeypatch.setattr(routes.email_helpers, "_list_email_accounts", lambda: [])
-    monkeypatch.setattr(core.database, "SessionLocal", lambda: _DB())
-
-    assert sh._gather_inputs()["failed"] == {}
-
-
-@pytest.mark.parametrize("source,service", [
-    ("settings", "searxng"),
-    ("integrations", "ntfy"),
-    ("accounts", "email"),
-    ("endpoints", "providers"),
-])
-def test_failed_source_is_not_reported_as_disabled(monkeypatch, source, service):
-    import asyncio
-    monkeypatch.setattr(sh, "_gather_inputs", lambda: {
-        "settings": {"search_provider": "disabled"},
-        "integrations": [], "accounts": [], "endpoints": [],
-        "failed": {source: "network_error"},
-    })
-    out = asyncio.run(sh.collect_service_health(None, None))
-    entry = next(s for s in out["services"] if s["name"] == service)
-    assert entry["status"] != sh.DISABLED
-    assert entry["meta"]["error"] == sh.CONFIG_SOURCE_ERROR
-    assert entry["meta"]["source"] == source
-    assert entry["meta"]["source_error"] == "network_error"
-    # A failed source must reach the aggregate verdict.
-    assert out["overall"] != sh.OK
-    assert set(out) == {"overall", "services", "timestamp"}
-
-
-def test_all_sources_failing_cannot_report_overall_ok(monkeypatch):
-    # The exact shape from the report: settings loads and says search is off,
-    # the other three sources raise. Before the fix this was overall "ok" with
-    # five "disabled" entries.
-    import asyncio
-    monkeypatch.setattr(sh, "_gather_inputs", lambda: {
-        "settings": {"search_provider": "disabled"},
-        "integrations": [], "accounts": [], "endpoints": [],
-        "failed": {"integrations": "error", "accounts": "error",
-                   "endpoints": "error"},
-    })
-    out = asyncio.run(sh.collect_service_health(None, None))
-    by_name = {s["name"]: s for s in out["services"]}
-    assert out["overall"] == sh.DEGRADED
-    # Loaded-and-genuinely-empty still reads as disabled.
-    assert by_name["searxng"]["status"] == sh.DISABLED
-    for name in ("ntfy", "email", "providers"):
-        assert by_name[name]["status"] == sh.DEGRADED
-
-
-def test_empty_inventory_without_failure_stays_disabled(monkeypatch):
-    import asyncio
-    monkeypatch.setattr(sh, "_gather_inputs", lambda: {
-        "settings": {"search_provider": "disabled"},
-        "integrations": [], "accounts": [], "endpoints": [], "failed": {},
-    })
-    out = asyncio.run(sh.collect_service_health(_Store(True), _Store(True)))
-    assert out["overall"] == sh.OK
-    assert all(s["status"] == sh.DISABLED
-               for s in out["services"] if s["name"] != "chromadb")
-
-
-def test_one_failed_source_still_probes_the_others(monkeypatch):
-    # A broken endpoint DB must not stop ntfy/email from being probed.
-    import asyncio
-    probed = []
-
-    def _probe(name):
-        def _fn(*_a, **_k):
-            probed.append(name)
-            return sh._svc(name, sh.OK, "probed")
-        return _fn
-
-    monkeypatch.setattr(sh, "_gather_inputs", lambda: {
-        "settings": {}, "integrations": [], "accounts": [], "endpoints": [],
-        "failed": {"endpoints": "timeout"},
-    })
-    monkeypatch.setattr(sh, "searxng_health", _probe("searxng"))
-    monkeypatch.setattr(sh, "ntfy_health", _probe("ntfy"))
-    monkeypatch.setattr(sh, "email_health", _probe("email"))
-    monkeypatch.setattr(sh, "providers_health", _probe("providers"))
-
-    out = asyncio.run(sh.collect_service_health(None, None))
-    assert sorted(probed) == ["email", "ntfy", "searxng"]
-    assert "providers" not in probed
-    by_name = {s["name"]: s for s in out["services"]}
-    assert by_name["providers"]["status"] == sh.DEGRADED
-    assert by_name["ntfy"]["status"] == sh.OK
-
-
-def test_source_failure_entry_carries_no_raw_detail(monkeypatch):
-    import asyncio
-    monkeypatch.setattr(sh, "_gather_inputs", lambda: {
-        "settings": {}, "integrations": [], "accounts": [], "endpoints": [],
-        "failed": {"accounts": "auth_or_protocol_error"},
-    })
-    out = asyncio.run(sh.collect_service_health(None, None))
-    entry = next(s for s in out["services"] if s["name"] == "email")
-    assert entry["detail"] == (
-        "Could not read configuration (configuration source could not be read).")
-    assert set(entry["meta"]) == {"error", "source", "source_error"}
-
-
-def test_collect_tolerates_inputs_without_a_failed_key(monkeypatch):
-    # `_gather_inputs()` is monkeypatched in a number of existing tests (and by
-    # anything calling the collector with a stub); a payload predating `failed`
-    # must still probe normally rather than raise.
-    import asyncio
-    monkeypatch.setattr(sh, "_gather_inputs", lambda: {
-        "settings": {"search_provider": "disabled"},
-        "integrations": [], "accounts": [], "endpoints": [],
-    })
-    out = asyncio.run(sh.collect_service_health(_Store(True), _Store(True)))
-    assert out["overall"] == sh.OK

tests/test_session_search.py

@@ -8,7 +8,7 @@ from sqlalchemy.orm import sessionmaker
 from core.database import Base
 from core.database import ChatMessage as DbChatMessage
 from core.database import Session as DbSession
-from src.session_search import SessionSearchResult, _snippet, search_session_messages
+from src.session_search import SessionSearchResult, search_session_messages
 
 
 def _db(with_fts=True):
@@ -61,47 +61,6 @@ def _has_fts(db):
     )
 
 
-def test_snippet_locates_quoted_phrase_instead_of_raw_query():
-    content = "A" * 100 + "The session search result is useful." + "Z" * 100
-
-    snippet = _snippet(content, '"session search"', radius=20)
-
-    assert "session search" in snippet
-    assert snippet.startswith("...")
-    assert snippet.endswith("...")
-
-
-def test_snippet_locates_punctuation_bearing_term_case_insensitively():
-    content = "A" * 100 + "Use FOO_BAR.py for routing." + "Z" * 100
-
-    snippet = _snippet(content, "foo_bar.py!", radius=20)
-
-    assert "FOO_BAR.py" in snippet
-
-
-def test_snippet_uses_first_meaningful_matching_term():
-    content = "A" * 100 + "second appears here; first appears later." + "Z" * 100
-
-    snippet = _snippet(content, "first second", radius=12)
-
-    assert "second appears" in snippet
-    assert "first appears" not in snippet
-
-
-def test_snippet_falls_back_to_content_start_when_no_term_matches():
-    content = "Beginning of the transcript, followed by more detail."
-
-    assert _snippet(content, '"missing phrase"', radius=10) == content[:20]
-
-
-def test_snippet_preserves_boundary_markers_and_truncation():
-    content = "A" * 50 + "target" + "Z" * 50
-
-    snippet = _snippet(content, "target", radius=5)
-
-    assert snippet == "...AAAAAtargetZZZZZ..."
-
-
 def test_session_search_uses_fts_and_returns_context():
     db = _db(with_fts=True)
     try:

tests/test_skill_frontmatter_list_escapes.py

@@ -1,54 +0,0 @@
-"""Inline frontmatter lists must preserve quoted values across save/load cycles."""
-
-import importlib.util
-from pathlib import Path
-import sys
-import unittest
-
-
-# Load the dependency-free formatter without starting the services package.
-_PATH = Path(__file__).resolve().parents[1] / "services" / "memory" / "skill_format.py"
-_SPEC = importlib.util.spec_from_file_location("_skill_list_format_under_test", _PATH)
-_FORMAT = importlib.util.module_from_spec(_SPEC)
-sys.modules[_SPEC.name] = _FORMAT
-_SPEC.loader.exec_module(_FORMAT)
-
-
-class FrontmatterListEscapesTests(unittest.TestCase):
-    def test_skill_tags_survive_repeated_save_load_cycles(self):
-        tags = ['review "release, notes', 'use "search", then summarize', 'publish']
-        skill = _FORMAT.Skill(name="release-review", tags=tags)
-        for _ in range(5):
-            skill = _FORMAT.Skill.from_markdown(skill.to_markdown())
-            self.assertEqual(skill.tags, tags)
-
-    def test_escaped_quotes_preserve_each_list_field(self):
-        for field in ("tags", "platforms", "requires_toolsets", "fallback_for_toolsets"):
-            with self.subTest(field=field):
-                values = ['review "release, notes', 'publish']
-                skill = _FORMAT.Skill(name="release-review", **{field: values})
-                restored = _FORMAT.Skill.from_markdown(skill.to_markdown())
-                self.assertEqual(getattr(restored, field), values)
-
-    def test_backslash_parity_does_not_hide_quotes_or_list_separators(self):
-        for count in range(1, 5):
-            with self.subTest(backslashes=count):
-                values = ['review ' + '\\' * count + '"release, notes', 'path, ' + '\\' * count, 'publish']
-                text = _FORMAT.emit_frontmatter({"tags": values})
-                parsed, _ = _FORMAT.parse_frontmatter(f"---\n{text}\n---\n")
-                self.assertEqual(parsed["tags"], values)
-
-    def test_single_quoted_backslashes_remain_literal(self):
-        text = "---\ntags: ['C:\\', next]\n---\n"
-        parsed, _ = _FORMAT.parse_frontmatter(text)
-        self.assertEqual(parsed["tags"], ["C:\\", "next"])
-
-    def test_nested_lists_preserve_quoted_brackets_and_commas(self):
-        values = [['review "], notes', 'publish'], 'archive']
-        text = _FORMAT.emit_frontmatter({"tags": values})
-        parsed, _ = _FORMAT.parse_frontmatter(f"---\n{text}\n---\n")
-        self.assertEqual(parsed["tags"], values)
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/test_skill_rename_collision.py

@@ -1,83 +0,0 @@
-"""Renaming a skill onto a name the owner already uses must be refused.
-
-``update_skill`` only checked whether the target directory existed. A
-skill in another category with the wanted name lives in a different
-directory, so the rename went through and the owner ended up with two
-skills sharing one name. Update and delete look skills up by name, so the
-next DELETE removed whichever of the two ``os.walk`` reached first, which
-was often the one the user did not pick.
-"""
-import pytest
-
-from routes.skills_routes import SkillUpdateRequest, setup_skills_routes
-from services.memory.skills import SkillsManager
-
-from tests.test_skills_routes_owner_update import _request, _route_handler, _write_skill_md
-
-
-def _two_skills(tmp_path, owner="alice"):
-    mgr = SkillsManager(str(tmp_path))
-    mgr.add_skill(name="deploy-app", description="Deploy the web app", category="ops",
-                  source="user", procedure=["ship it"], owner=owner)
-    mgr.add_skill(name="draft-notes", description="Draft meeting notes", category="writing",
-                  source="user", procedure=["write"], owner=owner)
-    return mgr
-
-
-def _names(mgr, owner="alice"):
-    return sorted((s["name"], s["category"]) for s in mgr.load(owner=owner))
-
-
-def test_rename_onto_a_name_in_another_category_is_refused(tmp_path):
-    mgr = _two_skills(tmp_path)
-
-    assert mgr.update_skill("draft-notes", {"name": "deploy-app"}, owner="alice") is False
-    assert _names(mgr) == [("deploy-app", "ops"), ("draft-notes", "writing")]
-
-
-def test_delete_after_refused_rename_removes_only_the_named_skill(tmp_path):
-    mgr = _two_skills(tmp_path)
-    mgr.update_skill("draft-notes", {"name": "deploy-app"}, owner="alice")
-
-    assert mgr.delete_skill("draft-notes", owner="alice") is True
-    assert _names(mgr) == [("deploy-app", "ops")]
-
-
-def test_rename_to_a_free_name_still_moves_the_skill(tmp_path):
-    mgr = _two_skills(tmp_path)
-
-    assert mgr.update_skill("draft-notes", {"name": "meeting-notes"}, owner="alice") is True
-    assert _names(mgr) == [("deploy-app", "ops"), ("meeting-notes", "writing")]
-
-
-def test_another_owners_skill_does_not_block_the_rename(tmp_path):
-    skills_root = tmp_path / "skills"
-    _write_skill_md(skills_root, "bob-cat", "caveman-mode", "bob")
-    _write_skill_md(skills_root, "alice-cat", "terse-mode", "alice")
-    mgr = SkillsManager(str(tmp_path))
-
-    assert mgr.update_skill("terse-mode", {"name": "caveman-mode"}, owner="alice") is True
-    assert [s["name"] for s in mgr.load(owner="alice")] == ["caveman-mode"]
-    assert [s["name"] for s in mgr.load(owner="bob")] == ["caveman-mode"]
-
-
-def test_keeping_the_same_name_is_not_a_conflict(tmp_path):
-    mgr = _two_skills(tmp_path)
-
-    assert mgr.update_skill("draft-notes", {"name": "Draft Notes", "status": "published"},
-                            owner="alice") is True
-    assert [s["status"] for s in mgr.load(owner="alice") if s["name"] == "draft-notes"] == ["published"]
-
-
-@pytest.mark.asyncio
-async def test_put_route_answers_409_for_a_taken_name(tmp_path):
-    from fastapi import HTTPException
-
-    mgr = _two_skills(tmp_path)
-    update_route = _route_handler(setup_skills_routes(mgr), "/api/skills/{skill_id}", "PUT")
-
-    with pytest.raises(HTTPException) as exc:
-        await update_route(_request("alice"), "draft-notes", SkillUpdateRequest(name="deploy-app"))
-
-    assert exc.value.status_code == 409
-    assert _names(mgr) == [("deploy-app", "ops"), ("draft-notes", "writing")]

tests/test_streamed_tool_markup.py

@@ -27,102 +27,3 @@ def test_dsml_tool_markup_strips_to_empty_visible_text():
 def test_chunk_split_tool_call_prefix_is_buffered_and_not_persisted():
     assert _streamed_tool_markup_starts('I will search<tool_cal')
     assert _strip_incomplete_tool_markup_tail('I will search<tool_cal') == 'I will search'
-
-
-def test_bare_less_than_and_comparison_operators_false_alarm_recognition():
-    # A bare "<" starts buffering because it could be a tool-call tag prefix like "<tool_call>"
-    assert _streamed_tool_markup_starts(' <')
-    assert _streamed_tool_markup_starts('x <')
-    assert _streamed_tool_markup_starts('<tool_call')
-    assert _streamed_tool_markup_starts('<invoke')
-
-    # Once subsequent characters arrive and cannot become a tool-call tag, false alarm is detected
-    assert not _streamed_tool_markup_starts(' < 2')
-    assert not _streamed_tool_markup_starts('x < 2')
-    assert not _streamed_tool_markup_starts('len(items) < 2')
-    assert not _streamed_tool_markup_starts(' < 2:')
-    assert not _streamed_tool_markup_starts('x <= y')
-    assert not _streamed_tool_markup_starts('a < b')
-
-
-async def test_stream_agent_loop_does_not_truncate_at_less_than_operator(monkeypatch):
-    import json
-    import src.agent_loop as al
-
-    async def fake_stream(*args, **kwargs):
-        for d in ["def is_short(items):\n", "    return len(items)", " <", " 2\n"]:
-            yield "data: " + json.dumps({"delta": d}) + "\n\n"
-        yield "data: [DONE]\n\n"
-
-    monkeypatch.setattr(al, "get_setting", lambda k, d=None: d, raising=False)
-    monkeypatch.setattr(al, "get_mcp_manager", lambda: None, raising=False)
-    monkeypatch.setattr(al, "estimate_tokens", lambda *a, **k: 10, raising=False)
-    monkeypatch.setattr(al, "stream_llm_with_fallback", fake_stream, raising=False)
-
-    deltas = []
-    async for chunk in al.stream_agent_loop(
-        "http://local.test/v1",
-        "qwen3.6-35b-a3b-heretic",
-        [{"role": "user", "content": "Write python function"}],
-        max_rounds=1,
-        owner="test_user",
-    ):
-        for line in chunk.split("\n"):
-            line = line.strip()
-            if line.startswith("data: ") and line[6:] != "[DONE]":
-                try:
-                    payload = json.loads(line[6:])
-                    if "delta" in payload:
-                        deltas.append(payload["delta"])
-                except Exception:
-                    pass
-
-    full_text = "".join(deltas)
-    assert full_text == "def is_short(items):\n    return len(items) < 2\n"
-
-
-async def test_stream_agent_loop_still_hides_real_tool_markup(monkeypatch):
-    import json
-    import src.agent_loop as al
-
-    async def fake_stream(*args, **kwargs):
-        chunks = [
-            "Sure.",
-            " <",
-            "tool",
-            "_call",
-            '>{"name":"host_shell","arguments":{"command":"pwd"}}',
-            "</",
-            "tool",
-            "_call",
-            ">",
-            " done",
-        ]
-        for c in chunks:
-            yield "data: " + json.dumps({"delta": c}) + "\n\n"
-        yield "data: [DONE]\n\n"
-
-    monkeypatch.setattr(al, "get_setting", lambda k, d=None: d, raising=False)
-    monkeypatch.setattr(al, "get_mcp_manager", lambda: None, raising=False)
-    monkeypatch.setattr(al, "estimate_tokens", lambda *a, **k: 10, raising=False)
-    monkeypatch.setattr(al, "stream_llm_with_fallback", fake_stream, raising=False)
-
-    deltas = []
-    async for chunk in al.stream_agent_loop(
-        "http://local.test/v1",
-        "qwen3.6-35b-a3b-heretic",
-        [{"role": "user", "content": "run command"}],
-        max_rounds=1,
-        owner="test_user",
-    ):
-        for line in chunk.split("\n"):
-            line = line.strip()
-            if line.startswith("data: ") and line[6:] != "[DONE]":
-                try:
-                    payload = json.loads(line[6:])
-                    if "delta" in payload:
-                        deltas.append(payload["delta"])
-                except Exception:
-                    pass
-
-    assert "".join(deltas) == "Sure. done"

tests/test_tab_stream_rejoin_static.py

@@ -2,7 +2,7 @@ from pathlib import Path
 
 
 ROOT = Path(__file__).resolve().parents[1]
-CHAT = (ROOT / "static/js/chat.js").read_text(encoding="utf-8")
+CHAT = (ROOT / "static/js/chat.js").read_text()
 
 
 def _visibility_handler() -> str:

tests/test_tool_path_confinement.py

@@ -28,11 +28,6 @@ def standalone_dispatch_authority(monkeypatch):
                         server_authorized_executor(tool_execution.execute_tool_block))
 
 
-def _native(path: str) -> str:
-    """POSIX-style literal -> native separators (the policy splits on os.sep)."""
-    return path.replace("/", os.sep)
-
-
 def _make_block(tool_type, content):
     return SimpleNamespace(tool_type=tool_type, content=content)
 
@@ -41,27 +36,27 @@ def _make_block(tool_type, content):
 
 def test_sensitive_ssh_dir():
     from src.tool_execution import _is_sensitive_path
-    assert _is_sensitive_path(_native("/home/user/.ssh/authorized_keys"))
+    assert _is_sensitive_path("/home/user/.ssh/authorized_keys")
-    assert _is_sensitive_path(_native(os.path.expanduser("~") + "/.ssh/config"))
+    assert _is_sensitive_path(os.path.expanduser("~") + "/.ssh/config")
 
 
 def test_sensitive_gnupg_dir():
     from src.tool_execution import _is_sensitive_path
-    assert _is_sensitive_path(_native("/home/user/.gnupg/pubring.kbx"))
+    assert _is_sensitive_path("/home/user/.gnupg/pubring.kbx")
 
 
 def test_sensitive_shell_rc():
     from src.tool_execution import _is_sensitive_path
-    assert _is_sensitive_path(_native("/home/user/.bashrc"))
+    assert _is_sensitive_path("/home/user/.bashrc")
-    assert _is_sensitive_path(_native("/home/user/.zshrc"))
+    assert _is_sensitive_path("/home/user/.zshrc")
-    assert _is_sensitive_path(_native("/home/user/.profile"))
+    assert _is_sensitive_path("/home/user/.profile")
 
 
 def test_sensitive_key_filenames():
     from src.tool_execution import _is_sensitive_path
-    assert _is_sensitive_path(_native("/tmp/id_rsa"))
+    assert _is_sensitive_path("/tmp/id_rsa")
-    assert _is_sensitive_path(_native("/tmp/id_ed25519"))
+    assert _is_sensitive_path("/tmp/id_ed25519")
-    assert _is_sensitive_path(_native("/tmp/authorized_keys"))
+    assert _is_sensitive_path("/tmp/authorized_keys")
 
 
 def test_non_sensitive_path():
@@ -191,11 +186,9 @@ def test_allows_agent_workspace(tmp_path):
         os.unlink(target)
 
 
-def test_allows_tmp(tmp_path, monkeypatch):
+def test_allows_tmp(tmp_path):
     """Paths under /tmp (or its realpath) must resolve cleanly."""
     from src.tool_execution import _resolve_tool_path
-    # Windows has no /tmp; its temp root is only allowed via $TMPDIR.
-    monkeypatch.setenv("TMPDIR", str(tmp_path))
     f = tmp_path / "confinement-test.txt"
     f.write_text("ok")
     resolved = _resolve_tool_path(str(f))
@@ -365,4 +358,4 @@ async def test_write_file_dispatch_blocks_cron(monkeypatch):
 def test_application_secrets_are_sensitive_paths(filename):
     from src.tool_execution import _is_sensitive_path
 
-    assert _is_sensitive_path(_native(f"/tmp/odysseus-data/{filename}"))
+    assert _is_sensitive_path(f"/tmp/odysseus-data/{filename}")

tests/test_vision_description_provenance.py

@@ -1,132 +0,0 @@
-"""Issue #5573 — the vision model's description must not read as the user's own words.
-
-For a text-only chat model the description comes from a separate vision call and
-is appended to the user's message. Unlabelled, the chat model answers the prose
-instead of the image — reviewing the user's "writing" back to them.
-"""
-
-import importlib
-from types import SimpleNamespace
-
-import pytest
-
-DESCRIPTION = "A chocolate cake, plated with a mirror glaze and gold leaf."
-QUESTION = "What am I looking at?"
-
-
-class _UploadHandler:
-    def __init__(self, file_info):
-        self._file_info = file_info
-
-    def resolve_upload(self, att_id, owner=None):
-        return self._file_info if att_id == self._file_info["id"] else None
-
-    def is_image_file(self, *_args, **_kwargs):
-        return True
-
-
-def _no_vision_call(*_args, **_kwargs):
-    raise AssertionError("the vision model must not be called on this path")
-
-
-@pytest.fixture
-def vision_env(monkeypatch, tmp_path):
-    """Text-only chat model with one image attachment, no DB and no real vision call.
-
-    Other tests drop src.chat_handler from sys.modules, so resolve it here rather
-    than at import time — otherwise the patches land on a different module object
-    than the one under test.
-    """
-    module = importlib.import_module("src.chat_handler")
-    monkeypatch.setattr(module, "UPLOAD_DIR", str(tmp_path))
-    monkeypatch.setattr(module, "model_supports_vision", lambda *a, **k: False)
-    monkeypatch.setattr(module, "_sync_upload_vision_to_gallery", lambda *a, **k: None)
-    monkeypatch.setattr(module, "build_user_content", lambda text, *a, **k: text)
-    monkeypatch.setattr(
-        importlib.import_module("src.settings"), "get_setting", lambda key, default=None: default
-    )
-    return SimpleNamespace(module=module, tmp_path=tmp_path, file_info={
-        "id": "img-1", "name": "cake.jpg", "path": str(tmp_path / "cake.jpg"),
-        "mime": "image/jpeg", "size": 1, "hash": "h",
-    })
-
-
-async def _preprocess(env):
-    handler = env.module.ChatHandler(
-        session_manager=None, memory_manager=None, chat_processor=None,
-        research_handler=None, preset_manager=None,
-        upload_handler=_UploadHandler(env.file_info),
-    )
-    sess = SimpleNamespace(model="chat-model", endpoint_url="", owner="user", id="s1")
-    enhanced, *_ = await handler.preprocess_message(
-        QUESTION, ["img-1"], sess, auto_opened_docs=[],
-    )
-    return enhanced
-
-
-def _describe(env, monkeypatch, text):
-    monkeypatch.setattr(env.module, "analyze_image_with_vl_result",
-                        lambda *a, **k: {"text": text, "model": "vl-model"})
-
-
-def _label_above(enhanced, description):
-    """The line the description is introduced by."""
-    return enhanced.split(description)[0].rstrip("\n").rsplit("\n", 1)[-1]
-
-
-@pytest.mark.asyncio
-async def test_description_is_marked_as_not_the_users_message(vision_env, monkeypatch):
-    _describe(vision_env, monkeypatch, DESCRIPTION)
-    enhanced = await _preprocess(vision_env)
-
-    assert QUESTION in enhanced, "the user's own words must survive untouched"
-    label = _label_above(enhanced, DESCRIPTION)
-    assert label.startswith("[") and "user" in label.lower(), (
-        "the description is appended as bare prose, so the chat model reads it as "
-        f"the user's own writing. Got:\n{enhanced}"
-    )
-
-
-@pytest.mark.asyncio
-async def test_cached_description_is_labelled_too(vision_env, monkeypatch):
-    """The cache holds an auto description or a hand-corrected one, and the label
-    has to be true either way — it is a description of the image regardless."""
-    cache = vision_env.tmp_path / ".vision"
-    cache.mkdir()
-    (cache / "img-1.txt").write_text(DESCRIPTION, encoding="utf-8")
-    monkeypatch.setattr(vision_env.module, "analyze_image_with_vl_result", _no_vision_call)
-
-    enhanced = await _preprocess(vision_env)
-
-    label = _label_above(enhanced, DESCRIPTION)
-    assert label.startswith("[") and "user" in label.lower(), (
-        f"a cached description is injected with no label. Got:\n{enhanced}"
-    )
-
-
-@pytest.mark.asyncio
-async def test_client_side_image_marker_is_preserved(vision_env, monkeypatch):
-    """chatRenderer.js and sessions.js strip the block by matching `[Image: <name>]\\n`.
-
-    Renaming that marker leaves the raw description rendered in the user's bubble.
-    """
-    _describe(vision_env, monkeypatch, DESCRIPTION)
-    assert "[Image: cake.jpg]\n" in await _preprocess(vision_env)
-
-
-@pytest.mark.asyncio
-async def test_no_dangling_label_when_the_vision_model_returns_nothing(vision_env, monkeypatch):
-    _describe(vision_env, monkeypatch, "")
-    enhanced = await _preprocess(vision_env)
-    assert enhanced.endswith("[Image: cake.jpg]\n"), (
-        "an empty description must leave the bare marker, trailing newline included "
-        f"— the client's strip regex needs it. Got:\n{enhanced!r}"
-    )
-
-
-@pytest.mark.asyncio
-async def test_vision_capable_model_path_is_unchanged(vision_env, monkeypatch):
-    monkeypatch.setattr(vision_env.module, "model_supports_vision", lambda *a, **k: True)
-    monkeypatch.setattr(vision_env.module, "analyze_image_with_vl_result", _no_vision_call)
-
-    assert await _preprocess(vision_env) == f"{QUESTION}\n\n[Image attached: cake.jpg]"

tests/test_visual_report_mobile_toolbar.py

@@ -5,7 +5,7 @@ from bs4 import BeautifulSoup
 from src.visual_report import generate_visual_report
 
 
-SOURCE = (Path(__file__).resolve().parents[1] / "src/visual_report.py").read_text(encoding="utf-8")
+SOURCE = (Path(__file__).resolve().parents[1] / "src/visual_report.py").read_text()
 
 
 def test_export_bookmark_is_anchored_and_expands_on_demand():

tests/test_web_search_tool_not_clickable_static.py

@@ -2,8 +2,8 @@ from pathlib import Path
 
 
 ROOT = Path(__file__).resolve().parents[1]
-RENDERER = (ROOT / "static/js/chatRenderer.js").read_text(encoding="utf-8")
+RENDERER = (ROOT / "static/js/chatRenderer.js").read_text()
-CHAT = (ROOT / "static/js/chat.js").read_text(encoding="utf-8")
+CHAT = (ROOT / "static/js/chat.js").read_text()
 
 
 def test_saved_web_search_tool_icon_has_no_action_target():