fix(hwfit): distinguish Apple Silicon bandwidth variants (#2564)

* fix: resolve Apple Silicon bandwidth variants

* fix(hwfit): preserve string lookup path in _lookup_bandwidth

* fix(hwfit): guard Apple bandwidth lookup against false GPU matches

Add "apple" not in gn check to _lookup_apple_bandwidth() so that
non-Apple GPUs with "m3"/"m4"/"m5" in their names (e.g. NVIDIA
Quadro M4 000) don't incorrectly match Apple bandwidth tiers.

Addresses @o3LL review comment on PR #2564.

.dockerignore

@@ -10,6 +10,12 @@ dist/
 build/
 .env
 .env.bak.*
+# Secrets: keep plaintext and every transient secrets.env variant out of
+# the build context. If an encrypted secrets.env is used, it is mounted
+# at runtime — never baked into the image. Mirrored in .gitignore.
+secrets.env
+secrets.env.*
+!secrets.env.example
 /data/
 /logs/
 .git/

.env.example

@@ -190,3 +190,10 @@ SEARXNG_INSTANCE=http://localhost:8080
 # These overlays only expose the GPU devices. The slim Odysseus image
 # still needs CUDA/ROCm userspace via Cookbook -> Dependencies (vLLM,
 # llama-cpp-python, etc.) before models can actually serve on GPU.
+
+# ============================================================
+# Storage Paths (Docker Compose)
+# ============================================================
+
+# APP_DATA_DIR=./data
+# APP_LOGS_DIR=./logs

.github/CODEOWNERS

@@ -1,8 +1,9 @@
 # Code owners.
 #
-# Every file is owned by the maintainer, so that when branch protection has
+# Intentionally empty for now. The catch-all rule that mapped every path to a
-# "Require review from Code Owners" turned on, no pull request can be merged
+# single owner froze all merges the moment "Require review from Code Owners"
-# without the maintainer's review. This is the human gate that backs up the
+# was enabled, because no other maintainer's approval could satisfy the gate.
-# automated security checks. See docs/security-ci.md for how to turn it on.
+# A per-area ownership map (security/auth, CI, frontend, agent internals, with
-
+# multiple named owners per line) is being worked out in issue #593; once
-*       @pewdiepie-archdaemon
+# agreed it replaces this file. Until then, required reviews and the security
+# CI gate (docs/security-ci.md) remain in force via branch protection.

.github/pull_request_review_template.md

@@ -0,0 +1,123 @@
+# Pull Request Review Template
+
+Use this shape as a copyable reference for substantive PR reviews; GitHub does
+not auto-apply this file to review comments. Omit sections that do not add
+useful signal. Lead with confirmed findings; keep speculative notes out of the
+public review unless they are framed as a concrete open question.
+
+## Small PR Path
+
+For narrow docs, typo, test-only, or obvious local fixes, a short review is
+enough:
+
+```md
+LGTM after checking:
+- scope:
+- validation:
+- residual risk:
+```
+
+Use the fuller structure below for larger, risky, multi-finding, or
+security-sensitive reviews.
+
+## Findings
+
+**<sub><sub>![P2 Badge](https://img.shields.io/badge/P2-yellow?style=flat)</sub></sub> issue (test): Short issue title**
+
+- **Problem:** Concrete broken flow, contract, input, or risk.
+
+- **Impact:** Why this matters to users, CI, maintainers, data, security, or scale.
+
+- **Ask:** Smallest practical correction or decision the author should make.
+
+- **Location:** `path:line`
+
+## Open Questions
+
+- **question (scope, non-blocking): Short author question** Ask the concrete
+  intent, scope, or tradeoff question.
+
+## Validation
+
+- Ran:
+- Not run:
+- Residual risk:
+
+## PR Hygiene
+
+- Target/template/checks:
+- Related, duplicate, or superseding context:
+
+## No Findings Variant
+
+```md
+## Findings
+
+none confirmed
+
+## Validation
+
+- Ran:
+- Not run:
+- Residual risk:
+```
+
+## Legend
+
+- **Findings:** Verified, author-actionable issues that should be fixed or
+  consciously accepted before merge.
+- **Priority badges:** The shields.io badges below are optional formatting for
+  priority labels. Plain `P0`, `P1`, `P2`, or `P3` text is also acceptable when
+  an external image dependency is undesirable or may not render.
+  - **P0:** `![P0 Badge](https://img.shields.io/badge/P0-red?style=flat)` -
+    release-blocking or actively dangerous.
+  - **P1:** `![P1 Badge](https://img.shields.io/badge/P1-orange?style=flat)` -
+    serious bug, security risk, data-loss risk, or broken primary flow.
+  - **P2:** `![P2 Badge](https://img.shields.io/badge/P2-yellow?style=flat)` -
+    meaningful correctness, test, maintainability, or edge-case issue.
+  - **P3:** `![P3 Badge](https://img.shields.io/badge/P3-lightgrey?style=flat)` -
+    minor polish or low-risk cleanup.
+- **Intent labels:**
+  - **`issue`:** A confirmed defect, regression, broken contract, or concrete
+    risk.
+  - **`suggestion`:** A non-blocking improvement that would make the PR clearer,
+    safer, or easier to maintain.
+  - **`nit`:** A tiny, non-blocking cleanup or style note. Use it only when the
+    author can safely ignore it without changing the review outcome.
+  - **`question`:** A real author-facing clarification about intent, scope, or
+    tradeoffs. Do not use questions to hide an issue that should be stated
+    directly.
+  - **`LGTM`:** "Looks good to me." Use only when the review found no blocking
+    issues, or when any remaining notes are clearly optional.
+- **Decorations:** Optional labels in parentheses that clarify the finding type,
+  scope, or merge impact.
+  - **`security`:** Auth, authorization, ownership, secrets, SSRF, injection,
+    unsafe external input, or other trust-boundary concerns.
+  - **`test`:** Missing, failing, misleading, brittle, or insufficient tests.
+  - **`scope`:** PR scope, feature boundaries, unrelated churn, or work that
+    should be split into a separate issue or PR.
+  - **`ci`:** CI configuration, workflow failures, flaky checks, or validation
+    signal quality.
+  - **`api`:** Route, request/response, public function, schema, persistence, or
+    integration contract changes.
+  - **`docs`:** User-facing docs, contributor docs, examples, or comments that
+    need to change with the code.
+  - **`non-blocking`:** Useful feedback that should not prevent merge by
+    itself.
+- **Finding fields:**
+  - **Problem:** What is wrong, what contract is ambiguous, or what risk the PR
+    introduces.
+  - **Impact:** Why the problem matters in practical terms.
+  - **Ask:** The smallest concrete fix, test, or decision requested from the PR
+    author.
+  - **Location:** The most useful repo-relative file and line reference for the
+    finding, using `path:line`.
+- **Optional sections:**
+  - **Open Questions:** Genuine scope or intent questions; omit when there are
+    no real questions.
+  - **Validation:** What the reviewer ran, what was intentionally not run, and
+    what risk remains after review.
+  - **PR Hygiene:** Target-branch, template, CI/check, duplicate, related-work,
+    or superseding-PR notes.
+- **`none confirmed`:** Use only when no review-worthy findings were confirmed;
+  still list validation gaps or residual risk when relevant.

.github/workflows/ci.yml

@@ -19,10 +19,10 @@ jobs:
     name: Python syntax (compileall)
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
         with:
           persist-credentials: false
-      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065  # v5
+      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6.2.0
         with:
           python-version: "3.11"
       # Byte-compile sources — catches syntax errors without installing deps.
@@ -32,10 +32,10 @@ jobs:
     name: JS syntax (node --check)
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
         with:
           persist-credentials: false
-      - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020  # v4
+      - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e  # v6.4.0
         with:
           node-version: "20"
       # Syntax-check our own JS (skip vendored libs in static/lib).
@@ -54,7 +54,7 @@ jobs:
     # ROADMAP "fresh install smoke tests" item; make this required once green.
     continue-on-error: true
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
         with:
           fetch-depth: 0
           persist-credentials: false
@@ -81,7 +81,7 @@ jobs:
             echo "docs_only=false" >> "$GITHUB_OUTPUT"
           fi
 
-      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065  # v5
+      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6.2.0
         if: steps.docs-check.outputs.docs_only != 'true'
         with:
           python-version: "3.11"

.github/workflows/codeql.yml

@@ -45,17 +45,17 @@ jobs:
         language: [python, javascript-typescript]
     steps:
       - name: Checkout repository
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
         with:
           persist-credentials: false
 
       - name: Initialize CodeQL
-        uses: github/codeql-action/init@03e4368ac7daa2bd82b3e85262f3bf87ee112f57  # v3.36.0
+        uses: github/codeql-action/init@8aad20d150bbac5944a9f9d289da16a4b0d87c1e  # v4.36.2
         with:
           languages: ${{ matrix.language }}
           build-mode: none
 
       - name: Perform CodeQL analysis
-        uses: github/codeql-action/analyze@03e4368ac7daa2bd82b3e85262f3bf87ee112f57  # v3.36.0
+        uses: github/codeql-action/analyze@8aad20d150bbac5944a9f9d289da16a4b0d87c1e  # v4.36.2
         with:
           category: "/language:${{ matrix.language }}"

.github/workflows/container-scan.yml

@@ -37,7 +37,7 @@ jobs:
       contents: read
     steps:
       - name: Checkout repository
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
         with:
           persist-credentials: false
 

.github/workflows/container-trivy.yml

@@ -52,7 +52,7 @@ jobs:
       contents: read
     steps:
       - name: Checkout repository
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
         with:
           persist-credentials: false
 
@@ -93,7 +93,7 @@ jobs:
       security-events: write  # upload SARIF to the Security tab
     steps:
       - name: Checkout repository
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
         with:
           persist-credentials: false
 
@@ -119,7 +119,7 @@ jobs:
           TRIVY_DB_REPOSITORY: ghcr.io/aquasecurity/trivy-db:2
 
       - name: Upload Trivy results
-        uses: github/codeql-action/upload-sarif@03e4368ac7daa2bd82b3e85262f3bf87ee112f57  # v3.36.0
+        uses: github/codeql-action/upload-sarif@8aad20d150bbac5944a9f9d289da16a4b0d87c1e  # v4.36.2
         with:
           sarif_file: trivy-results.sarif
           category: trivy-image

.github/workflows/dependency-review.yml

@@ -36,7 +36,7 @@ jobs:
       contents: read
     steps:
       - name: Checkout repository
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
         with:
           persist-credentials: false
 
@@ -55,7 +55,7 @@ jobs:
       contents: read
     steps:
       - name: Checkout repository
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
         with:
           persist-credentials: false
 

.github/workflows/secret-scan.yml

@@ -35,7 +35,7 @@ jobs:
       contents: read
     steps:
       - name: Checkout repository
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
         with:
           # Full history so a secret committed in an earlier commit (and later
           # deleted) is still caught -- deletion does not remove it from Git.

.github/workflows/workflow-security.yml

@@ -36,7 +36,7 @@ jobs:
       contents: read
     steps:
       - name: Checkout repository
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
         with:
           persist-credentials: false
 
@@ -61,7 +61,7 @@ jobs:
       contents: read
     steps:
       - name: Checkout repository
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
         with:
           persist-credentials: false
 

.gitignore

@@ -14,6 +14,15 @@ venv/
 .env
 .env.bak.*
 !.env.example
+# Local uv lockfile (optional, per-platform — see "Faster installs with uv" in README)
+requirements.lock
+
+# SOPS workflow — encrypted `secrets.env` is intentionally committable,
+# but every variant (plaintext, manual decrypt copy, editor backup)
+# must stay out of git. Mirrored in .dockerignore so the same artifacts
+# also cannot enter image build layers.
+secrets.env.*
+!secrets.env.example
 
 # Data — all user data stays local
 data/
@@ -61,6 +70,9 @@ output.txt.txt
 *.tiff
 *.pdf
 
+# …except shipped static assets
+!static/icons/*.png
+
 # …except shipped demo assets in docs/ that the README links to.
 !docs/*.jpg
 !docs/*.jpeg

Dockerfile

@@ -1,4 +1,4 @@
-FROM python:3.12-slim
+FROM python:3.14-slim
 
 # System deps. tmux is required by Cookbook for background downloads/serves.
 # openssh-client is required for Cookbook remote server tests, setup, probes,

README.md

@@ -12,6 +12,8 @@
 
 A self-hosted AI workspace -- meant to be the self-hosted version of the UI experience you get from ChatGPT and Claude. But with more jank and fun. Running on your own hardware, with your own data -- local-first, privacy-first, and no trojan.
 
+[![Packaging status](https://repology.org/badge/vertical-allrepos/odysseus-ai.svg)](https://repology.org/project/odysseus-ai/versions)
+
 ## Features
   - **Chat** -- chat with any local model or API; adding them is super simple.<br>　<sub>vLLM · llama.cpp · Ollama · OpenRouter · OpenAI · GitHub Copilot</sub>
   - **Agent** -- hand it tools and let it run the whole task itself.<br>　<sub>built on [opencode](https://github.com/anomalyco/opencode) · MCP · web · files · shell · skills · memory</sub>
@@ -73,6 +75,10 @@ binds the web UI to `127.0.0.1` by default. If the port is taken, set
 `APP_PORT=7001` in `.env` and recreate the container. Set `APP_BIND=0.0.0.0`
 only when you intentionally want LAN/reverse-proxy access.
 
+> **On Apple Silicon (M-series) Macs:** Docker can't reach the Metal GPU, so
+> Cookbook serves local models on CPU only. For GPU-accelerated model serving,
+> run natively instead — see [Apple Silicon](#apple-silicon) below.
+
 ### Native Linux / macOS
 ```bash
 git clone https://github.com/pewdiepie-archdaemon/odysseus.git
@@ -333,6 +339,25 @@ To expose Odysseus on a local network or Tailscale with HTTPS:
 | `PyMuPDF` | PDF page rendering in the side viewer panel and form-filling. (Note: AGPL-3.0) |
 | `markitdown` | Office/EPUB document text extraction (converts .docx/.xlsx/.pptx/.xls/.epub to Markdown). |
 
+### Faster, reproducible installs with uv (optional)
+[uv](https://docs.astral.sh/uv/) works as a drop-in replacement for the
+venv + pip steps in the native install guides, no project changes are needed but this change results in faster installs along with a lockfile for reproducible environments. After [installing `uv`](https://docs.astral.sh/uv/getting-started/installation/), use:
+
+```bash
+uv venv venv --python 3.13
+uv pip install -r requirements.txt
+# then continue as usual: python setup.py, uvicorn, ...
+```
+
+`requirements.txt` is intentionally unpinned, so two installs at different times can produce different package versions. If you want a reproducible environment (e.g. across your own machines, or to roll back after a bad upgrade), snapshot and restore exact versions with:
+
+```bash
+uv pip compile requirements.txt -o requirements.lock   # snapshot current resolution
+uv pip sync requirements.lock                          # reproduce it exactly later
+```
+
+`requirements.lock` is gitignored and platform-specific (compile it on the OS you deploy to). Regenerate it deliberately when you want to take upgrades. The plain `uv pip install -r requirements.txt` keeps following the unpinned requirements like pip does.
+
 ### Outlook / Office 365 email
 Odysseus email accounts currently use IMAP/SMTP username-password auth. Outlook
 and Microsoft 365 generally require OAuth instead, so normal Microsoft mailbox
@@ -364,6 +389,7 @@ Odysseus serves plain HTTP on its app port. Docker Compose binds Odysseus and th
 4. Keep raw service and model ports internal-only.
 
 Cloudflare Access, Tailscale, Caddy, nginx, and Traefik can all fit this pattern; none are required by Odysseus. If your access layer reaches Odysseus on the same host, proxy to `http://127.0.0.1:7000` and keep `AUTH_ENABLED=true`, `LOCALHOST_BYPASS=false`, and `SECURE_COOKIES=true`.
+`ALLOWED_ORIGINS` lists exact permitted origins for cross-origin browser/API clients; ordinary same-origin reverse-proxy access usually does not need a special CORS entry.
 
 Common internal-only ports from the default docs/compose setup:
 
@@ -395,8 +421,11 @@ Key settings:
 | `SEARXNG_SECRET` | generated on first Docker boot | Optional SearXNG cookie/CSRF secret. Leave blank unless you need to pin it. |
 | `APP_BIND` | `127.0.0.1` | Docker Compose host bind address for the web UI. Use `0.0.0.0` only for intentional LAN/reverse-proxy access. |
 | `APP_PORT` | `7000` | Docker Compose host port for the web UI. |
+| `APP_DATA_DIR` | `./data` | Docker Compose host directory for application data volumes. |
+| `APP_LOGS_DIR` | `./logs` | Docker Compose host directory for application logs. |
 | `AUTH_ENABLED` | `true` | Enable/disable login |
 | `LOCALHOST_BYPASS` | `false` | Development-only auth bypass for loopback requests. Keep false for shared/network deployments. |
+| `ALLOWED_ORIGINS` | `http://localhost,http://127.0.0.1` | Comma-separated exact permitted origins for cross-origin browser/API clients. |
 | `SECURE_COOKIES` | `false` | Set true when serving Odysseus through HTTPS at a trusted proxy or private access gateway. |
 | `DATABASE_URL` | `sqlite:///./data/app.db` | Database connection string |
 | `CHROMADB_HOST` | `localhost` | ChromaDB host for vector memory. Docker overrides this to `chromadb`. |
@@ -440,6 +469,9 @@ docs/      landing page (index.html) + preview clips
 All user data lives in `data/` (gitignored): `app.db` (sessions, messages, documents),
 `memory.json`, `presets.json`, `uploads/`, `personal_docs/`, `chroma/`, `settings.json`.
 
+To back up or restore everything in `data/`, see the
+[Backup & Restore guide](docs/backup-restore.md).
+
 ## Star History
 
 <a href="https://www.star-history.com/?repos=pewdiepie-archdaemon%2Fodysseus&type=date&legend=top-left">

app.py

@@ -69,10 +69,37 @@ from src.generated_images import GENERATED_IMAGE_HEADERS, resolve_generated_imag
 from starlette.responses import RedirectResponse
 
 # ========= LOGGING =========
-logging.basicConfig(
+import logging.handlers
-    level=logging.INFO,
+from core.constants import DATA_DIR
-    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+
-)
+_root_logger = logging.getLogger()
+_root_logger.setLevel(logging.INFO)
+_formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+
+# Clear existing handlers to avoid duplicates
+for _h in list(_root_logger.handlers):
+    _root_logger.removeHandler(_h)
+
+_console_h = logging.StreamHandler()
+_console_h.setFormatter(_formatter)
+_root_logger.addHandler(_console_h)
+
+try:
+    _log_dir = os.path.join(DATA_DIR, "logs")
+    os.makedirs(_log_dir, exist_ok=True)
+    _log_file = os.path.join(_log_dir, "app.log")
+
+    # RotatingFileHandler is not multi-process safe (e.g. if uvicorn is run with --workers N).
+    # Odysseus is single-process by convention, so this is acceptable, but be aware that
+    # concurrent log rotation issues can arise if multiple workers are configured.
+    _file_h = logging.handlers.RotatingFileHandler(
+        _log_file, maxBytes=5 * 1024 * 1024, backupCount=3, encoding="utf-8"
+    )
+    _file_h.setFormatter(_formatter)
+    _root_logger.addHandler(_file_h)
+except Exception as e:
+    _root_logger.warning(f"Failed to initialize file logging handler (falling back to console-only): {e}")
+
 logger = logging.getLogger(__name__)
 
 # ========= APP =========
@@ -140,6 +167,7 @@ _TIMEOUT_EXEMPT_PREFIXES = (
     "/api/cookbook/setup",  # remote pacman/apt installs
     "/api/upload",          # large files
     "/api/image",           # diffusion proxies (inpaint/harmonize/upscale/etc.) — own 120s httpx timeout
+    "/api/memory/audit",    # retains own 120s LLM inactivity timeout
 )
 
 

core/auth.py

@@ -3,6 +3,7 @@ Authentication module — multi-user password hashing, session tokens, config pe
 Config stored in data/auth.json. Uses bcrypt directly.
 """
 
+import enum
 import json
 import os
 import secrets
@@ -83,6 +84,15 @@ def _verify_password(password: str, hashed: str) -> bool:
     return bcrypt.checkpw(password.encode("utf-8"), hashed.encode("utf-8"))
 
 
+class SetAdminResult(enum.Enum):
+    """Outcome of AuthManager.set_admin, so callers can map each case to a
+    precise response instead of guessing from a bare bool."""
+    OK = "ok"
+    USER_NOT_FOUND = "user_not_found"
+    NOT_AUTHORIZED = "not_authorized"   # requester is not an admin
+    LAST_ADMIN = "last_admin"           # would remove the last remaining admin
+
+
 class AuthManager:
     """Manages multi-user password + session-token auth system."""
 
@@ -387,6 +397,69 @@ class AuthManager:
         logger.info(f"Updated privileges for '{username}': {current}")
         return True
 
+    def set_admin(self, username: str, is_admin: bool,
+                  requesting_user: str) -> SetAdminResult:
+        """Promote/demote an existing user to/from admin. Admin only.
+
+        Refuses to remove the last remaining admin so the instance can never
+        be locked out of admin access; self-demotion is allowed as long as
+        another admin remains. Admin status is re-checked live on every
+        request, so unlike delete/rename no session or token revocation is
+        needed — a demoted admin simply fails the next is_admin() gate.
+
+        Promotion stashes the user's current privilege map and demotion
+        restores it, so a temporary admin stint can't silently broaden a
+        user's non-admin access; users without a stash (created as admin,
+        or promoted before stashing existed) demote to DEFAULT_PRIVILEGES.
+
+        Counting admins and flipping the flag happen in one critical section
+        so two concurrent demotions can't race the admin count to zero.
+        """
+        username = (username or "").strip().lower()
+        requesting_user = (requesting_user or "").strip().lower()
+        is_admin = bool(is_admin)
+        with self._config_lock:
+            target = self._config.get("users", {}).get(username)
+            if target is None:
+                return SetAdminResult.USER_NOT_FOUND
+            if not self.users.get(requesting_user, {}).get("is_admin"):
+                return SetAdminResult.NOT_AUTHORIZED
+            currently_admin = bool(target.get("is_admin"))
+            if currently_admin == is_admin:
+                return SetAdminResult.OK  # no-op; leave privileges untouched
+            if currently_admin and not is_admin:
+                admin_count = sum(1 for d in self.users.values() if d.get("is_admin"))
+                if admin_count <= 1:
+                    return SetAdminResult.LAST_ADMIN
+            # Write order matters for lock-free readers: get_privileges()
+            # reads without _config_lock and trusts is_admin, so the admin
+            # flag must be flipped while the stored map is safe to expose —
+            # before writing admin privileges on promote, after restoring
+            # the pre-admin map on demote.
+            if is_admin:
+                target["is_admin"] = True
+                # Stash the pre-admin map so a later demotion can restore it.
+                # While is_admin is set the stored map is inert: get_privileges
+                # short-circuits to ADMIN_PRIVILEGES and set_privileges refuses
+                # admins, so only set_admin ever touches the stash.
+                target["privileges_before_admin"] = dict(
+                    target.get("privileges") or DEFAULT_PRIVILEGES
+                )
+                target["privileges"] = dict(ADMIN_PRIVILEGES)
+            else:
+                # Restore the stashed pre-admin map. Fall back to defaults for
+                # users created as admins (their stored map is ADMIN_PRIVILEGES,
+                # which must not leak past demotion — e.g. can_use_bash) and
+                # for admins promoted before the stash existed.
+                target["privileges"] = dict(
+                    target.pop("privileges_before_admin", None)
+                    or DEFAULT_PRIVILEGES
+                )
+                target["is_admin"] = False
+            self._save()
+        logger.info("Set is_admin=%s for '%s' (by '%s')", is_admin, username, requesting_user)
+        return SetAdminResult.OK
+
     def change_password(self, username: str, current_password: str, new_password: str) -> bool:
         username = username.strip().lower()
         if username not in self.users:

core/database.py

@@ -1602,6 +1602,7 @@ class CalendarCal(TimestampMixin, Base):
     # NULL for local calendars and for CalDAV calendars created before
     # multi-account support was added (treated as "use any configured account").
     account_id = Column(String, nullable=True, index=True)
+    caldav_base_url = Column(String, nullable=True)
 
     events = relationship("CalendarEvent", back_populates="calendar", cascade="all, delete-orphan")
 
@@ -1632,10 +1633,27 @@ class CalendarEvent(TimestampMixin, Base):
     # vanishes upstream). NULL/local = created locally (agent, email triage, or
     # a UI event whose write-back failed) and must NOT be pruned by the sync.
     origin      = Column(String, nullable=True, index=True)
+    remote_href = Column(String, nullable=True)        # CalDAV object URL for updates/deletes
+    remote_etag = Column(String, nullable=True)        # Last seen CalDAV ETag, when available
+    caldav_sync_pending = Column(String, nullable=True) # create | update | delete retry marker
 
     calendar = relationship("CalendarCal", back_populates="events")
 
 
+class CalendarDeletedEvent(TimestampMixin, Base):
+    """Hidden CalDAV delete tombstone retained until remote delete succeeds."""
+    __tablename__ = "caldav_deleted_events"
+
+    uid = Column(String, primary_key=True, index=True)
+    owner = Column(String, nullable=True, index=True)
+    calendar_id = Column(String, nullable=True, index=True)
+    remote_href = Column(String, nullable=True)
+    remote_etag = Column(String, nullable=True)
+    caldav_base_url = Column(String, nullable=True)
+    summary = Column(String, nullable=True)
+    last_error = Column(Text, nullable=True)
+
+
 class Integration(TimestampMixin, Base):
     """An external service connection (email, RSS, webhook, etc.)."""
     __tablename__ = "integrations"
@@ -1767,6 +1785,7 @@ def init_db():
     _migrate_add_calendar_is_utc()
     _migrate_add_calendar_origin()
     _migrate_add_calendar_account_id()
+    _migrate_add_caldav_sync_columns()
     _migrate_chat_messages_fts()
     _migrate_encrypt_email_passwords()
     _migrate_encrypt_signatures()
@@ -2067,6 +2086,31 @@ def _migrate_add_calendar_account_id():
             pass
 
 
+def _migrate_add_caldav_sync_columns():
+    """Add remote CalDAV metadata used for bidirectional sync."""
+    import sqlite3
+    db_path = DATABASE_URL.replace("sqlite:///", "")
+    if not os.path.exists(db_path):
+        return
+    try:
+        conn = sqlite3.connect(db_path)
+        ev_columns = [row[1] for row in conn.execute("PRAGMA table_info(calendar_events)").fetchall()]
+        if ev_columns and "remote_href" not in ev_columns:
+            conn.execute("ALTER TABLE calendar_events ADD COLUMN remote_href TEXT")
+        if ev_columns and "remote_etag" not in ev_columns:
+            conn.execute("ALTER TABLE calendar_events ADD COLUMN remote_etag TEXT")
+        if ev_columns and "caldav_sync_pending" not in ev_columns:
+            conn.execute("ALTER TABLE calendar_events ADD COLUMN caldav_sync_pending TEXT")
+
+        cal_columns = [row[1] for row in conn.execute("PRAGMA table_info(calendars)").fetchall()]
+        if cal_columns and "caldav_base_url" not in cal_columns:
+            conn.execute("ALTER TABLE calendars ADD COLUMN caldav_base_url TEXT")
+        conn.commit()
+        conn.close()
+    except Exception as e:
+        logging.getLogger(__name__).warning(f"CalDAV sync metadata migration failed: {e}")
+
+
 def _migrate_add_calendar_metadata():
     """Add importance/event_type/last_pinged columns to calendar_events table."""
     import sqlite3

docker-compose.gpu-amd.yml

@@ -16,18 +16,18 @@ services:
     ports:
       - "${APP_BIND:-127.0.0.1}:${APP_PORT:-7000}:7000"
     volumes:
-      - ./data:/app/data:z
+      - ${APP_DATA_DIR:-./data}:/app/data:z
-      - ./logs:/app/logs:z
+      - ${APP_LOGS_DIR:-./logs}:/app/logs:z
       # Cookbook remote-server SSH identity. Odysseus can generate a key here;
       # add the shown public key to each remote server's authorized_keys.
-      - ./data/ssh:/app/.ssh:z
+      - ${APP_DATA_DIR:-./data}/ssh:/app/.ssh:z
       # Cookbook local model cache. Inside Docker, "Local" means the Odysseus
       # container, so persist its HuggingFace cache under ./data/huggingface.
-      - ./data/huggingface:/app/.cache/huggingface:z
+      - ${APP_DATA_DIR:-./data}/huggingface:/app/.cache/huggingface:z
       # Cookbook-installed Python CLIs/packages (vLLM, llama-cpp-python, etc.)
       # land under /app/.local for the odysseus user. Persist them so a
       # container recreate does not silently remove installed serve engines.
-      - ./data/local:/app/.local:z
+      - ${APP_DATA_DIR:-./data}/local:/app/.local:z
     extra_hosts:
       # Lets the container reach local services on the Docker host, including
       # Ollama at http://host.docker.internal:11434.

docker-compose.gpu-nvidia.yml

@@ -15,18 +15,18 @@ services:
     ports:
       - "${APP_BIND:-127.0.0.1}:${APP_PORT:-7000}:7000"
     volumes:
-      - ./data:/app/data:z
+      - ${APP_DATA_DIR:-./data}:/app/data:z
-      - ./logs:/app/logs:z
+      - ${APP_LOGS_DIR:-./logs}:/app/logs:z
       # Cookbook remote-server SSH identity. Odysseus can generate a key here;
       # add the shown public key to each remote server's authorized_keys.
-      - ./data/ssh:/app/.ssh:z
+      - ${APP_DATA_DIR:-./data}/ssh:/app/.ssh:z
       # Cookbook local model cache. Inside Docker, "Local" means the Odysseus
       # container, so persist its HuggingFace cache under ./data/huggingface.
-      - ./data/huggingface:/app/.cache/huggingface:z
+      - ${APP_DATA_DIR:-./data}/huggingface:/app/.cache/huggingface:z
       # Cookbook-installed Python CLIs/packages (vLLM, llama-cpp-python, etc.)
       # land under /app/.local for the odysseus user. Persist them so a
       # container recreate does not silently remove installed serve engines.
-      - ./data/local:/app/.local:z
+      - ${APP_DATA_DIR:-./data}/local:/app/.local:z
     extra_hosts:
       # Lets the container reach local services on the Docker host, including
       # Ollama at http://host.docker.internal:11434.

docker-compose.yml

@@ -4,18 +4,18 @@ services:
     ports:
       - "${APP_BIND:-127.0.0.1}:${APP_PORT:-7000}:7000"
     volumes:
-      - ./data:/app/data:z
+      - ${APP_DATA_DIR:-./data}:/app/data:z
-      - ./logs:/app/logs:z
+      - ${APP_LOGS_DIR:-./logs}:/app/logs:z
       # Cookbook remote-server SSH identity. Odysseus can generate a key here;
       # add the shown public key to each remote server's authorized_keys.
-      - ./data/ssh:/app/.ssh:z
+      - ${APP_DATA_DIR:-./data}/ssh:/app/.ssh:z
       # Cookbook local model cache. Inside Docker, "Local" means the Odysseus
       # container, so persist its HuggingFace cache under ./data/huggingface.
-      - ./data/huggingface:/app/.cache/huggingface:z
+      - ${APP_DATA_DIR:-./data}/huggingface:/app/.cache/huggingface:z
       # Cookbook-installed Python CLIs/packages (vLLM, llama-cpp-python, etc.)
       # land under /app/.local for the odysseus user. Persist them so a
       # container recreate does not silently remove installed serve engines.
-      - ./data/local:/app/.local:z
+      - ${APP_DATA_DIR:-./data}/local:/app/.local:z
     extra_hosts:
       # Lets the container reach local services on the Docker host, including
       # Ollama at http://host.docker.internal:11434.

docs/agent-migration.md

@@ -0,0 +1,194 @@
+# Agent migration manifests
+
+Odysseus should be able to learn from another agent without blindly trusting
+that agent's whole state. The safe migration path is:
+
+```text
+source agent export -> source adapter -> agent-migration.v1 manifest -> preview -> apply
+```
+
+The manifest is intentionally source-neutral. OpenClaw, Hermes, a folder of
+Markdown notes, or any other agent can have its own adapter, but Odysseus only
+needs to understand the normalized manifest.
+
+## Why not import everything as memory?
+
+Durable memory should stay compact and useful. Long notes, logs, session
+transcripts, and project archives are useful context, but they are not all
+memories. A good migration keeps two layers separate:
+
+- **Archive documents** preserve source material for search, reading, and later
+  extraction.
+- **Memory candidates** are short facts or preferences that can be reviewed
+  before being saved into Odysseus memory.
+
+This keeps Odysseus' existing memory-review flow intact while giving it better
+source material to review.
+
+## Manifest shape
+
+`agent-migration.v1` is a JSON object:
+
+```json
+{
+  "schema_version": "agent-migration.v1",
+  "generated_at": "2026-06-06T00:00:00Z",
+  "source": {
+    "name": "example-agent",
+    "kind": "generic"
+  },
+  "summary": {
+    "item_count": 3,
+    "counts_by_kind": {
+      "memory": 1,
+      "skill": 1,
+      "conversation_thread": 1,
+      "archive_document": 1
+    },
+    "warning_count": 0
+  },
+  "items": [],
+  "warnings": []
+}
+```
+
+Each item has a stable `id`, a `kind`, source metadata, and enough content for a
+future importer to preview it before applying.
+
+Supported item kinds in the first pass:
+
+- `memory` — a candidate memory with `text`, `category`, `source`, and
+  provenance metadata.
+- `skill` — a `SKILL.md` file with content and parsed frontmatter metadata.
+- `conversation_thread` — a normalized transcript thread from an exported chat
+  history. Message content is optional; adapters can preserve only thread
+  metadata, message counts, timestamps, and hashes when a manifest should stay
+  small or avoid embedding private transcript text.
+- `archive_document` — long-form source material. Content is optional; adapters
+  can preserve only path/hash/size metadata when a manifest should stay small.
+
+## Build a manifest
+
+Use the read-only helper:
+
+```bash
+python3 scripts/agent_migration_manifest.py \
+  --source-name old-agent \
+  --source-kind generic \
+  --memory-json /path/to/memories.json \
+  --skills-dir /path/to/skills \
+  --conversation-json /path/to/conversations.json \
+  --archive /path/to/notes \
+  --output /tmp/agent-migration.json
+```
+
+The helper does not write to `data/`, call an LLM, import Odysseus modules, or
+modify the source. It only writes JSON.
+
+Memory JSON may be:
+
+```json
+[
+  "A plain memory string",
+  {
+    "text": "A categorized memory",
+    "category": "preference",
+    "source": "old-agent"
+  }
+]
+```
+
+or an object containing a list under `memories`, `memory`, `items`, or `data`.
+
+Skills are scanned recursively for `SKILL.md`:
+
+```bash
+python3 scripts/agent_migration_manifest.py \
+  --source-name hermes \
+  --source-kind hermes \
+  --skills-dir ~/.hermes/skills \
+  --output /tmp/hermes-skills-manifest.json
+```
+
+Archive documents are metadata-only by default. To embed text content:
+
+```bash
+python3 scripts/agent_migration_manifest.py \
+  --source-name notes-export \
+  --archive /path/to/markdown-notes \
+  --include-archive-content \
+  --output /tmp/notes-manifest.json
+```
+
+Conversation exports are also metadata-only by default:
+
+```bash
+python3 scripts/agent_migration_manifest.py \
+  --source-name chatgpt-export \
+  --source-kind chatgpt \
+  --conversation-json /path/to/conversations.json \
+  --output /tmp/chatgpt-conversations-manifest.json
+```
+
+The first pass supports generic conversation JSON such as:
+
+```json
+[
+  {
+    "id": "thread-1",
+    "title": "Project plan",
+    "messages": [
+      {"role": "user", "content": "Can we design this?"},
+      {"role": "assistant", "content": "Yes, start with a narrow slice."}
+    ]
+  }
+]
+```
+
+It also recognizes ChatGPT-style `mapping` exports from `conversations.json`.
+To embed normalized messages:
+
+```bash
+python3 scripts/agent_migration_manifest.py \
+  --source-name chatgpt-export \
+  --source-kind chatgpt \
+  --conversation-json /path/to/conversations.json \
+  --include-conversation-content \
+  --max-conversation-messages 2000 \
+  --output /tmp/chatgpt-conversations-with-content.json
+```
+
+Content embedding is explicit because exported chat histories can be huge and
+private. A future source-specific adapter can add ZIP traversal, attachment
+metadata, and provider-specific project/workspace fields while still emitting
+the same `conversation_thread` manifest item.
+
+## Recommended apply behavior
+
+A future Odysseus importer should treat the manifest as untrusted user-provided
+data and apply it in stages:
+
+1. Show a dry-run summary with counts, warnings, duplicates, and sample items.
+2. Back up current `data/` state before writing anything.
+3. Import archive documents as documents or another searchable source, not as
+   memory.
+4. Import conversation threads as searchable archived context first, with
+   citations back to the source thread. Do not turn whole transcripts into
+   memory.
+5. Show memory candidates for review before saving through the normal memory
+   path.
+6. Import skills only after name/category conflict checks.
+7. Skip secrets by default. Credentials need explicit, provider-specific flows.
+
+## What belongs in source adapters?
+
+Adapters can be source-specific. The core manifest should not be.
+
+For example, an OpenClaw adapter may know about OpenClaw's workspace files. A
+Hermes adapter may know about `~/.hermes/config.yaml` and `~/.hermes/skills`.
+A ChatGPT adapter may know about `conversations.json`, uploaded-file metadata,
+and image attachment directories. A Claude adapter may know about Claude's
+export shape and project boundaries. A generic adapter may only know about
+memory JSON, conversation JSON, `SKILL.md`, and Markdown folders.
+
+Nonstandard folders should be adapter details, not required Odysseus concepts.

docs/backup-restore.md

@@ -0,0 +1,129 @@
+# Backup & Restore
+
+Odysseus keeps all of your state in the `data/` directory — the SQLite database
+(`app.db`), the Fernet encryption key (`data/.app_key`), the vault, memory, RAG
+indexes, personal documents, and uploads. The `scripts/odysseus-backup` tool
+snapshots that directory into a single gzip tarball and restores it later.
+
+Snapshots are safe to take while the app is running: SQLite databases are copied
+through SQLite's own `.backup` API rather than a raw file copy, so an in-flight
+write can't corrupt the snapshot.
+
+> **A snapshot contains your secrets.** The tarball includes the Fernet
+> encryption key (`data/.app_key`), the vault, sessions, and any stored
+> provider/API tokens — so treat it like a password. Store backups somewhere
+> private, never commit them to Git, and prefer an encrypted destination when
+> copying them offsite.
+
+## Quick start
+
+Run the tool from the repository root:
+
+```bash
+# Create a snapshot → backups/odysseus-backup-<YYYYMMDD-HHMMSS>.tar.gz
+./scripts/odysseus-backup snapshot
+
+# List existing snapshots (most recent first)
+./scripts/odysseus-backup list
+
+# Check a tarball's integrity without extracting it
+./scripts/odysseus-backup verify backups/odysseus-backup-20260101-120000.tar.gz
+
+# Restore (destructive — see the warning below)
+./scripts/odysseus-backup restore backups/odysseus-backup-20260101-120000.tar.gz --yes
+```
+
+The script depends only on the Python standard library, so any `python3` on your
+`PATH` will run it — you don't need the app's virtualenv active.
+
+Every command prints a JSON result. Add `--pretty` for indented output.
+
+## Commands
+
+### `snapshot`
+
+Writes a `tar.gz` of `data/` to `backups/<timestamp>.tar.gz`.
+
+| Flag | Effect |
+| --- | --- |
+| `--out PATH` | Write to a specific path instead of the default `backups/` location. Must be **outside** `data/`. |
+| `--include-research` | Include `data/deep_research/` (skipped by default — research runs are large). |
+| `--include-attachments` | Include `data/mail-attachments/` (skipped by default — cached IMAP extractions, re-derivable). |
+
+By default the snapshot includes everything under `data/` **except**
+`deep_research/` and `mail-attachments/`. Personal uploads and documents are
+included.
+
+```bash
+# Snapshot straight to a mounted NAS path
+./scripts/odysseus-backup snapshot --out /mnt/nas/odysseus-$(date +%F).tar.gz
+
+# Full snapshot including research runs and mail attachments
+./scripts/odysseus-backup snapshot --include-research --include-attachments
+```
+
+### `list`
+
+Lists the tarballs in `backups/`, most recent first, with size and modification
+time.
+
+### `verify PATH`
+
+Opens the tarball read-only and walks every member to confirm it is intact and
+safe to restore. Nothing is extracted. Use this before relying on an old backup
+or after copying one across machines.
+
+### `restore PATH --yes`
+
+Overwrites `data/` from a tarball.
+
+> **Restore is destructive.** It replaces the current `data/` directory. `--yes`
+> is required so a mistyped command can't wipe your live state.
+
+Restore is not a blind delete: before extracting, the tool **renames your current
+`data/` to `data.before-restore-<timestamp>`** in the repository root. If a
+restore turns out to be wrong, your previous state is still there — delete the
+restored `data/` and rename the stashed directory back. The restore path is also
+validated entry-by-entry: archives containing absolute paths, `..` segments,
+symlinks, or anything outside `data/` are rejected.
+
+## Scheduling offsite backups
+
+The tarball output composes cleanly with cron and any copy tool. For example, a
+nightly snapshot copied offsite:
+
+```cron
+0 3 * * *  cd /path/to/odysseus && ./scripts/odysseus-backup snapshot --out "/mnt/nas/odysseus-$(date +\%F).tar.gz"
+```
+
+Swap the `--out` target for `scp`, `rclone`, `s3cmd`, or similar to push the
+snapshot to remote storage.
+
+## Docker vs native installs
+
+The tool reads `data/` and writes `backups/` relative to the repository root, so
+where you run it matters:
+
+- **Native installs** — run it from the repo root as shown above. `data/` and
+  `backups/` are both in the repo directory.
+- **Docker** — `docker-compose.yml` bind-mounts the host's `./data` to
+  `/app/data`, so the live data is also present on the host. **Run the tool on
+  the host** from the repo root; the snapshot reads the bind-mounted `./data` and
+  writes to `./backups` on the host. Running it *inside* the container is not
+  recommended, because `backups/` is not a mounted volume and the tarball would
+  be lost when the container is recreated.
+
+> **ChromaDB caveat (Docker only).** In the Docker setup, ChromaDB stores its
+> vectors in a separate Compose-managed volume (declared as `chromadb-data`),
+> **not** under `./data`. `odysseus-backup` therefore does not capture the Docker
+> ChromaDB store. Back it up separately if you need it. Compose prefixes the
+> volume with the project name, so find the real name first
+> (`docker volume ls | grep chromadb`), then archive it — for example:
+>
+> ```bash
+> docker run --rm -v <project>_chromadb-data:/data -v "$PWD":/backup \
+>   alpine tar czf /backup/chromadb.tar.gz -C /data .
+> ```
+>
+> On native installs ChromaDB lives at `data/chroma/` and is included in the
+> snapshot normally.

launch-windows.ps1

@@ -141,7 +141,20 @@ if (-not (Find-GitBash)) {
     Write-Host "      https://git-scm.com/download/win" -ForegroundColor Yellow
 }
 
-# 6. Start the server (use `python -m uvicorn` - bare `uvicorn` may not be on PATH)
+# 6. Point CUDA_PATH at a real CUDA toolkit so GPU llama-cpp-python can import.
+$cudaBase = "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA"
+if (Test-Path $cudaBase) {
+    $cudaBest = Get-ChildItem $cudaBase -Directory -ErrorAction SilentlyContinue |
+        Where-Object { Test-Path (Join-Path $_.FullName "bin") } |
+        Sort-Object { try { [version]($_.Name -replace "^v", "") } catch { [version]"0.0" } } -Descending |
+        Select-Object -First 1
+    if ($cudaBest) {
+        $env:CUDA_PATH = $cudaBest.FullName
+        Write-Host ("Using CUDA_PATH = " + $cudaBest.FullName) -ForegroundColor Cyan
+    }
+}
+
+# 7. Start the server (use `python -m uvicorn` - bare `uvicorn` may not be on PATH)
 Write-Step ("Starting Odysseus at http://{0}:{1}" -f $BindHost, $Port)
 Write-Host "Press Ctrl+C to stop."
 Write-Host ""

mcp_servers/memory_server.py

@@ -93,16 +93,15 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
             if category_filter:
                 msg += f" in category '{category_filter}'"
             return [TextContent(type="text", text=msg + ".")]
+
         lines = [f"Found {len(memories)} memory entries:\n"]
-        for m in memories[:100]:
+        for m in memories:
             cat = m.get("category", "fact")
             mid = m.get("id", "?")[:8]
             text = m.get("text", "")
             if len(text) > 150:
                 text = text[:150] + "..."
             lines.append(f"- [{cat}] `{mid}` — {text}")
-        if len(memories) > 100:
-            lines.append(f"... and {len(memories) - 100} more")
         return [TextContent(type="text", text="\n".join(lines))]
 
     elif action == "add":

package-lock.json

@@ -5,16 +5,16 @@
   "packages": {
     "": {
       "dependencies": {
-        "@anthropic-ai/sdk": "^0.98.0"
+        "@anthropic-ai/sdk": "^0.104.1"
       },
       "devDependencies": {
-        "@antithesishq/bombadil": "^0.3.2"
+        "@antithesishq/bombadil": "^0.5.0"
       }
     },
     "node_modules/@anthropic-ai/sdk": {
-      "version": "0.98.0",
+      "version": "0.104.1",
-      "resolved": "https://registry.npmjs.org/@anthropic-ai/sdk/-/sdk-0.98.0.tgz",
+      "resolved": "https://registry.npmjs.org/@anthropic-ai/sdk/-/sdk-0.104.1.tgz",
-      "integrity": "sha512-N7aXtCvC5g6T1Y4V29lJjceu/zTkVkIZF0jdBvagr0TRFHuKeImffalGWEfqZKrvjH+IQbzJWw6TmSmUzrlMgg==",
+      "integrity": "sha512-gGACa/+IaiXzRRmF96aOhamoBgapKRBiFWbmmTFP8aMkpaEcuStF+Q61bjo4vPxBM7gqWJNZqsngslRdnLHv0Q==",
       "license": "MIT",
       "dependencies": {
         "json-schema-to-ts": "^3.1.1",
@@ -33,11 +33,14 @@
       }
     },
     "node_modules/@antithesishq/bombadil": {
-      "version": "0.3.2",
+      "version": "0.5.0",
-      "resolved": "https://registry.npmjs.org/@antithesishq/bombadil/-/bombadil-0.3.2.tgz",
+      "resolved": "https://registry.npmjs.org/@antithesishq/bombadil/-/bombadil-0.5.0.tgz",
-      "integrity": "sha512-ATy1w9ZY5gbny1H8DFc7rxZitT7DLLLFDiGcRZe+8TQiUrV5tLO+IJGOVNNLp3RpCqjZqSsxGiKoQsx31ipV1g==",
+      "integrity": "sha512-s0zImmr0iyvSP6QcVLvf40CUiZYIdWBAxiq20uhzujwvfitYa3PGJN652k/pLtVccHM/JrGQxZdvLnihZpltHA==",
       "dev": true,
-      "license": "MIT"
+      "license": "MIT",
+      "bin": {
+        "bombadil": "bin/bombadil.js"
+      }
     },
     "node_modules/@babel/runtime": {
       "version": "7.29.7",

package.json

@@ -4,9 +4,9 @@
     "url": "https://github.com/pewdiepie-archdaemon/odysseus.git"
   },
   "devDependencies": {
-    "@antithesishq/bombadil": "^0.3.2"
+    "@antithesishq/bombadil": "^0.5.0"
   },
   "dependencies": {
-    "@anthropic-ai/sdk": "^0.98.0"
+    "@anthropic-ai/sdk": "^0.104.1"
   }
 }

requirements-optional.txt

@@ -33,4 +33,4 @@ PyMuPDF
 # magika (onnxruntime), already a core dep via fastembed. We avoid the
 # [all]/Azure/audio extras (cloud + heavy). Pinned to a release >30 days old per
 # the dependency-age discussion in issue #485.
-markitdown[docx,pptx,xlsx,xls]==0.1.5
+markitdown[docx,pptx,xlsx,xls]==0.1.6

requirements.txt

@@ -3,8 +3,8 @@ uvicorn
 python-multipart
 python-dotenv
 httpx
-pydantic>=2.0
+pydantic>=2.13.4
-pydantic-settings>=2.0
+pydantic-settings>=2.14.1
 SQLAlchemy
 pypdf
 beautifulsoup4

routes/auth_routes.py

@@ -12,7 +12,7 @@ import re
 from pathlib import Path
 
 from core.atomic_io import atomic_write_json, atomic_write_text
-from core.auth import AuthManager
+from core.auth import AuthManager, SetAdminResult
 from src.constants import DEEP_RESEARCH_DIR, MEMORY_FILE, SKILLS_DIR
 from src.rate_limiter import RateLimiter
 from src.settings_scrub import scrub_settings
@@ -73,6 +73,11 @@ class DeleteUserRequest(BaseModel):
 class RenameUserRequest(BaseModel):
     username: str
 
+
+class SetAdminRequest(BaseModel):
+    is_admin: bool
+
+
 class SetOpenRegistrationRequest(BaseModel):
     enabled: bool
 
@@ -487,6 +492,31 @@ def setup_auth_routes(auth_manager: AuthManager) -> APIRouter:
             invalidator()
         return {"ok": True, "username": new_username, "renamed_self": old_username == user}
 
+    @router.put("/users/{username}/admin")
+    async def set_user_admin(username: str, body: SetAdminRequest, request: Request):
+        """Promote/demote a user to/from admin. Admin only.
+
+        The last remaining admin can't be demoted (no lockout). Self-demotion
+        is allowed while another admin exists; the `self` flag tells the UI to
+        reload the acting user into the normal-user view.
+        """
+        user = _get_current_user(request)
+        if not user or not auth_manager.is_admin(user):
+            raise HTTPException(403, "Admin only")
+        result = auth_manager.set_admin(username, body.is_admin, user)
+        if result is SetAdminResult.USER_NOT_FOUND:
+            raise HTTPException(404, "User not found")
+        if result is SetAdminResult.NOT_AUTHORIZED:
+            raise HTTPException(403, "Admin only")
+        if result is SetAdminResult.LAST_ADMIN:
+            raise HTTPException(400, "Cannot demote the last admin")
+        target = (username or "").strip().lower()
+        return {
+            "ok": True,
+            "is_admin": body.is_admin,
+            "self": target == (user or "").strip().lower(),
+        }
+
     @router.post("/signup-toggle", deprecated=True)
     async def toggle_signup(request: Request):
         """

routes/calendar_routes.py

@@ -11,7 +11,7 @@ from pydantic import BaseModel
 from sqlalchemy import or_, and_
 from dateutil.rrule import rrulestr
 
-from core.database import SessionLocal, CalendarCal, CalendarEvent
+from core.database import SessionLocal, CalendarCal, CalendarDeletedEvent, CalendarEvent
 from src.auth_helpers import require_user
 from src.upload_limits import read_upload_limited, ICS_MAX_BYTES
 
@@ -126,6 +126,54 @@ def _resolve_base_uid(uid: str) -> str:
         raise ValueError("malformed compound UID: missing base before ::")
     return base
 
+
+async def _push_caldav_event_after_commit(owner: str, uid: str, action: str):
+    """Best-effort CalDAV write-through. Local writes stay authoritative if
+    the remote server is unreachable; pending flags let /sync retry later."""
+    try:
+        result = {"ok": True}
+        if action == "create":
+            from src.caldav_sync import push_event_create
+            result = await push_event_create(owner, uid)
+        elif action == "update":
+            from src.caldav_sync import push_event_update
+            result = await push_event_update(owner, uid)
+        elif action == "delete":
+            from src.caldav_sync import push_event_delete
+            result = await push_event_delete(owner, uid)
+        if result and not result.get("ok") and not result.get("skipped"):
+            raise RuntimeError(result.get("error") or result)
+    except Exception as e:
+        logger.warning("CalDAV %s push failed for uid=%s: %s", action, uid, e)
+        if action in {"create", "update"}:
+            db = SessionLocal()
+            try:
+                ev = _get_or_404_event(db, uid, owner)
+                ev.caldav_sync_pending = action
+                db.commit()
+            except Exception:
+                db.rollback()
+            finally:
+                db.close()
+
+
+def _record_caldav_delete_tombstone(db, ev: CalendarEvent, owner: str) -> None:
+    if not (ev.calendar and ev.calendar.source == "caldav"):
+        return
+    tombstone = db.query(CalendarDeletedEvent).filter(
+        CalendarDeletedEvent.uid == ev.uid,
+        CalendarDeletedEvent.owner == owner,
+    ).first()
+    if not tombstone:
+        tombstone = CalendarDeletedEvent(uid=ev.uid, owner=owner)
+        db.add(tombstone)
+    tombstone.calendar_id = ev.calendar_id
+    tombstone.remote_href = ev.remote_href
+    tombstone.remote_etag = ev.remote_etag
+    tombstone.caldav_base_url = getattr(ev.calendar, "caldav_base_url", None)
+    tombstone.summary = ev.summary or ""
+    tombstone.last_error = None
+
 # ── Pydantic models ──
 
 class EventCreate(BaseModel):
@@ -843,13 +891,13 @@ def setup_calendar_routes() -> APIRouter:
             return {"ok": False, "error": str(e)[:200]}
 
     @router.post("/sync")
-    async def sync_caldav_endpoint(request: Request):
+    async def sync_caldav_endpoint(request: Request, direction: str = "pull"):
-        """Pull events from the configured CalDAV server into local DB.
+        """Sync events with the configured CalDAV server.
         Returns counts + any per-calendar errors. Called by the frontend
         on calendar open and by the periodic scheduler loop."""
         owner = _require_user(request)
-        from src.caldav_sync import sync_caldav
+        from src.caldav_sync import sync_caldav_direction
-        return await sync_caldav(owner)
+        return await sync_caldav_direction(owner, direction)
 
 
     @router.delete("/calendars/{cal_id}")
@@ -1002,19 +1050,12 @@ def setup_calendar_routes() -> APIRouter:
                 is_utc=_is_utc and not data.all_day,
                 rrule=data.rrule or "",
                 color=data.color or None,
+                caldav_sync_pending="create" if cal.source == "caldav" else None,
             )
             db.add(ev)
             db.commit()
             if cal.source == "caldav":
-                # Push the new event to the remote so it appears on the user's
+                await _push_caldav_event_after_commit(owner, uid, "create")
-                # other devices — the sync is otherwise pull-only (#800).
-                from src.caldav_writeback import writeback_event
-                await writeback_event(owner, cal.source, cal.id, {
-                    "uid": uid, "summary": data.summary, "description": data.description,
-                    "location": data.location, "dtstart": dtstart, "dtend": dtend,
-                    "all_day": data.all_day, "is_utc": _is_utc and not data.all_day,
-                    "rrule": data.rrule or "",
-                })
             return {"ok": True, "uid": uid}
         except HTTPException:
             raise
@@ -1060,15 +1101,12 @@ def setup_calendar_routes() -> APIRouter:
                 ev.rrule = data.rrule
             if data.color is not None:
                 ev.color = data.color if data.color else None
+            is_caldav = ev.calendar and ev.calendar.source == "caldav"
+            if is_caldav:
+                ev.caldav_sync_pending = "update"
             db.commit()
-            cal = db.query(CalendarCal).filter(CalendarCal.id == ev.calendar_id).first()
+            if is_caldav:
-            if cal and cal.source == "caldav":
+                await _push_caldav_event_after_commit(owner, base_uid, "update")
-                from src.caldav_writeback import writeback_event
-                await writeback_event(owner, cal.source, cal.id, {
-                    "uid": ev.uid, "summary": ev.summary, "description": ev.description,
-                    "location": ev.location, "dtstart": ev.dtstart, "dtend": ev.dtend,
-                    "all_day": ev.all_day, "is_utc": ev.is_utc, "rrule": ev.rrule or "",
-                })
             return {"ok": True}
         except HTTPException:
             raise
@@ -1089,15 +1127,13 @@ def setup_calendar_routes() -> APIRouter:
         db = SessionLocal()
         try:
             ev = _get_or_404_event(db, base_uid, owner)
-            # Capture what the remote push needs BEFORE the row is gone.
+            is_caldav = ev.calendar and ev.calendar.source == "caldav"
-            _cal = db.query(CalendarCal).filter(CalendarCal.id == ev.calendar_id).first()
+            if is_caldav:
-            _is_caldav = bool(_cal and _cal.source == "caldav")
+                _record_caldav_delete_tombstone(db, ev, owner)
-            _cal_id, _ev_uid = ev.calendar_id, ev.uid
             db.delete(ev)
             db.commit()
-            if _is_caldav:
+            if is_caldav:
-                from src.caldav_writeback import writeback_event
+                await _push_caldav_event_after_commit(owner, base_uid, "delete")
-                await writeback_event(owner, "caldav", _cal_id, {"uid": _ev_uid}, delete=True)
             return {"ok": True}
         except HTTPException:
             raise

routes/chat_helpers.py

@@ -159,9 +159,17 @@ async def auto_name_session(session_manager, sess):
             return
 
         owner = getattr(sess, "owner", None)
-        t_url, t_model, t_headers = resolve_task_endpoint(
+        t_url, t_model, t_headers = resolve_task_endpoint(owner=owner)
-            sess.endpoint_url, sess.model, sess.headers, owner=owner,
+        if not t_model:
-        )
+            # If no task/utility model is configured at all, fall back to
+            # the session's own model so auto-naming still works even on
+            # minimal setups.
+            from src.endpoint_resolver import resolve_endpoint
+            _fallback = resolve_endpoint("default", owner=owner)
+            if _fallback and _fallback[1]:
+                t_url, t_model, t_headers = _fallback
+            else:
+                t_url, t_model, t_headers = sess.endpoint_url, sess.model, sess.headers
         if not t_model:
             logger.debug("[auto-name] No model provided, skipping")
             return
@@ -497,6 +505,29 @@ def _normalize_model_id_from_cache(sess) -> Optional[str]:
     return None
 
 
+def _session_is_research_spinoff(sess) -> bool:
+    """True if this session was created via research "Discuss" spin-off.
+
+    Detected by the primer system message the spin-off endpoint seeds into
+    history (metadata ``research_spinoff_from``). Such sessions are grounded
+    on the seeded report, so global memory + personal-doc RAG injection is
+    suppressed for them (the report is the sole knowledge base). Handles both
+    ChatMessage objects and plain dicts.
+    """
+    for m in getattr(sess, "history", []) or []:
+        role = getattr(m, "role", None)
+        if role is None and isinstance(m, dict):
+            role = m.get("role")
+        if role != "system":
+            continue
+        md = getattr(m, "metadata", None)
+        if md is None and isinstance(m, dict):
+            md = m.get("metadata")
+        if (md or {}).get("research_spinoff_from"):
+            return True
+    return False
+
+
 async def build_chat_context(
     sess,
     request,
@@ -562,9 +593,17 @@ async def build_chat_context(
         mem_enabled, user, incognito, no_memory, uprefs.get("memory_enabled", "NOT_SET"),
     )
 
+    # Research-spinoff ("Discuss") sessions are grounded on the seeded report:
+    # the primer system message IS the knowledge base. Injecting global memory
+    # or personal-doc RAG on every turn pulls in keyword-matched but off-topic
+    # facts ("wrong data") and competes with the report, so suppress both here.
+    is_research_spinoff = _session_is_research_spinoff(sess)
+    if is_research_spinoff:
+        mem_enabled = False
+
     # Use RAG?
     use_rag_val = (str(use_rag).lower() != "false") if use_rag is not None else True
-    if incognito or not allow_tool_preprocessing:
+    if incognito or not allow_tool_preprocessing or is_research_spinoff:
         use_rag_val = False
 
     # If pre-fetched search context was provided (compare mode), skip live web search
@@ -587,7 +626,7 @@ async def build_chat_context(
         incognito=incognito,
         use_skills=skills_enabled,
     )
-    if use_rag is not None:
+    if use_rag is not None or is_research_spinoff:
         _preface_kwargs["use_rag"] = use_rag_val
     preface, rag_sources, web_sources = chat_processor.build_context_preface(**_preface_kwargs)
 

routes/chat_routes.py

@@ -696,7 +696,12 @@ def setup_chat_routes(
         # by default without having to send allow_bash in every request.
         if allow_bash is not None and str(allow_bash).lower() != "true":
             disabled_tools.add("bash")
-        if allow_web_search is not None and str(allow_web_search).lower() != "true":
+        _explicit_web_intent = bool(_tool_intent and _tool_intent.category == "web")
+        if (
+            allow_web_search is not None
+            and str(allow_web_search).lower() != "true"
+            and not _explicit_web_intent
+        ):
             disabled_tools.add("web_search")
             disabled_tools.add("web_fetch")
 

routes/codex_routes.py

@@ -18,6 +18,7 @@ from fastapi.responses import StreamingResponse
 from src.auth_helpers import require_authenticated_request, require_user
 from src.tool_implementations import do_manage_notes
 from src.constants import COOKBOOK_STATE_FILE
+from routes._validators import validate_remote_host, validate_ssh_port
 
 
 COOKBOOK_READ_SCOPES = {"cookbook:read", "cookbook:launch"}
@@ -36,6 +37,21 @@ DOCS_WRITE_SCOPES = {"documents:write"}
 WRITE_ACTIONS = {"add", "create", "new", "save", "remind", "update", "delete", "toggle_item", "remove", "remove_item"}
 
 
+def _ssh_prefix_for_task(task: dict) -> tuple[str, str]:
+    """Resolve a cookbook task's stored SSH target into ``(host, port_flag)``.
+
+    ``host`` is ``""`` for a local task. ``remoteHost`` / ``sshPort`` come from
+    cookbook_state.json and get interpolated into an ``ssh`` command string, so
+    validate them the same way the cookbook routes do. A tampered entry with
+    shell metacharacters in ``remoteHost`` is rejected with 400 rather than
+    injected.
+    """
+    host = validate_remote_host((task.get("remoteHost") or "").strip() or None) or ""
+    ssh_port = validate_ssh_port((task.get("sshPort") or "").strip() or None) or ""
+    port_flag = f"-p {ssh_port} " if ssh_port and ssh_port != "22" else ""
+    return host, port_flag
+
+
 async def _as_owner(request: Request, owner: str, fn, *args, **kwargs):
     """Run an existing route handler with request.state.current_user temporarily
     set to ``owner`` so its internal get_current_user/require_user calls see
@@ -486,8 +502,7 @@ def setup_codex_routes(
         task = next((t for t in tasks if t.get("sessionId") == session_id), None)
         if task is None:
             raise HTTPException(404, "task not found")
-        host = (task.get("remoteHost") or "").strip()
+        host, port_flag = _ssh_prefix_for_task(task)
-        ssh_port = (task.get("sshPort") or "").strip()
         # Prefer the persisted log file over the tmux pane. The pane gets
         # overwritten by the post-crash neofetch banner + bash prompt the
         # moment vllm exits; the log file is the raw stdout/stderr and
@@ -499,7 +514,6 @@ def setup_codex_routes(
             f"else tmux capture-pane -t {session_id} -p -S -{tail}; fi"
         )
         if host:
-            port_flag = f"-p {ssh_port} " if ssh_port and ssh_port != "22" else ""
             import shlex
             cmd = f"ssh {port_flag}{host} {shlex.quote(inner)}"
         else:
@@ -561,10 +575,8 @@ def setup_codex_routes(
         state = _read_cookbook_state()
         tasks = state.get("tasks") or []
         task = next((t for t in tasks if t.get("sessionId") == session_id), None)
-        host = ((task or {}).get("remoteHost") or "").strip()
+        host, port_flag = _ssh_prefix_for_task(task or {})
-        ssh_port = ((task or {}).get("sshPort") or "").strip()
         if host:
-            port_flag = f"-p {ssh_port} " if ssh_port and ssh_port != "22" else ""
             cmd = f"ssh {port_flag}{host} \"tmux kill-session -t {session_id}\""
         else:
             cmd = f"tmux kill-session -t {session_id}"

routes/contacts_routes.py

@@ -45,10 +45,14 @@ def _save_settings(settings):
 def _get_carddav_config():
     import os
     settings = _load_settings()
+    password = settings.get("carddav_password", os.environ.get("CARDDAV_PASSWORD", ""))
+    if password and "carddav_password" in settings:
+        from src.secret_storage import decrypt
+        password = decrypt(password)
     return {
         "url": settings.get("carddav_url", os.environ.get("CARDDAV_URL", "")),
         "username": settings.get("carddav_username", os.environ.get("CARDDAV_USERNAME", "")),
-        "password": settings.get("carddav_password", os.environ.get("CARDDAV_PASSWORD", "")),
+        "password": password,
     }
 
 
@@ -785,7 +789,11 @@ def setup_contacts_routes():
                     except ValueError as e:
                         raise HTTPException(400, str(e))
                 else:
-                    settings[key] = data[key]
+                    value = data[key]
+                    if key == "carddav_password" and value:
+                        from src.secret_storage import encrypt
+                        value = encrypt(value)
+                    settings[key] = value
         _save_settings(settings)
         # Force re-fetch
         _contact_cache["fetched_at"] = None

routes/cookbook_helpers.py

@@ -362,7 +362,12 @@ def _user_shell_path_bootstrap() -> list[str]:
         '  ODYSSEUS_USER_PATH="$("$ODYSSEUS_USER_SHELL" -ic \'printf "__ODYSSEUS_PATH__%s\\n" "$PATH"\' 2>/dev/null | sed -n \'s/^__ODYSSEUS_PATH__//p\' | tail -n 1 || true)"',
         '  if [ -n "$ODYSSEUS_USER_PATH" ]; then export PATH="$ODYSSEUS_USER_PATH:$PATH"; fi',
         'fi',
-        'command -v python3 >/dev/null 2>&1 || python3() { python "$@"; }',
+        # Windows can expose python3 as a Microsoft Store App Execution Alias
+        # under WindowsApps. Git Bash sees that stub as present, but it exits
+        # before running Python. A Windows venv usually has python.exe, not
+        # python3.exe, so treat a missing or WindowsApps python3 as absent.
+        '_odys_py3="$(command -v python3 2>/dev/null || true)"',
+        'case "$_odys_py3" in ""|*[Ww]indows[Aa]pps*) python3() { python "$@"; } ;; esac',
         'command -v python >/dev/null 2>&1 || python() { python3 "$@"; }',
     ]
 
@@ -573,6 +578,36 @@ _GGUF_PRELUDE_RE = re.compile(
 _OLLAMA_HOST_ASSIGNMENT_RE = re.compile(r"(?:^|\s)OLLAMA_HOST=([^\s]+)")
 _OLLAMA_BIND_RE = re.compile(r"^\[([^\]]+)\]:(\d+)$|^([^:]+):(\d+)$")
 _OLLAMA_BIND_HOST_RE = re.compile(r"^[A-Za-z0-9._:-]+$")
+_LLAMA_CPP_PYTHON_GGML_TYPES = {
+    "f32": "0",
+    "f16": "1",
+    "q4_0": "2",
+    "q4_1": "3",
+    "q5_0": "6",
+    "q5_1": "7",
+    "q8_0": "8",
+    "q8_1": "9",
+    "q2_k": "10",
+    "q3_k": "11",
+    "q4_k": "12",
+    "q5_k": "13",
+    "q6_k": "14",
+    "q8_k": "15",
+    "iq2_xxs": "16",
+    "iq2_xs": "17",
+    "iq3_xxs": "18",
+    "iq1_s": "19",
+    "iq4_nl": "20",
+    "iq3_s": "21",
+    "iq2_s": "22",
+    "iq4_xs": "23",
+    "mxfp4": "39",
+    "nvfp4": "40",
+    "q1_0": "41",
+}
+_LLAMA_CPP_PYTHON_TYPE_FLAG_RE = re.compile(
+    r"(?P<flag>--type_[kv])(?P<sep>\s+|=)(?P<quote>['\"]?)(?P<value>[A-Za-z0-9_]+)(?P=quote)"
+)
 
 
 def _ollama_bind_from_cmd(cmd: str | None, *, default_host: str = "127.0.0.1") -> tuple[str, str]:
@@ -604,6 +639,22 @@ def _ollama_bind_from_cmd(cmd: str | None, *, default_host: str = "127.0.0.1") -
     return f"[{host}]" if bracketed_host else host, port
 
 
+def _normalize_llama_cpp_python_cache_types(cmd: str | None) -> str | None:
+    """Map llama.cpp KV cache type names to llama-cpp-python's integer enum."""
+    if not cmd or "llama_cpp.server" not in cmd:
+        return cmd
+
+    def repl(match: re.Match[str]) -> str:
+        value = match.group("value")
+        mapped = _LLAMA_CPP_PYTHON_GGML_TYPES.get(value.lower())
+        if not mapped:
+            return match.group(0)
+        quote = match.group("quote")
+        return f"{match.group('flag')}{match.group('sep')}{quote}{mapped}{quote}"
+
+    return _LLAMA_CPP_PYTHON_TYPE_FLAG_RE.sub(repl, cmd)
+
+
 def _check_serve_binary(seg: str) -> None:
     """Validate that a single command segment starts with an allowlisted binary
     (after skipping leading env-var assignments like `CUDA_VISIBLE_DEVICES=0`)."""
@@ -742,6 +793,7 @@ def _append_llama_cpp_linux_accel_build_lines(runner_lines: list[str]) -> None:
     runner_lines.append('    done')
     # rm -rf build so a prior poisoned CMakeCache.txt (e.g. from a failed CUDA
     # or HIP attempt) doesn't cause the next configure to reuse stale settings.
+    runner_lines.append('    mkdir -p ~/bin')
     runner_lines.append('    cd ~/llama.cpp && rm -rf build')
     runner_lines.append('    if command -v hipconfig &>/dev/null || [ -d /opt/rocm ] || [ -n "$ROCM_PATH" ] || [ -n "$HIP_PATH" ]; then')
     runner_lines.append('      if command -v hipconfig &>/dev/null; then')
@@ -1046,6 +1098,16 @@ def _diagnose_serve_output(text: str) -> dict | None:
             "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)|"
+            r"(Python\.h|libnuma\.so\.1|common_ops)[\s\S]*sgl_kernel|"
+            r"Please ensure sgl_kernel is properly installed",
+            "SGLang native dependencies are missing on this server.",
+            [
+                {"label": "install OS packages: libnuma-dev python3.12-dev build-essential", "op": "manual"},
+                {"label": "upgrade sglang-kernel after OS packages are installed", "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.",

routes/cookbook_output.py

@@ -4,6 +4,62 @@ Kept dependency-free (no FastAPI / SQLAlchemy imports) so the behavior can be
 unit-tested without standing up the whole app.
 """
 
+import re
+
+_FETCHING_ZERO_FILES_RE = re.compile(r"Fetching\s+0\s+files", re.IGNORECASE)
+
+# Probe scripts for the dead-session download check, run as
+# `python3 -c <PROBE> <repo_id> <cache_root>` (locally or over SSH).
+# cache_root is the task's custom download dir, '' for the default HF cache.
+# It has to be passed explicitly: the download runner exports
+# HF_HOME=<local_dir>, so that task's cache lives under <local_dir>/hub, and
+# the probe process's own environment knows nothing about it.
+HF_CACHE_COMPLETE_PROBE = (
+    "import os,sys;"
+    "repo=sys.argv[1];"
+    "root=os.path.expanduser(sys.argv[2]) if len(sys.argv)>2 and sys.argv[2] else '';"
+    "base=os.path.join(root,'hub') if root else (os.environ.get('HUGGINGFACE_HUB_CACHE') or os.path.join(os.environ.get('HF_HOME', os.path.expanduser('~/.cache/huggingface')), 'hub'));"
+    "d=os.path.join(base,'models--'+repo.replace('/','--'));"
+    "snap=os.path.join(d,'snapshots');"
+    "ok=os.path.isdir(snap) and any(os.path.isdir(os.path.join(snap,x)) and os.listdir(os.path.join(snap,x)) for x in os.listdir(snap));"
+    "inc=False;"
+    "blobs=os.path.join(d,'blobs');"
+    "inc=os.path.isdir(blobs) and any(x.endswith('.incomplete') for x in os.listdir(blobs));"
+    "sys.exit(0 if ok and not inc else 1)"
+)
+
+HF_CACHE_INCOMPLETE_PROBE = (
+    "import os,sys;"
+    "repo=sys.argv[1];"
+    "root=os.path.expanduser(sys.argv[2]) if len(sys.argv)>2 and sys.argv[2] else '';"
+    "base=os.path.join(root,'hub') if root else (os.environ.get('HUGGINGFACE_HUB_CACHE') or os.path.join(os.environ.get('HF_HOME', os.path.expanduser('~/.cache/huggingface')), 'hub'));"
+    "d=os.path.join(base,'models--'+repo.replace('/','--'));"
+    "blobs=os.path.join(d,'blobs');"
+    "inc=os.path.isdir(blobs) and any(x.endswith('.incomplete') for x in os.listdir(blobs));"
+    "sys.exit(0 if inc else 1)"
+)
+
+
+def classify_dead_download(full_snapshot: str):
+    """Resolve a dead download session's status from its runner markers.
+
+    The runner prints DOWNLOAD_OK only after exiting 0 (and DOWNLOAD_FAILED
+    otherwise), so the markers stay trustworthy after the tmux pane is gone.
+    Returns (status, zero_files), or None when the snapshot carries no marker
+    and the caller has to fall back to the cache probe. Same precedence as
+    the live-session branch: DOWNLOAD_OK wins, except a "Fetching 0 files"
+    run is an error (nothing matched the include/quant pattern).
+    """
+    if not full_snapshot:
+        return None
+    if "DOWNLOAD_OK" in full_snapshot:
+        if _FETCHING_ZERO_FILES_RE.search(full_snapshot):
+            return ("error", True)
+        return ("completed", False)
+    if "DOWNLOAD_FAILED" in full_snapshot:
+        return ("error", False)
+    return None
+
 
 def error_aware_output_tail(full_snapshot: str, status: str) -> str:
     """Return the trailing slice of a task log for the status response.

routes/cookbook_routes.py

@@ -30,7 +30,10 @@ from core.platform_compat import (
     which_tool,
 )
 from routes.shell_routes import TMUX_LOG_DIR
-from routes.cookbook_output import error_aware_output_tail
+from routes.cookbook_output import (
+    error_aware_output_tail, classify_dead_download,
+    HF_CACHE_COMPLETE_PROBE, HF_CACHE_INCOMPLETE_PROBE,
+)
 
 logger = logging.getLogger(__name__)
 
@@ -46,6 +49,7 @@ from routes.cookbook_helpers import (
     _diagnose_serve_output, run_ssh_command_async,
     _ollama_bind_from_cmd, _pip_install_fallback_chain, _pip_install_no_cache,
     _user_shell_path_bootstrap, _venv_safe_local_pip_install_cmd,
+    _normalize_llama_cpp_python_cache_types,
     ModelDownloadRequest, ServeRequest,
 )
 
@@ -54,7 +58,7 @@ _HF_TOKEN_STATUS_SNIPPET = (
     'echo "[odysseus] HF token: applied"; '
     'else '
     'echo "[odysseus] HF token: NOT SET — gated/private models will be denied. '
-    'Add one in Odysseus Settings -> Cookbook -> HuggingFace Token."; '
+    'Add one in Odysseus Cookbook -> Settings -> HuggingFace Token."; '
     'fi'
 )
 
@@ -170,6 +174,16 @@ def setup_cookbook_routes() -> APIRouter:
                 "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)|"
+                r"(Python\.h|libnuma\.so\.1|common_ops)[\s\S]*sgl_kernel|"
+                r"Please ensure sgl_kernel is properly installed",
+                "SGLang native dependencies are missing on this server.",
+                [
+                    {"label": "install OS packages: libnuma-dev python3.12-dev build-essential", "op": "manual"},
+                    {"label": "upgrade sglang-kernel after OS packages are installed", "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.",
@@ -353,7 +367,11 @@ def setup_cookbook_routes() -> APIRouter:
             # all output to the log the poller reads. Paths handed to bash use
             # POSIX form + shell-quoting so drive paths / spaces survive.
             inner = TMUX_LOG_DIR / f"{session_id}_run.sh"
-            inner.write_text("\n".join(bash_lines) + "\n", encoding="utf-8")
+            pp = shlex.quote(pid_path.as_posix())
+            inner.write_text(
+                f"printf '%s\\n' \"$$\" > {pp}\n" + "\n".join(bash_lines) + "\n",
+                encoding="utf-8",
+            )
             lp = shlex.quote(log_path.as_posix())
             ip = shlex.quote(inner.as_posix())
             script_path = TMUX_LOG_DIR / f"{session_id}.sh"
@@ -1211,6 +1229,7 @@ def setup_cookbook_routes() -> APIRouter:
         # many downstream `"engine" in req.cmd` membership checks can't hit
         # `TypeError: argument of type 'NoneType'` (a 500 instead of a clean 400).
         req.cmd = _validate_serve_cmd(req.cmd) or ""
+        req.cmd = _normalize_llama_cpp_python_cache_types(req.cmd) or ""
         req.cmd = _venv_safe_local_pip_install_cmd(
             req.cmd,
             local=not bool(req.remote_host),
@@ -2620,30 +2639,20 @@ def setup_cookbook_routes() -> APIRouter:
     def _cookbook_tasks_status_sync():
         import subprocess
 
-        def _download_cache_complete(repo_id: str, remote_host: str = "", ssh_port: str = "") -> bool:
+        def _download_cache_complete(repo_id: str, remote_host: str = "", ssh_port: str = "", cache_root: str = "") -> bool:
             """Best-effort check for a completed HF cache entry.
 
             tmux output can stop at a stale progress line if the pane/session
             disappears before Cookbook captures the final DOWNLOAD_OK marker.
             In that case, trust the cache shape: a snapshot directory with files
             and no *.incomplete blobs means HuggingFace finished materializing the
-            model.
+            model. cache_root is the task's custom download dir — the runner
+            pointed HF_HOME there, so the cache lives under <cache_root>/hub,
+            not wherever this probe's environment says.
             """
             if not repo_id or "/" not in repo_id:
                 return False
-            py = (
+            cmd = ["python3", "-c", HF_CACHE_COMPLETE_PROBE, repo_id, cache_root or ""]
-                "import os,sys;"
-                "repo=sys.argv[1];"
-                "base=os.environ.get('HUGGINGFACE_HUB_CACHE') or os.path.join(os.environ.get('HF_HOME', os.path.expanduser('~/.cache/huggingface')), 'hub');"
-                "d=os.path.join(base,'models--'+repo.replace('/','--'));"
-                "snap=os.path.join(d,'snapshots');"
-                "ok=os.path.isdir(snap) and any(os.path.isdir(os.path.join(snap,x)) and os.listdir(os.path.join(snap,x)) for x in os.listdir(snap));"
-                "inc=False;"
-                "blobs=os.path.join(d,'blobs');"
-                "inc=os.path.isdir(blobs) and any(x.endswith('.incomplete') for x in os.listdir(blobs));"
-                "sys.exit(0 if ok and not inc else 1)"
-            )
-            cmd = ["python3", "-c", py, repo_id]
             try:
                 if remote_host:
                     ssh_base = ["ssh"]
@@ -2657,7 +2666,7 @@ def setup_cookbook_routes() -> APIRouter:
             except Exception:
                 return False
 
-        def _download_cache_incomplete(repo_id: str, remote_host: str = "", ssh_port: str = "") -> bool:
+        def _download_cache_incomplete(repo_id: str, remote_host: str = "", ssh_port: str = "", cache_root: str = "") -> bool:
             """Best-effort check for resumable HF partial blobs.
 
             A lost SSH/tmux session can leave a real download still incomplete.
@@ -2666,16 +2675,7 @@ def setup_cookbook_routes() -> APIRouter:
             """
             if not repo_id or "/" not in repo_id:
                 return False
-            py = (
+            cmd = ["python3", "-c", HF_CACHE_INCOMPLETE_PROBE, repo_id, cache_root or ""]
-                "import os,sys;"
-                "repo=sys.argv[1];"
-                "base=os.environ.get('HUGGINGFACE_HUB_CACHE') or os.path.join(os.environ.get('HF_HOME', os.path.expanduser('~/.cache/huggingface')), 'hub');"
-                "d=os.path.join(base,'models--'+repo.replace('/','--'));"
-                "blobs=os.path.join(d,'blobs');"
-                "inc=os.path.isdir(blobs) and any(x.endswith('.incomplete') for x in os.listdir(blobs));"
-                "sys.exit(0 if inc else 1)"
-            )
-            cmd = ["python3", "-c", py, repo_id]
             try:
                 if remote_host:
                     ssh_base = ["ssh"]
@@ -2880,7 +2880,7 @@ def setup_cookbook_routes() -> APIRouter:
                 and (
                     ".incomplete" in full_snapshot
                     or bool(re.search(r'model-\d+-of-\d+\.[A-Za-z0-9_.-]+:\s+(?:[0-9]|[1-8][0-9])%', full_snapshot))
-                    or _download_cache_incomplete(_payload.get("repo_id") or model, remote, str(_tport or ""))
+                    or _download_cache_incomplete(_payload.get("repo_id") or model, remote, str(_tport or ""), _payload.get("local_dir") or "")
                 )
             )
             if is_alive or (local_win_task and full_snapshot):
@@ -2921,11 +2921,19 @@ def setup_cookbook_routes() -> APIRouter:
                 else:
                     status = "running"
             else:
-                # Session is dead — check if it completed or crashed
+                # Session is dead — check if it completed or crashed. The
-                if (
+                # runner markers in the retained output are conclusive
+                # (DOWNLOAD_OK only prints after exit 0), so check them before
+                # the cache probe, which can't see ollama pulls at all.
+                marker = classify_dead_download(full_snapshot) if task_type == "download" else None
+                if marker is not None:
+                    status, download_zero_files = marker
+                    if status == "completed" and not progress_text:
+                        progress_text = "Download complete"
+                elif (
                     task_type == "download"
                     and not download_has_incomplete_evidence
-                    and _download_cache_complete(_payload.get("repo_id") or model, remote, str(_tport or ""))
+                    and _download_cache_complete(_payload.get("repo_id") or model, remote, str(_tport or ""), _payload.get("local_dir") or "")
                 ):
                     status = "completed"
                     if not progress_text:

routes/diagnostics_routes.py

@@ -1,12 +1,13 @@
 """Diagnostics routes — /api/db/stats, /api/rag/stats, /api/test/youtube, /api/test-research."""
 
 import logging
+import os
 from typing import Dict, Any
 
 from fastapi import APIRouter, HTTPException, Form, Request
 
 from services.youtube.youtube_handler import extract_youtube_id, extract_transcript_async
-from core.constants import DEFAULT_HOST
+from core.constants import DEFAULT_HOST, DATA_DIR
 from core.middleware import require_admin
 
 logger = logging.getLogger(__name__)
@@ -28,6 +29,30 @@ def setup_diagnostics_routes(
         from src.service_health import collect_service_health
         return await collect_service_health(rag_manager, memory_vector)
 
+    @router.get("/api/diagnostics/logs")
+    async def get_diagnostics_logs(request: Request, limit: int = 200) -> Dict[str, Any]:
+        require_admin(request)
+        limit = max(1, min(limit, 1000))
+        try:
+            log_file = os.path.join(DATA_DIR, "logs", "app.log")
+            if not os.path.exists(log_file):
+                return {"status": "success", "logs": []}
+
+            # Safe tail read of the log file (max 5MB via rotation)
+            with open(log_file, "r", encoding="utf-8", errors="ignore") as f:
+                lines = f.readlines()
+
+            tail_lines = lines[-limit:] if len(lines) > limit else lines
+            tail_lines = [line.rstrip('\r\n') for line in tail_lines]
+
+            return {
+                "status": "success",
+                "logs": tail_lines
+            }
+        except Exception as e:
+            logger.error(f"Diagnostics logs retrieval error: {e}")
+            raise HTTPException(500, f"Failed to retrieve logs: {str(e)}")
+
     @router.get("/api/db/stats")
     async def get_database_stats(request: Request) -> Dict[str, Any]:
         require_admin(request)

routes/email_routes.py

@@ -1087,7 +1087,10 @@ def setup_email_routes():
             return {"contacts": [], "error": "Mail operation failed"}
 
     @router.get("/search")
-    async def search_emails(
+    # Sync def: the body is blocking IMAP I/O with no awaits. As `async def` it ran
+    # directly on the event loop and stalled the whole app during a search; as a sync
+    # def FastAPI runs it in a threadpool, keeping the loop responsive.
+    def search_emails(
         q: str = Query(""),
         folder: str = Query("INBOX"),
         limit: int = Query(50),
@@ -1736,7 +1739,9 @@ def setup_email_routes():
             return {"success": False, "error": "Mail operation failed"}
 
     @router.post("/archive/{uid}")
-    async def archive_email(uid: str, folder: str = Query("INBOX"), account_id: str | None = Query(None), owner: str = Depends(require_owner)):
+    # Sync def: blocking IMAP I/O with no awaits — see search_emails above. Runs in a
+    # threadpool instead of blocking the event loop.
+    def archive_email(uid: str, folder: str = Query("INBOX"), account_id: str | None = Query(None), owner: str = Depends(require_owner)):
         """Move email to Archive folder."""
         try:
             with _imap(account_id, owner=owner) as conn:

routes/gallery_routes.py

@@ -19,6 +19,7 @@ from src.upload_limits import (
     GALLERY_TRANSFORM_UPLOAD_MAX_BYTES,
 )
 from src.constants import GENERATED_IMAGES_DIR
+from src.optional_deps import patch_realesrgan_torchvision_compat
 
 from routes.gallery_helpers import (
     GalleryPatch, _extract_exif, _image_to_dict, _owner_filter, _human_size,
@@ -108,6 +109,32 @@ def _visible_image_endpoint_for_base(db, base: str, owner: str | None):
     return fallback
 
 
+async def _fetch_result_image_b64(url: str) -> Optional[str]:
+    """Fetch an image URL returned in an upstream response body, base64-encoded
+    (or None on a non-200).
+
+    The URL comes from the diffusion/OpenAI server's response, not from our own
+    config, so a malicious or compromised endpoint could otherwise steer this
+    fetch at an internal or cloud-metadata address. Validate it the same way the
+    client-supplied endpoint is validated before the first request.
+    """
+    import base64
+    import httpx
+    from src.url_safety import check_outbound_url
+
+    ok, reason = check_outbound_url(
+        url,
+        block_private=os.getenv("IMAGE_BLOCK_PRIVATE_IPS", "false").lower() == "true",
+    )
+    if not ok:
+        raise HTTPException(502, f"Upstream returned an unsafe image URL: {reason}")
+    async with httpx.AsyncClient(timeout=60) as c2:
+        ir = await c2.get(url)
+        if ir.status_code == 200:
+            return base64.b64encode(ir.content).decode()
+    return None
+
+
 def setup_gallery_routes() -> APIRouter:
     router = APIRouter(tags=["gallery"])
 
@@ -904,14 +931,22 @@ def setup_gallery_routes() -> APIRouter:
                 raise HTTPException(404, "Image not found")
 
             img_filename = img.filename
-            # Remove the file from disk
+            # Soft-delete the record first; the DB is the source of truth.
+            img.is_active = False
+            db.commit()
+
+            # Only after the soft-delete commit succeeds do we remove the file.
+            # If the file were deleted first and the commit then failed/rolled
+            # back, the still-active record would point at a missing file.
+            # Best-effort so a missing or locked file can't 500 a delete that
+            # already succeeded logically. Uses the path-confined resolver so a
+            # malformed stored filename can't escape generated_images.
+            try:
                 img_path = _gallery_image_path(img_filename)
                 if img_path.exists():
                     img_path.unlink()
-
+            except Exception as e:
-            # Soft-delete the record
+                logger.warning(f"Could not remove gallery image file for {img_filename}: {e}")
-            img.is_active = False
-            db.commit()
 
             # Strip stale chat-history references so the image bubble
             # (and its prompt caption) doesn't come back after a server
@@ -1142,10 +1177,7 @@ def setup_gallery_routes() -> APIRouter:
                         if item.get("b64_json"):
                             raw_b64 = item["b64_json"]
                         elif item.get("url"):
-                            async with httpx.AsyncClient(timeout=60) as c2:
+                            raw_b64 = await _fetch_result_image_b64(item["url"])
-                                img_r = await c2.get(item["url"])
-                                if img_r.status_code == 200:
-                                    raw_b64 = base64.b64encode(img_r.content).decode()
                     if not raw_b64:
                         raise HTTPException(502, "OpenAI returned no image")
 
@@ -1206,7 +1238,7 @@ def setup_gallery_routes() -> APIRouter:
         original and regenerates `strength` fraction. With strength ~0.4
         you get edge blending + lighting unification while keeping the
         composition recognisable."""
-        import httpx, base64 as _b64
+        import httpx
         user = require_privilege(request, "can_generate_images")
         body = await request.json()
 
@@ -1382,10 +1414,9 @@ def setup_gallery_routes() -> APIRouter:
                             if item.get("b64_json"):
                                 return {"image": item["b64_json"]}
                             if item.get("url"):
-                                async with httpx.AsyncClient(timeout=60) as c2:
+                                img_b64 = await _fetch_result_image_b64(item["url"])
-                                    ir = await c2.get(item["url"])
+                                if img_b64:
-                                    if ir.status_code == 200:
+                                    return {"image": img_b64}
-                                        return {"image": _b64.b64encode(ir.content).decode()}
                     last_err = f"{path}: server returned no image"
                 except httpx.ConnectError as e:
                     raise HTTPException(502, f"Can't reach diffusion server at {base}: {e}")
@@ -1445,6 +1476,7 @@ def setup_gallery_routes() -> APIRouter:
         img_bytes = base64.b64decode(image_b64)
         src = Image.open(io.BytesIO(img_bytes)).convert("RGB")
         try:
+            patch_realesrgan_torchvision_compat()
             from realesrgan import RealESRGANer
         except ImportError:
             return {"error": "realesrgan not installed. Install it from Cookbook → Dependencies (search 'realesrgan')."}
@@ -1494,6 +1526,7 @@ def setup_gallery_routes() -> APIRouter:
         img_bytes = base64.b64decode(image_b64)
         src = Image.open(io.BytesIO(img_bytes)).convert("RGB")
         try:
+            patch_realesrgan_torchvision_compat()
             from basicsr.archs.rrdbnet_arch import RRDBNet
             from realesrgan import RealESRGANer
         except ImportError:

routes/mcp_routes.py

@@ -108,6 +108,12 @@ def _load_disabled_map():
         db.close()
 
 
+def _mcp_oauth_redirect_uri() -> str:
+    """Shared callback URL for legacy Google and generic MCP OAuth flows."""
+    from src.mcp_oauth import REDIRECT_URI
+    return REDIRECT_URI
+
+
 def setup_mcp_routes(mcp_manager: McpManager):
     """Setup MCP routes with the provided manager."""
 
@@ -445,9 +451,9 @@ def setup_mcp_routes(mcp_manager: McpManager):
             client_id = keys["client_id"]
             scopes = oauth_cfg.get("scopes", [])
 
-            # For Desktop App creds, redirect to localhost — the user will
+            # For Desktop App creds, default to localhost — the user will
             # paste the resulting URL back if they're on a different device.
-            redirect_uri = "http://localhost:7000/api/mcp/oauth/callback"
+            redirect_uri = _mcp_oauth_redirect_uri()
 
             params = {
                 "client_id": client_id,
@@ -469,7 +475,7 @@ def setup_mcp_routes(mcp_manager: McpManager):
                 return RedirectResponse(auth_url)
             else:
                 # Remote device — show paste-back page
-                return HTMLResponse(_oauth_authorize_page(auth_url, server_id, host))
+                return HTMLResponse(_oauth_authorize_page(auth_url, server_id, host, redirect_uri))
         finally:
             db.close()
 
@@ -536,7 +542,7 @@ def setup_mcp_routes(mcp_manager: McpManager):
             client_id = keys["client_id"]
             client_secret = keys["client_secret"]
 
-            redirect_uri = "http://localhost:7000/api/mcp/oauth/callback"
+            redirect_uri = _mcp_oauth_redirect_uri()
 
             async with httpx.AsyncClient() as client:
                 resp = await client.post(
@@ -603,13 +609,19 @@ def setup_mcp_routes(mcp_manager: McpManager):
     return router
 
 
-def _oauth_authorize_page(auth_url: str, server_id: str, host: str) -> str:
+def _oauth_authorize_page(
+    auth_url: str,
+    server_id: str,
+    host: str,
+    redirect_uri: str = "http://localhost:7000/api/mcp/oauth/callback",
+) -> str:
     """Page with Google sign-in link and URL paste-back form for remote access."""
     # Escape values interpolated into the page: `host` comes from the request
     # Host header and `server_id` from the OAuth state — neither is trusted.
     auth_url = html.escape(auth_url, quote=True)
     server_id = html.escape(server_id, quote=True)
     host = html.escape(host, quote=True)
+    redirect_uri = html.escape(redirect_uri, quote=True)
     return f"""<!DOCTYPE html>
 <html><head>
 <meta charset="UTF-8"><title>Authorize — Odysseus</title>
@@ -654,7 +666,7 @@ def _oauth_authorize_page(auth_url: str, server_id: str, host: str) -> str:
   <div class="divider"></div>
   <form method="POST" action="http://{host}/api/mcp/oauth/exchange/{server_id}">
     <p>Paste the URL from your browser after signing in:</p>
-    <input type="text" name="callback_url" placeholder="http://localhost:7000/api/mcp/oauth/callback?code=..." required>
+    <input type="text" name="callback_url" placeholder="{redirect_uri}?code=..." required>
     <br><button type="submit">Connect</button>
   </form>
 </div></body></html>"""

routes/memory_routes.py

@@ -29,6 +29,7 @@ from src.llm_core import llm_call_async
 from services.memory.memory_extractor import audit_memories
 from src.auth_helpers import get_current_user, require_user
 from src.endpoint_resolver import resolve_endpoint
+from src.task_endpoint import resolve_task_endpoint
 from src.upload_limits import read_upload_limited, MEMORY_IMPORT_MAX_BYTES
 
 logger = logging.getLogger(__name__)
@@ -240,14 +241,18 @@ def setup_memory_routes(memory_manager: MemoryManager, session_manager: SessionM
         }
         messages = [system_msg] + sess.get_context_messages()
 
+        t_url, t_model, t_headers = resolve_task_endpoint(
+            sess.endpoint_url, sess.model, sess.headers, owner=_owner(request)
+        )
+
         try:
             suggestion_text = await llm_call_async(
-                sess.endpoint_url,
+                t_url,
-                sess.model,
+                t_model,
                 messages,
                 temperature=0.2,
                 max_tokens=500,
-                headers=sess.headers,
+                headers=t_headers,
             )
             try:
                 suggestions = json.loads(suggestion_text)
@@ -278,7 +283,15 @@ def setup_memory_routes(memory_manager: MemoryManager, session_manager: SessionM
         endpoint_url = model = None
         headers = {}
 
-        # Try default model from settings first
+        # Try utility model from settings first — memory audit is a background
+        # task and should prefer the lighter utility model over the main chat model.
+        from src.task_endpoint import resolve_task_endpoint
+        user = _owner(request)
+        t_url, t_model, t_headers = resolve_task_endpoint(owner=user)
+        if t_url and t_model:
+            endpoint_url, model, headers = t_url, t_model, t_headers
+        else:
+            # Fall back to default model if no task/utility model configured
             settings = _load_settings()
             ep_id = settings.get("default_endpoint_id", "")
             default_model = settings.get("default_model", "")
@@ -360,13 +373,14 @@ def setup_memory_routes(memory_manager: MemoryManager, session_manager: SessionM
             try:
                 sess = session_manager.get_session(session)
                 _assert_session_owner(sess, _owner(request))
-                endpoint_url = sess.endpoint_url
+                endpoint_url, model, headers = resolve_task_endpoint(
-                model = sess.model
+                    sess.endpoint_url, sess.model, sess.headers, owner=_owner(request)
-                headers = sess.headers
+                )
             except KeyError:
-                 raise HTTPException(404, "Session not found — needed for LLM config")
+                logger.warning("Session %s not found, falling back to utility endpoint", session)
-        else:
                 endpoint_url, model, headers = resolve_endpoint("utility", owner=_owner(request))
+        else:
+            endpoint_url, model, headers = resolve_task_endpoint(owner=_owner(request))
     
         if not endpoint_url or not model:
             raise HTTPException(400, "No LLM model configured. Set a default model in Settings.")

routes/model_routes.py

@@ -248,6 +248,9 @@ _PROVIDER_CURATED = {
     "zai-coding": [
         "glm-5.1", "glm-5v-turbo", "glm-5-turbo", "glm-4.7", "glm-4.5-air",
     ],
+    "kimi-code": [
+        "kimi-for-coding",
+    ],
     "deepseek": [
         "deepseek-chat", "deepseek-reasoner",
     ],
@@ -315,6 +318,8 @@ def _match_provider_curated(base_url: str, provider: str) -> str:
     parsed = urlparse(base_url)
     if _host_match(base_url, "z.ai") and "/api/coding" in (parsed.path or ""):
         return "zai-coding"
+    if _host_match(base_url, "kimi.com") and "/coding" in (parsed.path or ""):
+        return "kimi-code"
     for domain, key in _HOST_TO_CURATED:
         if _host_match(base_url, domain):
             return key
@@ -703,6 +708,7 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
     """Probe a base URL's /models endpoint and return list of model IDs.
     For Anthropic, queries their /v1/models API, falling back to hardcoded list."""
     from src.endpoint_resolver import resolve_url
+    from src.llm_core import httpx_get_kimi_aware
     base = resolve_url(_normalize_base(base_url))
     provider = _safe_detect_provider(base)
     if provider == "chatgpt-subscription":
@@ -738,7 +744,7 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
     url = _safe_build_models_url(base)
     headers = _safe_build_headers(api_key, base)
     try:
-        r = httpx.get(url, headers=headers, timeout=timeout, verify=llm_verify())
+        r = httpx_get_kimi_aware(url, headers, timeout=timeout, verify=llm_verify())
         r.raise_for_status()
         data = r.json()
         # OpenAI format: {"data": [{"id": "model-name"}]}
@@ -754,6 +760,11 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
                 for _e in _PROVIDER_CURATED.get(_ck, []):
                     if _e not in set(models) and not any(m.startswith(_e) for m in models):
                         models.append(_e)
+            if _host_match(base, "kimi.com") and "/coding" in (urlparse(base).path or ""):
+                _ck = _match_provider_curated(base, None)
+                for _e in _PROVIDER_CURATED.get(_ck, []):
+                    if _e not in set(models) and not any(m.startswith(_e) for m in models):
+                        models.append(_e)
             return [m for m in models if _is_chat_model(m)]
     except httpx.HTTPStatusError as e:
         if api_key:
@@ -870,15 +881,52 @@ def _ping_endpoint(base_url: str, api_key: str = None, timeout: float = 1.5) ->
 
 
 def _model_endpoint_error_message(base_url: str, ping: Dict[str, Any] = None) -> str:
-    """Return a provider-aware error message for failed endpoint probes."""
+    """Return a provider-aware error message for failed endpoint probes.
+
+    Surfaces the URL we actually probed and, when the endpoint looks like
+    LM Studio (port 1234 or hostname match), adds a hint about loading a
+    model and confirming the Developer Server is running. The user previously
+    saw a generic "No models found for that provider/key" with no way to
+    tell whether the URL was wrong, the server was down, or the server was
+    reachable but had no model loaded (issue #25).
+    """
     ping = ping or {}
     error = ping.get("error")
+    from src.endpoint_resolver import build_models_url
+    try:
+        probed = build_models_url(base_url) or base_url
+    except Exception:
+        probed = base_url
     parsed = urlparse(base_url)
     host = (parsed.hostname or "").lower()
     is_ollama = parsed.port == 11434 or "ollama" in host or "ollama" in base_url.lower()
+    is_lmstudio = (
+        parsed.port == 1234
+        or "lmstudio" in host
+        or "lm-studio" in host
+        or "lm_studio" in host
+    )
+
+    if is_lmstudio:
+        parts = [
+            "LM Studio is reachable, but no models were reported.",
+            f"Probed {probed}.",
+        ]
+        if error:
+            parts.append(f"Last probe error: {error}.")
+        parts.append(
+            "Open LM Studio, load at least one model, and confirm the "
+            "Developer Server is running on port 1234."
+        )
+        parts.append(
+            "Base URL should be http://localhost:1234/v1 (native) or "
+            "http://host.docker.internal:1234/v1 (Docker)."
+        )
+        return " ".join(parts)
 
     if is_ollama:
         parts = ["No Ollama models found for that endpoint."]
+        parts.append(f"Probed {probed}.")
         if error:
             parts.append(f"Last probe error: {error}.")
         parts.append("Check that Ollama is running and that the base URL is correct.")
@@ -888,9 +936,9 @@ def _model_endpoint_error_message(base_url: str, ping: Dict[str, Any] = None) ->
         return " ".join(parts)
 
     if error:
-        return f"No models found for that provider/key. Last probe error: {error}."
+        return f"No models found for that provider/key. Probed {probed}. Last probe error: {error}."
 
-    return "No models found for that provider/key."
+    return f"No models found for that provider/key. Probed {probed}."
 
 
 def _normalize_model_ids(value):

routes/personal_routes.py

@@ -160,8 +160,11 @@ def setup_personal_routes(personal_docs_manager, rag_manager, rag_available):
             JSON response confirming removal
         """
         try:
-            if not directory:
+            # Confine to PERSONAL_DIR — parity with add_directory_to_rag (which
-                raise HTTPException(400, "Directory path is required")
+            # resolves the path the same way). Without this, an arbitrary or
+            # `..`-escaping path is passed straight to
+            # personal_docs_manager.remove_directory / rag.remove_directory.
+            directory = _resolve_allowed_personal_dir(directory)
 
             logger.info(f"Removing directory from RAG: {directory}")
 

routes/shell_routes.py

@@ -1,6 +1,7 @@
 """Shell routes — user-facing command execution endpoint."""
 
 import asyncio
+import importlib
 import json
 import logging
 import os
@@ -14,6 +15,7 @@ from collections import namedtuple
 from pathlib import Path
 from typing import Dict, Any
 from core.platform_compat import IS_APPLE_SILICON, which_tool
+from src.optional_deps import prepare_optional_dependency_import
 
 # POSIX-only: `pty`/`fcntl` transitively import `termios`, which does NOT exist
 # on Windows, so importing them unconditionally crashed app startup there
@@ -149,6 +151,11 @@ def _pip_dist_name(pkg: dict) -> str:
     return (pkg.get("name") or "").replace("_", "-")
 
 
+def _import_optional_dependency_for_status(name: str):
+    prepare_optional_dependency_import(name)
+    return importlib.import_module(name)
+
+
 def _package_installed_from_probe(name: str, probe: dict) -> bool:
     """Return whether an optional dependency is usable by Cookbook.
 
@@ -970,7 +977,6 @@ def setup_shell_routes() -> APIRouter:
         """
         _require_admin(request)
         _reject_cross_site(request)
-        import importlib
         import importlib.metadata as importlib_metadata
         import shlex
         import json as _json
@@ -1057,6 +1063,13 @@ def setup_shell_routes() -> APIRouter:
                 "category": "Image",
                 "target": "remote",
             },
+            {
+                "name": "transformers",
+                "pip": "transformers",
+                "desc": "Hugging Face model components used by SD/Flux pipelines and image tools",
+                "category": "Image",
+                "target": "remote",
+            },
             {
                 "name": "rembg",
                 "pip": "rembg[gpu]",
@@ -1202,7 +1215,7 @@ def setup_shell_routes() -> APIRouter:
                     pkg["status_note"] = _package_status_note("vllm", probe)
             else:
                 try:
-                    importlib.import_module(pkg["name"])
+                    _import_optional_dependency_for_status(pkg["name"])
                     importlib_metadata.version(_pip_dist_name(pkg))
                     pkg["installed"] = True
                 except ImportError:
@@ -1251,6 +1264,7 @@ def setup_shell_routes() -> APIRouter:
             "sglang[all]",
             "diffusers",
             "diffusers[torch]",
+            "transformers",
             "TTS",
             "bark",
             "faster-whisper",

routes/webhook_routes.py

@@ -198,6 +198,8 @@ def setup_webhook_routes(
         "opencode-go": "https://opencode.ai/zen/go/v1",
         "fireworks": "https://api.fireworks.ai/inference/v1",
         "venice": "https://api.venice.ai/api/v1",
+        "kimi-code": "https://api.kimi.com/coding/v1",
+        "kimicode": "https://api.kimi.com/coding/v1",
     }
 
     # Model prefix → provider mapping for auto-detection
@@ -210,6 +212,8 @@ def setup_webhook_routes(
         "mistral": "mistral",
         "llama": "groq",
         "mixtral": "groq",
+        "kimi-for-coding": "kimi-code",
+        "kimi": "kimi-code",
     }
 
     def _resolve_base_url(model: Optional[str], provider: Optional[str]) -> Optional[str]:

scripts/agent_migration_manifest.py

@@ -0,0 +1,635 @@
+#!/usr/bin/env python3
+"""Build a neutral agent migration manifest.
+
+This helper is intentionally read-only. It does not import the Odysseus
+application package, write to data/, call an LLM, or apply anything. It turns
+common agent export shapes into a portable JSON manifest that Odysseus can
+preview or import later.
+"""
+from __future__ import annotations
+
+import argparse
+import hashlib
+import json
+import mimetypes
+import sys
+from dataclasses import dataclass
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any, Iterable
+
+
+SCHEMA_VERSION = "agent-migration.v1"
+TEXT_EXTENSIONS = {
+    ".cfg",
+    ".conf",
+    ".csv",
+    ".json",
+    ".log",
+    ".md",
+    ".markdown",
+    ".py",
+    ".rst",
+    ".toml",
+    ".txt",
+    ".yaml",
+    ".yml",
+}
+
+
+@dataclass(frozen=True)
+class InputWarning:
+    path: str
+    message: str
+
+
+def utc_now_iso() -> str:
+    return datetime.now(timezone.utc).replace(microsecond=0).isoformat().replace("+00:00", "Z")
+
+
+def sha256_text(text: str) -> str:
+    return hashlib.sha256(text.encode("utf-8")).hexdigest()
+
+
+def sha256_bytes(data: bytes) -> str:
+    return hashlib.sha256(data).hexdigest()
+
+
+def sha256_path(path: Path) -> str:
+    h = hashlib.sha256()
+    with path.open("rb") as f:
+        for chunk in iter(lambda: f.read(65536), b""):
+            h.update(chunk)
+    return h.hexdigest()
+
+
+def stable_id(kind: str, source_name: str, *parts: Any) -> str:
+    raw = "\x1f".join([kind, source_name, *[str(part) for part in parts]])
+    return f"{kind}:{hashlib.sha256(raw.encode('utf-8')).hexdigest()[:16]}"
+
+
+def read_json(path: Path) -> Any:
+    with path.open("r", encoding="utf-8") as handle:
+        return json.load(handle)
+
+
+def normalize_category(value: Any) -> str:
+    category = str(value or "fact").strip().lower()
+    return category or "fact"
+
+
+def normalize_memory_text(item: Any) -> str:
+    if isinstance(item, str):
+        return item.strip()
+    if isinstance(item, dict):
+        for key in ("text", "content", "memory", "value"):
+            value = item.get(key)
+            if isinstance(value, str) and value.strip():
+                return value.strip()
+    return ""
+
+
+def memory_metadata(item: Any, source_path: Path, index: int) -> dict[str, Any]:
+    metadata: dict[str, Any] = {
+        "source_path": str(source_path),
+        "source_index": index,
+    }
+    if isinstance(item, dict):
+        for key in ("id", "timestamp", "created_at", "updated_at", "source", "tags", "pinned"):
+            if key in item:
+                metadata[f"source_{key}"] = item.get(key)
+    return metadata
+
+
+def payload_items(payload: Any, keys: tuple[str, ...]) -> Any:
+    if isinstance(payload, dict):
+        for key in keys:
+            if isinstance(payload.get(key), list):
+                return payload[key]
+    return payload
+
+
+def collect_memory_json(path: Path, source_name: str) -> tuple[list[dict[str, Any]], list[InputWarning]]:
+    warnings: list[InputWarning] = []
+    try:
+        payload = read_json(path)
+    except Exception as exc:
+        return [], [InputWarning(str(path), f"could not read JSON: {exc}")]
+
+    payload = payload_items(payload, ("memories", "memory", "items", "data"))
+
+    if not isinstance(payload, list):
+        return [], [InputWarning(str(path), "expected a JSON list or an object containing a memory list")]
+
+    items: list[dict[str, Any]] = []
+    seen: set[str] = set()
+    for index, item in enumerate(payload):
+        text = normalize_memory_text(item)
+        if not text:
+            warnings.append(InputWarning(str(path), f"skipped memory at index {index}: missing text"))
+            continue
+        digest = sha256_text(text.strip().lower())
+        if digest in seen:
+            warnings.append(InputWarning(str(path), f"skipped duplicate memory at index {index}"))
+            continue
+        seen.add(digest)
+        category = normalize_category(item.get("category") if isinstance(item, dict) else "fact")
+        source = str(item.get("source") or source_name) if isinstance(item, dict) else source_name
+        items.append(
+            {
+                "id": stable_id("memory", source_name, path, index, digest),
+                "kind": "memory",
+                "text": text,
+                "category": category,
+                "source": source,
+                "metadata": memory_metadata(item, path, index),
+            }
+        )
+    return items, warnings
+
+
+def normalize_timestamp(value: Any) -> str | None:
+    if value is None or value == "":
+        return None
+    if isinstance(value, (int, float)):
+        try:
+            return (
+                datetime.fromtimestamp(float(value), timezone.utc)
+                .replace(microsecond=0)
+                .isoformat()
+                .replace("+00:00", "Z")
+            )
+        except (OverflowError, OSError, ValueError):
+            return str(value)
+    return str(value)
+
+
+def normalize_role(value: Any) -> str:
+    role = str(value or "unknown").strip().lower()
+    if role in {"human", "user"}:
+        return "user"
+    if role in {"assistant", "ai", "bot", "model"}:
+        return "assistant"
+    if role in {"system", "tool"}:
+        return role
+    return role or "unknown"
+
+
+def content_part_text(part: Any) -> str:
+    if isinstance(part, str):
+        return part
+    if isinstance(part, dict):
+        for key in ("text", "content", "value"):
+            value = part.get(key)
+            if isinstance(value, str):
+                return value
+        if part.get("type") == "text" and isinstance(part.get("text"), str):
+            return part["text"]
+    return ""
+
+
+def normalize_message_text(message: dict[str, Any]) -> str:
+    content = message.get("content")
+    if isinstance(content, str):
+        return content
+    if isinstance(content, list):
+        return "\n".join(text for text in (content_part_text(part).strip() for part in content) if text)
+    if isinstance(content, dict):
+        parts = content.get("parts")
+        if isinstance(parts, list):
+            return "\n".join(text for text in (content_part_text(part).strip() for part in parts) if text)
+        for key in ("text", "content", "value"):
+            value = content.get(key)
+            if isinstance(value, str):
+                return value
+    for key in ("text", "body", "message"):
+        value = message.get(key)
+        if isinstance(value, str):
+            return value
+    return ""
+
+
+def normalize_message(message: dict[str, Any]) -> dict[str, Any] | None:
+    author = message.get("author") if isinstance(message.get("author"), dict) else {}
+    role = (
+        message.get("role")
+        or message.get("sender")
+        or message.get("speaker")
+        or author.get("role")
+        or author.get("name")
+    )
+    text = normalize_message_text(message).strip()
+    if not text:
+        return None
+    normalized: dict[str, Any] = {
+        "role": normalize_role(role),
+        "text": text,
+    }
+    timestamp = normalize_timestamp(message.get("created_at") or message.get("create_time") or message.get("timestamp"))
+    if timestamp:
+        normalized["created_at"] = timestamp
+    message_id = message.get("id")
+    if message_id is not None:
+        normalized["source_id"] = str(message_id)
+    return normalized
+
+
+def chatgpt_mapping_messages(conversation: dict[str, Any]) -> list[dict[str, Any]]:
+    mapping = conversation.get("mapping")
+    if not isinstance(mapping, dict):
+        return []
+    rows: list[tuple[float, int, dict[str, Any]]] = []
+    for index, node in enumerate(mapping.values()):
+        if not isinstance(node, dict) or not isinstance(node.get("message"), dict):
+            continue
+        message = node["message"]
+        sort_value = message.get("create_time")
+        try:
+            sort_key = float(sort_value)
+        except (TypeError, ValueError):
+            sort_key = float(index)
+        normalized = normalize_message(message)
+        if normalized:
+            rows.append((sort_key, index, normalized))
+    return [row[2] for row in sorted(rows, key=lambda row: (row[0], row[1]))]
+
+
+def conversation_messages(conversation: dict[str, Any]) -> tuple[list[dict[str, Any]], str]:
+    mapped = chatgpt_mapping_messages(conversation)
+    if mapped:
+        return mapped, "chatgpt_mapping"
+    for key in ("messages", "chat_messages", "turns"):
+        raw_messages = conversation.get(key)
+        if isinstance(raw_messages, list):
+            messages = [
+                normalized
+                for raw in raw_messages
+                if isinstance(raw, dict)
+                for normalized in [normalize_message(raw)]
+                if normalized
+            ]
+            return messages, key
+    return [], "unknown"
+
+
+def conversation_title(conversation: dict[str, Any], index: int) -> str:
+    for key in ("title", "name", "summary"):
+        value = conversation.get(key)
+        if isinstance(value, str) and value.strip():
+            return value.strip()
+    return f"Conversation {index + 1}"
+
+
+def collect_conversation_json(
+    path: Path,
+    source_name: str,
+    *,
+    include_content: bool = False,
+    max_messages: int = 2000,
+) -> tuple[list[dict[str, Any]], list[InputWarning]]:
+    warnings: list[InputWarning] = []
+    try:
+        payload = read_json(path)
+    except Exception as exc:
+        return [], [InputWarning(str(path), f"could not read JSON: {exc}")]
+
+    payload = payload_items(payload, ("conversations", "conversation", "items", "data"))
+    if isinstance(payload, dict):
+        payload = [payload]
+    if not isinstance(payload, list):
+        return [], [InputWarning(str(path), "expected a JSON list or an object containing a conversation list")]
+
+    items: list[dict[str, Any]] = []
+    for index, conversation in enumerate(payload):
+        if not isinstance(conversation, dict):
+            warnings.append(InputWarning(str(path), f"skipped conversation at index {index}: expected object"))
+            continue
+        messages, format_hint = conversation_messages(conversation)
+        if not messages:
+            warnings.append(InputWarning(str(path), f"skipped conversation at index {index}: no text messages found"))
+            continue
+        title = conversation_title(conversation, index)
+        source_id = conversation.get("id") or conversation.get("uuid") or conversation.get("conversation_id")
+        text_digest = sha256_text("\n".join(f"{msg['role']}:{msg['text']}" for msg in messages))
+        metadata: dict[str, Any] = {
+            "source_path": str(path),
+            "source_index": index,
+            "source_format": format_hint,
+            "message_count": len(messages),
+            "text_sha256": text_digest,
+            "content_included": False,
+        }
+        if source_id is not None:
+            metadata["source_id"] = str(source_id)
+        for key in ("create_time", "created_at", "update_time", "updated_at"):
+            timestamp = normalize_timestamp(conversation.get(key))
+            if timestamp:
+                metadata[f"source_{key}"] = timestamp
+        item: dict[str, Any] = {
+            "id": stable_id("conversation", source_name, path, source_id or index, text_digest),
+            "kind": "conversation_thread",
+            "title": title,
+            "source": source_name,
+            "metadata": metadata,
+        }
+        if include_content:
+            if len(messages) > max_messages:
+                warnings.append(
+                    InputWarning(
+                        str(path),
+                        f"skipped conversation content at index {index}: over {max_messages} messages",
+                    )
+                )
+            else:
+                item["messages"] = messages
+                item["metadata"]["content_included"] = True
+        items.append(item)
+    return items, warnings
+
+
+def parse_skill_frontmatter(text: str) -> dict[str, Any]:
+    if not text.startswith("---"):
+        return {}
+    end = text.find("\n---", 3)
+    if end < 0:
+        return {}
+    frontmatter: dict[str, Any] = {}
+    for line in text[3:end].strip().splitlines():
+        if not line.strip() or line.lstrip().startswith("#") or ":" not in line:
+            continue
+        key, value = line.split(":", 1)
+        key = key.strip()
+        value = value.strip().strip('"').strip("'")
+        if key:
+            frontmatter[key] = value
+    return frontmatter
+
+
+def collect_skill_dir(path: Path, source_name: str) -> tuple[list[dict[str, Any]], list[InputWarning]]:
+    warnings: list[InputWarning] = []
+    if path.is_symlink():
+        return [], [InputWarning(str(path), "skills path is a symlink; skipped")]
+    if not path.exists():
+        return [], [InputWarning(str(path), "skills directory does not exist")]
+    if not path.is_dir():
+        return [], [InputWarning(str(path), "skills path is not a directory")]
+
+    items: list[dict[str, Any]] = []
+    for skill_path in sorted(path.rglob("SKILL.md")):
+        if skill_path.is_symlink():
+            warnings.append(InputWarning(str(skill_path), "skipped symlinked skill file"))
+            continue
+        try:
+            text = skill_path.read_text(encoding="utf-8")
+        except Exception as exc:
+            warnings.append(InputWarning(str(skill_path), f"could not read skill: {exc}"))
+            continue
+        frontmatter = parse_skill_frontmatter(text)
+        name = str(frontmatter.get("name") or skill_path.parent.name).strip() or skill_path.parent.name
+        items.append(
+            {
+                "id": stable_id("skill", source_name, skill_path, sha256_text(text)),
+                "kind": "skill",
+                "name": name,
+                "category": str(frontmatter.get("category") or "general"),
+                "source": source_name,
+                "format": "SKILL.md",
+                "content": text,
+                "metadata": {
+                    "source_path": str(skill_path),
+                    "sha256": sha256_text(text),
+                    "frontmatter": frontmatter,
+                },
+            }
+        )
+    return items, warnings
+
+
+def looks_textual(path: Path) -> bool:
+    if path.suffix.lower() in TEXT_EXTENSIONS:
+        return True
+    guessed, _ = mimetypes.guess_type(str(path))
+    return bool(guessed and (guessed.startswith("text/") or guessed in {"application/json"}))
+
+
+def iter_archive_dir(path: Path) -> Iterable[Path | InputWarning]:
+    try:
+        children = sorted(path.iterdir())
+    except Exception as exc:
+        yield InputWarning(str(path), f"could not scan archive directory: {exc}")
+        return
+    for child in children:
+        if child.is_symlink():
+            yield InputWarning(str(child), "skipped symlinked archive path")
+            continue
+        if child.is_file():
+            yield child
+        elif child.is_dir():
+            yield from iter_archive_dir(child)
+
+
+def iter_archive_files(paths: Iterable[Path]) -> Iterable[Path | InputWarning]:
+    for path in paths:
+        if path.is_symlink():
+            yield InputWarning(str(path), "skipped symlinked archive path")
+            continue
+        if path.is_file():
+            yield path
+        elif path.is_dir():
+            yield from iter_archive_dir(path)
+
+
+def collect_archive_paths(
+    paths: list[Path],
+    source_name: str,
+    *,
+    include_content: bool = False,
+    max_bytes: int = 256_000,
+) -> tuple[list[dict[str, Any]], list[InputWarning]]:
+    warnings: list[InputWarning] = []
+    items: list[dict[str, Any]] = []
+    existing_paths: list[Path] = []
+    for path in paths:
+        if path.is_symlink():
+            warnings.append(InputWarning(str(path), "archive path is a symlink; skipped"))
+            continue
+        if not path.exists():
+            warnings.append(InputWarning(str(path), "archive path does not exist"))
+            continue
+        if not path.is_file() and not path.is_dir():
+            warnings.append(InputWarning(str(path), "archive path is not a file or directory"))
+            continue
+        existing_paths.append(path)
+
+    for entry in iter_archive_files(existing_paths):
+        if isinstance(entry, InputWarning):
+            warnings.append(entry)
+            continue
+        path = entry
+        if not looks_textual(path):
+            warnings.append(InputWarning(str(path), "skipped non-text archive file"))
+            continue
+        try:
+            st = path.stat()
+        except Exception as exc:
+            warnings.append(InputWarning(str(path), f"could not stat archive file: {exc}"))
+            continue
+        size = st.st_size
+        try:
+            file_hash = sha256_path(path)
+        except Exception as exc:
+            warnings.append(InputWarning(str(path), f"could not hash archive file: {exc}"))
+            continue
+        if include_content and size > max_bytes:
+            warnings.append(InputWarning(str(path), f"skipped archive content over {max_bytes} bytes"))
+        archive_item: dict[str, Any] = {
+            "id": stable_id("archive", source_name, path, file_hash),
+            "kind": "archive_document",
+            "title": path.name,
+            "source": source_name,
+            "metadata": {
+                "source_path": str(path),
+                "size_bytes": size,
+                "sha256": file_hash,
+            },
+        }
+        if include_content and size <= max_bytes:
+            try:
+                archive_item["content"] = path.read_text(encoding="utf-8")
+            except UnicodeDecodeError:
+                archive_item["content"] = path.read_text(encoding="utf-8", errors="replace")
+                archive_item["metadata"]["decoded_with_replacement"] = True
+        items.append(archive_item)
+    return items, warnings
+
+
+def build_manifest(args) -> dict[str, Any]:
+    warnings: list[InputWarning] = []
+    items: list[dict[str, Any]] = []
+
+    for path in args.memory_json:
+        collected, got_warnings = collect_memory_json(path, args.source_name)
+        items.extend(collected)
+        warnings.extend(got_warnings)
+
+    for path in args.skills_dir:
+        collected, got_warnings = collect_skill_dir(path, args.source_name)
+        items.extend(collected)
+        warnings.extend(got_warnings)
+
+    for path in args.conversation_json:
+        collected, got_warnings = collect_conversation_json(
+            path,
+            args.source_name,
+            include_content=args.include_conversation_content,
+            max_messages=args.max_conversation_messages,
+        )
+        items.extend(collected)
+        warnings.extend(got_warnings)
+
+    if args.archive:
+        collected, got_warnings = collect_archive_paths(
+            args.archive,
+            args.source_name,
+            include_content=args.include_archive_content,
+            max_bytes=args.max_archive_bytes,
+        )
+        items.extend(collected)
+        warnings.extend(got_warnings)
+
+    counts: dict[str, int] = {}
+    for item in items:
+        counts[item["kind"]] = counts.get(item["kind"], 0) + 1
+
+    return {
+        "schema_version": SCHEMA_VERSION,
+        "generated_at": utc_now_iso(),
+        "source": {
+            "name": args.source_name,
+            "kind": args.source_kind,
+        },
+        "summary": {
+            "item_count": len(items),
+            "counts_by_kind": counts,
+            "warning_count": len(warnings),
+        },
+        "items": items,
+        "warnings": [{"path": warning.path, "message": warning.message} for warning in warnings],
+    }
+
+
+def parse_args(argv: list[str] | None = None):
+    parser = argparse.ArgumentParser(description="Build a neutral Odysseus agent migration manifest.")
+    parser.add_argument("--source-name", default="agent-export", help="Human-readable source name.")
+    parser.add_argument("--source-kind", default="generic", help="Source adapter kind, e.g. generic, openclaw, hermes.")
+    parser.add_argument(
+        "--memory-json",
+        action="append",
+        type=Path,
+        default=[],
+        help="JSON memory export. May be a list, or an object containing memories/items/data.",
+    )
+    parser.add_argument(
+        "--skills-dir",
+        action="append",
+        type=Path,
+        default=[],
+        help="Directory containing SKILL.md files. Scanned recursively.",
+    )
+    parser.add_argument(
+        "--archive",
+        action="append",
+        type=Path,
+        default=[],
+        help="Text/Markdown/JSON file or directory to preserve as archive documents.",
+    )
+    parser.add_argument(
+        "--conversation-json",
+        action="append",
+        type=Path,
+        default=[],
+        help="Conversation export JSON. Supports generic message lists and ChatGPT-style conversations.json.",
+    )
+    parser.add_argument(
+        "--include-archive-content",
+        action="store_true",
+        help="Embed archive document content in the manifest. By default only metadata is included.",
+    )
+    parser.add_argument(
+        "--max-archive-bytes",
+        type=int,
+        default=256_000,
+        help="Maximum bytes to embed per archive file when --include-archive-content is used.",
+    )
+    parser.add_argument(
+        "--include-conversation-content",
+        action="store_true",
+        help="Embed normalized conversation messages. By default only thread metadata is included.",
+    )
+    parser.add_argument(
+        "--max-conversation-messages",
+        type=int,
+        default=2000,
+        help="Maximum messages to embed per conversation when --include-conversation-content is used.",
+    )
+    parser.add_argument("--output", type=Path, help="Write manifest JSON to this path instead of stdout.")
+    parser.add_argument("--compact", action="store_true", help="Write compact JSON without indentation.")
+    return parser.parse_args(argv)
+
+
+def main(argv: list[str] | None = None) -> int:
+    args = parse_args(argv)
+    manifest = build_manifest(args)
+    text = json.dumps(manifest, ensure_ascii=False, sort_keys=True, separators=(",", ":")) if args.compact else (
+        json.dumps(manifest, ensure_ascii=False, indent=2, sort_keys=True) + "\n"
+    )
+    if args.output:
+        args.output.parent.mkdir(parents=True, exist_ok=True)
+        args.output.write_text(text, encoding="utf-8")
+    else:
+        sys.stdout.write(text)
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

services/hwfit/fit.py

@@ -19,22 +19,32 @@ GPU_BANDWIDTH = {
     "6950 xt": 576, "6900 xt": 512, "6800 xt": 512, "6800": 512, "6700 xt": 384, "6600 xt": 256, "6600": 224,
     "mi300x": 5300, "mi300": 5300, "mi250x": 3277, "mi250": 3277, "mi210": 1638, "mi100": 1229,
     "9070 xt": 624, "9070": 488, "9060 xt": 322, "9060": 322,
-    # Apple Silicon unified-memory bandwidth (GB/s). Keyed off the chip name
-    # reported by sysctl machdep.cpu.brand_string (e.g. "Apple M4 Max"). Listed
-    # before the bare "m_" keys matters less than length-sorting (done below),
-    # which guarantees "m4 max" is tried before "m4".
-    "m1 ultra": 800, "m1 max": 400, "m1 pro": 200, "m1": 68,
-    "m2 ultra": 800, "m2 max": 400, "m2 pro": 200, "m2": 100,
-    "m3 ultra": 800, "m3 max": 300, "m3 pro": 150, "m3": 100,
-    "m4 max": 546, "m4 pro": 273, "m4": 120,
-    "m5 max": 546, "m5 pro": 273, "m5": 150,
 }
 
 # Pre-sort keys by length descending for correct substring matching
 _BW_KEYS_SORTED = sorted(GPU_BANDWIDTH.keys(), key=len, reverse=True)
 
-# metal: backstop for Apple Silicon chips not in GPU_BANDWIDTH (e.g. a future
+# Apple Silicon unified-memory bandwidth (GB/s). For chip families with both
-# M5) — the named chips above take the accurate bandwidth path instead.
+# binned and full variants under the same "Apple Mx Max" brand string, prefer
+# GPU core count when hardware detection provides it; otherwise fall back to the
+# conservative tier so speed estimates do not over-promise.
+APPLE_BANDWIDTH_FIXED = {
+    "m1 ultra": 800, "m1 max": 400, "m1 pro": 200, "m1": 68,
+    "m2 ultra": 800, "m2 max": 400, "m2 pro": 200, "m2": 100,
+    "m3 ultra": 800, "m3 pro": 150, "m3": 100,
+    "m4 pro": 273, "m4": 120,
+    "m5 pro": 307, "m5": 153,
+}
+APPLE_BANDWIDTH_BY_CORES = {
+    "m3 max": {30: 300, 40: 400},
+    "m4 max": {32: 410, 40: 546},
+    "m5 max": {32: 460, 40: 614},
+}
+_APPLE_FIXED_KEYS_SORTED = sorted(APPLE_BANDWIDTH_FIXED.keys(), key=len, reverse=True)
+_APPLE_VARIANT_KEYS_SORTED = sorted(APPLE_BANDWIDTH_BY_CORES.keys(), key=len, reverse=True)
+
+# metal: backstop for Apple Silicon chips not in the explicit tables above
+# (e.g. a future M6) — use a conservative generic estimate when unknown.
 FALLBACK_K = {"cuda": 220, "rocm": 180, "metal": 150, "cpu_x86": 70, "cpu_arm": 90}
 
 USE_CASE_WEIGHTS = {
@@ -60,10 +70,51 @@ CONTEXT_TARGET = {
 }
 
 
-def _lookup_bandwidth(gpu_name):
+def _lookup_apple_bandwidth(system):
+    gpu_name = system.get("gpu_name")
     if not isinstance(gpu_name, str) or not gpu_name:
         return None
     gn = gpu_name.lower()
+
+    # Guard against false matches on non-Apple GPUs whose names contain
+    # "m3"/"m4"/"m5" (e.g. NVIDIA Quadro M4 000).
+    if "apple" not in gn:
+        return None
+
+    raw_cores = system.get("gpu_cores")
+    try:
+        gpu_cores = int(raw_cores) if raw_cores is not None else None
+    except (TypeError, ValueError):
+        gpu_cores = None
+
+    for key in _APPLE_VARIANT_KEYS_SORTED:
+        if key not in gn:
+            continue
+        if gpu_cores in APPLE_BANDWIDTH_BY_CORES[key]:
+            return APPLE_BANDWIDTH_BY_CORES[key][gpu_cores]
+        return min(APPLE_BANDWIDTH_BY_CORES[key].values())
+
+    for key in _APPLE_FIXED_KEYS_SORTED:
+        if key in gn:
+            return APPLE_BANDWIDTH_FIXED[key]
+    return None
+
+
+def _lookup_bandwidth(system):
+    if isinstance(system, dict):
+        gpu_name = system.get("gpu_name")
+    else:
+        gpu_name = system
+
+    if not isinstance(gpu_name, str) or not gpu_name:
+        return None
+
+    if isinstance(system, dict):
+        bw = _lookup_apple_bandwidth(system)
+        if bw is not None:
+            return bw
+
+    gn = gpu_name.lower()
     for key in _BW_KEYS_SORTED:
         if key in gn:
             return GPU_BANDWIDTH[key]
@@ -84,7 +135,7 @@ def _estimate_speed(model, quant, run_mode, system, offload_frac=0.0):
     """
     pb = _active_params_b(model)
     is_moe = model.get("is_moe", False)
-    bw = _lookup_bandwidth(system.get("gpu_name"))
+    bw = _lookup_bandwidth(system)
     backend = system.get("backend", "cpu_x86")
 
     if bw and run_mode in ("gpu", "cpu_offload"):

services/hwfit/hardware.py

@@ -1,3 +1,4 @@
+import json
 import os
 import platform
 import re
@@ -335,6 +336,37 @@ def _detect_apple_silicon():
     if total_gb <= 0:
         return None
 
+    def _parse_apple_gpu_cores(text):
+        if not text:
+            return None
+        try:
+            data = json.loads(text)
+        except (TypeError, ValueError, json.JSONDecodeError):
+            data = None
+        if isinstance(data, dict):
+            for gpu in data.get("SPDisplaysDataType") or []:
+                if not isinstance(gpu, dict):
+                    continue
+                model = str(gpu.get("sppci_model") or gpu.get("_name") or "")
+                if "apple" not in model.lower():
+                    continue
+                cores = gpu.get("sppci_cores")
+                try:
+                    return int(str(cores).strip())
+                except (TypeError, ValueError):
+                    continue
+        m = re.search(r"Total Number of Cores:\s*(\d+)", text)
+        if m:
+            try:
+                return int(m.group(1))
+            except ValueError:
+                return None
+        return None
+
+    gpu_cores = _parse_apple_gpu_cores(_run(["system_profiler", "SPDisplaysDataType", "-json"]))
+    if gpu_cores is None:
+        gpu_cores = _parse_apple_gpu_cores(_run(["system_profiler", "SPDisplaysDataType"]))
+
     # Usable GPU budget. macOS lets Metal use most of unified memory, but the
     # default working-set limit scales with RAM: small machines have to keep
     # more back for the OS + app. These fractions track Apple's
@@ -357,7 +389,7 @@ def _detect_apple_silicon():
         pass
 
     gpu = {"index": 0, "name": brand, "vram_gb": vram_gb}
-    return {
+    info = {
         "gpu_name": brand,
         "gpu_vram_gb": vram_gb,
         "gpu_count": 1,
@@ -369,6 +401,9 @@ def _detect_apple_silicon():
         # separate pool — downstream fit logic uses this to avoid double-budgeting.
         "unified_memory": True,
     }
+    if gpu_cores is not None:
+        info["gpu_cores"] = gpu_cores
+    return info
 
 
 def _read_file(path):
@@ -611,6 +646,93 @@ def _cache_key(host: str, ssh_port: str, platform_name: str):
     )
 
 
+def _is_containerized():
+    """Best-effort check for whether the local Odysseus process is running in a container."""
+    if _remote_host:
+        return False
+
+    if os.path.exists("/.dockerenv"):
+        return True
+
+    try:
+        with open("/proc/1/cgroup", encoding="utf-8", errors="replace") as f:
+            text = f.read().lower()
+        return any(marker in text for marker in ("docker", "containerd", "kubepods"))
+    except Exception:
+        return False
+
+
+def _hardware_visibility_warning(result):
+    """Return a non-blocking UX warning when detected hardware may only be container-visible."""
+    if not isinstance(result, dict):
+        return None
+
+    if result.get("manual_hardware"):
+        return None
+
+    if not result.get("containerized"):
+        return None
+
+    if result.get("gpu_error"):
+        return None
+
+    if not result.get("has_gpu"):
+        return {
+            "code": "container_no_gpu_visible",
+            "severity": "warning",
+            "title": "No GPU visible inside Docker",
+            "message": (
+                "Cookbook is scanning hardware from inside the Odysseus container. "
+                "If your host has a GPU, Docker may not be exposing it to the container, "
+                "so model recommendations may be CPU-only or too conservative."
+            ),
+            "actions": [
+                "manual_hardware",
+                "rescan",
+                "copy_diagnostics",
+            ],
+        }
+
+    total_ram = result.get("total_ram_gb") or 0
+    if total_ram and total_ram <= 8:
+        return {
+            "code": "container_low_ram_visible",
+            "severity": "info",
+            "title": "Container-visible RAM may be lower than host RAM",
+            "message": (
+                "Cookbook is seeing the RAM available inside the container. "
+                "If your host has more memory, validate host RAM separately or use Manual Hardware."
+            ),
+            "actions": [
+                "manual_hardware",
+                "rescan",
+                "copy_diagnostics",
+            ],
+        }
+
+    return None
+
+
+def _attach_probe_context(result, host=""):
+    """Attach probe-scope metadata and optional hardware visibility warning."""
+    if not isinstance(result, dict) or result.get("error"):
+        return result
+
+    is_remote = bool(host)
+    containerized = False if is_remote else _is_containerized()
+
+    result["probe_scope"] = "remote" if is_remote else ("container" if containerized else "native")
+    result["containerized"] = containerized
+
+    warning = _hardware_visibility_warning(result)
+    if warning:
+        result["hardware_visibility_warning"] = warning
+    else:
+        result.pop("hardware_visibility_warning", None)
+
+    return result
+
+
 def detect_system(host="", ssh_port="", platform="", fresh=False):
     """Detect system hardware: RAM, CPU, GPU. Cached per host (hardware rarely
     changes, and probing a remote host over SSH is slow). Pass fresh=True to
@@ -635,6 +757,7 @@ def detect_system(host="", ssh_port="", platform="", fresh=False):
     if _remote_platform == "windows" and _remote_host:
         result = _detect_windows()
         if result:
+            result = _attach_probe_context(result, host=host)
             _remote_host = None
             _remote_platform = None
             _cache_by_host[cache_key] = (now, result)
@@ -653,6 +776,7 @@ def detect_system(host="", ssh_port="", platform="", fresh=False):
     if not _remote_host and os.name == "nt":
         result = _detect_windows()
         if result:
+            result = _attach_probe_context(result, host=host)
             _cache_by_host[cache_key] = (now, result)
             return result
         # PowerShell probe failed entirely — fall through to the generic path
@@ -683,6 +807,7 @@ def detect_system(host="", ssh_port="", platform="", fresh=False):
             "gpu_name": gpu_info["gpu_name"],
             "gpu_vram_gb": gpu_info["gpu_vram_gb"],
             "gpu_count": gpu_info["gpu_count"],
+            "gpu_cores": gpu_info.get("gpu_cores"),
             "gpus": gpu_info.get("gpus", []),
             "gpu_groups": gpu_info.get("gpu_groups", []),
             "homogeneous": gpu_info.get("homogeneous", True),
@@ -714,6 +839,7 @@ def detect_system(host="", ssh_port="", platform="", fresh=False):
             "gpu_error": _last_gpu_error,
         }
 
+    result = _attach_probe_context(result, host=host)
     _remote_host = None
     _remote_platform = None
     _cache_by_host[cache_key] = (now, result)

services/hwfit/profiles.py

@@ -188,12 +188,18 @@ def compute_serve_profiles(system, model, serve_weights_gb=None, serve_quant=Non
         # Shrink context if even the chosen KV won't fit alongside weights.
         # Start from the smaller of the profile's target and the model's limit.
         cur_ctx = min(ctx, model_ctx_max)
-        while cur_ctx >= 8192:
+        # Floor the context-shrink loop at 8192, but never above the model's own
+        # trained limit. A model with a sub-8192 context (e.g. a 2048-token
+        # SmolLM) starts below 8192, so a hard-coded 8192 guard skipped the loop
+        # entirely and produced NO profile — the serve UI then fell back to
+        # manual flags even though the model fits the GPU trivially.
+        ctx_floor = min(8192, model_ctx_max)
+        while cur_ctx >= ctx_floor:
             kv = _kv_gb(model, cur_ctx, kv_type)
             n_cpu_moe, fits = _cpu_moe_for_budget(model, quant, kv, budget, fixed_gb=serve_weights_gb)
             est = _weights_gb(model, quant, serve_weights_gb) + kv + 0.6
             # If a non-MoE model can't fit even fully offloaded, try less context.
-            if model.get("is_moe") or fits or cur_ctx <= 8192:
+            if model.get("is_moe") or fits or cur_ctx <= ctx_floor:
                 profiles.append({
                     "key": key,
                     "label": label,

services/memory/skill_extractor.py

@@ -66,42 +66,58 @@ def _has_duplicate_title(skills, title: str) -> bool:
 def _extract_json_object(text: str) -> Optional[dict]:
     """Best-effort extraction of a JSON object from an LLM response.
 
-    The response may be wrapped in code fences or surrounded by prose, and some
+    The response may be wrapped in code fences or surrounded by prose. Uses
-    models emit a stray brace in the prose before the real object
+    json.JSONDecoder().raw_decode() to locate the boundaries of complete JSON
-    (e.g. "uses {placeholder} then {...}"). Slicing first-'{' .. last-'}' then
+    objects starting at each '{' position. Nested objects are filtered out to
-    grabs an unparseable span and the skill is silently lost. Try the whole
+    keep only top-level candidates. If multiple non-overlapping valid JSON
-    string first, then each '{' start position in turn, returning the first
+    objects are found, it is treated as ambiguous and returns None. Otherwise,
-    candidate that parses to a JSON object (dict). Returns None if none do.
+    returns the single valid candidate dictionary.
     """
     if not text:
         return None
     s = text.strip()
     if s.startswith("```"):
         s = s.split("\n", 1)[-1].rsplit("```", 1)[0].strip()
-    end = s.rfind("}")
-    if end == -1:
-        return None
 
-    def _as_dict(candidate):
+    decoder = json.JSONDecoder()
-        try:
+    candidates = []
-            obj = json.loads(candidate)
-        except (json.JSONDecodeError, ValueError):
-            return None
-        return obj if isinstance(obj, dict) else None
 
-    # The clean, common case: the whole (de-fenced) string is the object.
-    obj = _as_dict(s)
-    if obj is not None:
-        return obj
-    # Otherwise scan each '{' candidate up to the last '}'.
     start = s.find("{")
-    while 0 <= start < end:
+    while start != -1:
-        obj = _as_dict(s[start : end + 1])
+        try:
-        if obj is not None:
+            obj, idx = decoder.raw_decode(s[start:])
-            return obj
+            end_pos = start + idx
+            if isinstance(obj, dict):
+                candidates.append((start, end_pos, obj))
+        except (json.JSONDecodeError, ValueError):
+            pass
         start = s.find("{", start + 1)
+
+    # Filter out nested candidates to identify top-level dictionaries
+    top_level = []
+    for c in candidates:
+        is_nested = False
+        for other in candidates:
+            if other == c:
+                continue
+            if other[0] <= c[0] and c[1] <= other[1]:
+                is_nested = True
+                break
+        if not is_nested:
+            top_level.append(c)
+
+    if not top_level:
         return None
 
+    if len(top_level) > 1:
+        logger.debug(
+            "[skill-extract] Found multiple non-overlapping JSON objects: %s",
+            [item[2].get("title") for item in top_level]
+        )
+        return None
+
+    return top_level[0][2]
+
 
 async def maybe_extract_skill(
     session,

services/memory/skills.py

@@ -603,7 +603,6 @@ class SkillsManager:
         escalation) — those are work-in-progress and pollute the
         prompt with half-finished procedures.
         """
-        active_toolsets = active_toolsets or []
         out = []
         for s in self.load(owner=owner):
             status = s.get("status")
@@ -617,13 +616,16 @@ class SkillsManager:
             # Platform gating
             if platform and s.get("platforms") and platform not in s["platforms"]:
                 continue
-            # requires_toolsets: hide unless every required toolset is active
+            # requires_toolsets: hide unless every required toolset is active.
+            # active_toolsets=None means the caller doesn't know the active
+            # set (API listings, chat preface) — don't gate in that case;
+            # only an explicit list filters.
             req = s.get("requires_toolsets") or []
-            if req and not all(t in active_toolsets for t in req):
+            if req and active_toolsets is not None and not all(t in active_toolsets for t in req):
                 continue
             # fallback_for_toolsets: hide when any of those toolsets is active
             fb = s.get("fallback_for_toolsets") or []
-            if fb and any(t in active_toolsets for t in fb):
+            if fb and active_toolsets and any(t in active_toolsets for t in fb):
                 continue
             out.append({
                 "name": s["name"],

services/youtube/youtube_handler.py

@@ -64,20 +64,40 @@ def is_youtube_url(url: str) -> bool:
     return "youtube.com" in url or "youtu.be" in url
 
 
+# youtube.com-shaped hosts. music.youtube.com serves the same /watch and
+# /shorts paths, so links shared from YouTube Music must resolve too.
+_YT_HOSTS = ("www.youtube.com", "youtube.com", "m.youtube.com", "music.youtube.com")
+# Path prefixes whose first following segment is the video id. Covers the
+# /embed/ player, Shorts (/shorts/), live streams (/live/), and the legacy
+# /v/ embed — all of which `is_youtube_url` already treats as YouTube, so
+# they must be extractable or the link is silently dropped (neither web-fetched
+# nor transcript-fetched) by the chat pipeline.
+_YT_PATH_PREFIXES = ("/embed/", "/shorts/", "/live/", "/v/")
+
+
 def extract_youtube_id(url: str) -> Optional[str]:
-    """Extract YouTube video ID from various URL formats."""
+    """Extract a YouTube video ID from the common URL shapes:
+    watch?v=, youtu.be/<id>, /embed/<id>, /shorts/<id>, /live/<id>, /v/<id>,
+    across youtube.com / m.youtube.com / music.youtube.com / youtu.be."""
     if not isinstance(url, str):
         return None
     parsed = urllib.parse.urlparse(url)
-    if parsed.hostname in ("www.youtube.com", "youtube.com", "m.youtube.com"):
+    host = (parsed.hostname or "").lower()
+    if host in _YT_HOSTS:
         if parsed.path == "/watch":
             params = urllib.parse.parse_qs(parsed.query)
-            if "v" in params:
+            if params.get("v"):
                 return params["v"][0]
-        elif parsed.path.startswith("/embed/"):
+        else:
-            return parsed.path.split("/")[-1]
+            for prefix in _YT_PATH_PREFIXES:
-    elif parsed.hostname == "youtu.be":
+                if parsed.path.startswith(prefix):
-        return parsed.path[1:]
+                    vid = parsed.path[len(prefix):].split("/")[0]
+                    if vid:
+                        return vid
+    elif host == "youtu.be":
+        vid = parsed.path.lstrip("/").split("/")[0]
+        if vid:
+            return vid
     return None
 
 
@@ -170,6 +190,8 @@ def format_transcript_for_context(
     if segments:
         ctx += "Timestamped Transcript:\n"
         for seg in segments:
+            if not isinstance(seg, dict):
+                continue
             ctx += f"[{seg['timestamp']}] {seg['text']}\n"
         # Check length — fall back to plain text if too long
         if len(ctx) > 12000:
@@ -202,15 +224,24 @@ async def fetch_youtube_comments(
             f"https://www.youtube.com/watch?v={video_id}",
         ]
 
-        proc = await asyncio.wait_for(
+        proc = await asyncio.create_subprocess_exec(
-            asyncio.create_subprocess_exec(
             *cmd,
             stdout=asyncio.subprocess.PIPE,
             stderr=asyncio.subprocess.PIPE,
-            ),
-            timeout=timeout,
         )
-        stdout, stderr = await proc.communicate()
+        # Bound the wait on the process actually finishing, not on spawning it.
+        # create_subprocess_exec returns as soon as the child starts, so wrapping
+        # it in wait_for never enforces the timeout — proc.communicate() is the
+        # blocking step. Kill and reap the child if it overruns so it does not
+        # linger after we return.
+        try:
+            stdout, stderr = await asyncio.wait_for(
+                proc.communicate(), timeout=timeout
+            )
+        except asyncio.TimeoutError:
+            proc.kill()
+            await proc.wait()
+            raise
 
         if proc.returncode != 0:
             return {"success": False, "error": f"yt-dlp failed: {stderr.decode()[:200]}", "comments": []}

src/action_intents.py

@@ -91,6 +91,9 @@ _ROUTING_PATTERNS: tuple[tuple[str, str, Pattern[str]], ...] = tuple(
         ("ui", "tool or feature toggle request", r"\b(?:disable|enable|turn\s+(?:on|off))\s+(?:the\s+)?(?:shell|search|web|browser|documents?|memory|skills|images?|calendar|email|mail|research|incognito)\b"),
 
         # Deep research jobs, not quick conceptual mentions of research.
+        ("web", "explicit web search request", rf"{_PLEASE}(?:do|run|use|perform|make)\s+(?:a\s+)?(?:web\s+search|search\s+the\s+web)\b.+"),
+        ("web", "web lookup imperative request", rf"{_PLEASE}(?:web\s+search|search\s+the\s+web|search\s+online|look\s+up|google)\b.+"),
+        ("web", "assistant web lookup request", rf"{_ACTION_QUESTION}(?:web\s+search|search\s+the\s+web|search\s+online|look\s+up|google)\b.+"),
         ("research", "deep research imperative request", rf"{_PLEASE}(?:research|deep\s+dive|look\s+into|investigate)\s+.+"),
         ("research", "assistant deep research request", rf"{_ACTION_QUESTION}(?:research|do\s+research|deep\s+dive|look\s+into|investigate)\s+.+"),
 

src/agent_loop.py

@@ -262,6 +262,11 @@ _DOMAIN_RULES = {
 - Use `manage_settings` for preferences and tool enable/disable.
 - Use named tools over `app_api` when a named wrapper exists.
 - `app_api` is only for safe UI/API actions without a named tool; do not use it for shell, package installs, engine rebuilds, or sensitive auth/admin paths.""",
+    "contacts": """\
+## Contacts rules
+- Use `resolve_contact` to look up a contact's email or phone number by name. Searches the CardDAV address book and sent email history.
+- Use `manage_contact` to list, add, update, or delete contacts in the address book.
+- Do NOT use `manage_memory` for contact lookups — contact details live in the address book, not memory.""",
 }
 
 _DOMAIN_TOOL_MAP = {
@@ -274,6 +279,7 @@ _DOMAIN_TOOL_MAP = {
     "sessions": {"create_session", "list_sessions", "manage_session", "send_to_session", "search_chats"},
     "files": {"bash", "python", "read_file", "write_file", "edit_file", "grep", "glob", "ls", "get_workspace"},
     "settings": {"manage_settings", "manage_endpoints", "manage_mcp", "manage_webhooks", "manage_tokens", "app_api"},
+    "contacts": {"resolve_contact", "manage_contact"},
 }
 
 def _domain_rules_for_tools(tool_names: set) -> list[str]:
@@ -600,7 +606,7 @@ _API_HOSTS = frozenset([
     "api.deepseek.com", "deepseek.com",
     "api.together.xyz", "api.fireworks.ai",
     "api.perplexity.ai", "api.x.ai",
-    "ollama.com", "api.venice.ai",
+    "ollama.com", "api.venice.ai", "api.kimi.com",
     "api.githubcopilot.com",
     # Local OpenAI-compatible endpoints (llama.cpp, vLLM, LM Studio, etc.).
     # Without these, `_is_api_model` falls back to keyword sniffing on the
@@ -787,6 +793,12 @@ def _classify_agent_request(messages: List[Dict], last_user: str) -> Dict[str, o
         domains.add("documents")
     if has(r"\b(search|web|google|look up|latest|news|current|weather|forecast|stock price|price of|website|url|https?://|www\.)\b"):
         domains.add("web")
+    if has(
+        r"\b(wyszukaj|wyszukać|wyszukac)\b.*\b(internet|internecie|online|web)\b",
+        r"\b(sprawd[zź]|znajd[zź])\b.*\b(internet|internecie|online|web)\b",
+        r"\b(aktualn\w*|bieżąc\w*|biezac\w*|dzisiaj|teraz)\b.*\b(pogod\w*|temperatur\w*)\b",
+    ):
+        domains.add("web")
     if has(r"\b(research|deep dive|investigate|look into)\b"):
         domains.add("web")
     if has(r"\b(open|show|toggle|turn on|turn off|disable|enable|switch model|change model|settings|theme|panel)\b"):
@@ -797,6 +809,8 @@ def _classify_agent_request(messages: List[Dict], last_user: str) -> Dict[str, o
         domains.add("files")
     if has(r"\b(endpoint|api token|mcp|webhook|preference|configure|config|setting)\b"):
         domains.add("settings")
+    if has(r"\b(contact|contacts|phone|phone number|address book|vcard)\b"):
+        domains.add("contacts")
 
     low_signal = not continuation and not domains
     return {
@@ -1801,18 +1815,21 @@ async def stream_agent_loop(
         logger.info(f"[tool-rag] Using caller-provided relevant_tools ({len(_relevant_tools)} tools)")
     if not guide_only and not _relevant_tools and bool(_intent.get("low_signal")):
         from src.tool_index import ALWAYS_AVAILABLE
-        _relevant_tools = set(ALWAYS_AVAILABLE)
         if workspace:
             # An active workspace IS the file-work signal: a vague "look at the
             # project" means explore this folder. Surface only the READ-ONLY file
             # tools (intersection with the plan-mode read-only allowlist) so the
             # agent can investigate; write/shell tools stay out until the request
             # actually calls for them (RAG retrieval adds those on a real ask).
+            _relevant_tools = set(ALWAYS_AVAILABLE)
             from src.tool_security import PLAN_MODE_READONLY_TOOLS
             _relevant_tools |= (_DOMAIN_TOOL_MAP["files"] & PLAN_MODE_READONLY_TOOLS)
             logger.info("[tool-rag] Low-signal but workspace active; including read-only file tools")
         else:
-            logger.info("[tool-rag] Low-signal agent message; skipping retrieval and using always-available tools only")
+            # Don't short-circuit: fall through to RAG retrieval below.
+            # Non-English queries are flagged low_signal by the English-only
+            # intent classifier, but fastembed retrieval works across languages.
+            logger.info("[tool-rag] Low-signal query; will run RAG retrieval")
     if not guide_only and not _relevant_tools:
         try:
             from src.tool_index import get_tool_index, ALWAYS_AVAILABLE
@@ -1887,6 +1904,44 @@ async def stream_agent_loop(
     if _relevant_tools is not None and active_document is not None:
         _relevant_tools.update({"edit_document", "update_document", "suggest_document"})
 
+    # The skill index injected by _build_system_prompt tells the model to
+    # call `manage_skills action=view`, and Jaccard-matched skills are pasted
+    # into the prompt as procedures to follow — but neither path goes through
+    # tool selection, so the model can be handed a procedure naming tools
+    # (grep, read_file, ...) that aren't in its schema list. Keep the schemas
+    # in lockstep: manage_skills is callable whenever any skill is indexed,
+    # and a matched skill's declared requires_toolsets ride along with it.
+    if not guide_only and _relevant_tools is not None:
+        try:
+            from services.memory.skills import SkillsManager
+            from src.constants import DATA_DIR
+            _skills_on = True
+            try:
+                from routes.prefs_routes import _load_for_user as _load_prefs
+                _skills_on = (_load_prefs(owner) or {}).get("skills_enabled", True)
+            except Exception:
+                pass
+            _sm = SkillsManager(DATA_DIR)
+            _owner_skills = _sm.load(owner=owner) if _skills_on else []
+            if _owner_skills:
+                _relevant_tools.add("manage_skills")
+                if _retrieval_query:
+                    # Validate against every known executable tool, not just
+                    # TOOL_SECTIONS — code-nav tools (grep/glob/ls) ship as
+                    # schemas without a prompt-prose section.
+                    from src.tool_policy import known_tool_names
+                    _known = known_tool_names()
+                    for _sk in _sm.get_relevant_skills(
+                        _retrieval_query, skills=_owner_skills,
+                        threshold=0.25, max_items=3,
+                    ):
+                        _relevant_tools.update(
+                            t for t in (_sk.get("requires_toolsets") or [])
+                            if t in _known
+                        )
+        except Exception as _e:
+            logger.debug(f"[tool-rag] skill-aware tool include skipped: {_e}")
+
     if _relevant_tools is not None:
         logger.info("[agent-intent] selected_tools=%s", sorted(_relevant_tools)[:50])
 
@@ -1937,6 +1992,10 @@ async def stream_agent_loop(
     # and can override this list for users who know their setup.
     _model_no_tools = any(kw in _model_lc for kw in (
         "deepseek-r1",
+        # Open-weight GPT-OSS models are commonly served through llama.cpp /
+        # llama-cpp-python. Their names contain "gpt-o", but they do not use
+        # OpenAI's native tool-call channel unless the endpoint opts in.
+        "gpt-oss",
     ))
     # Native Ollama endpoints (/api/chat) handle tool schemas differently from
     # the OpenAI-compat path. Models like gemma4, qwen3.5, ministral respond to
@@ -1998,30 +2057,34 @@ async def stream_agent_loop(
     _t3 = time.time()
     try:
         from src.context_compactor import trim_for_context
-        from src.context_budget import compute_input_token_budget, DEFAULT_HARD_MAX
+        from src.context_budget import compute_input_token_budget, DEFAULT_HARD_MAX, DEFAULT_BUDGET, budget_is_explicit as _budget_is_explicit
-        from src.settings import is_setting_overridden
+        from src.model_context import budget_context_for_model
 
-        soft_budget = int(get_setting("agent_input_token_budget", 6000) or 0)
+        soft_budget = int(get_setting("agent_input_token_budget", DEFAULT_BUDGET) or 0)
         if soft_budget > 0:
             before_trim_tokens = estimate_tokens(messages)
             reserve_tokens = min(max(max_tokens or 1024, 512), 2048)
-            # Honour the configurable ceiling for the auto-derived budget path.
+            # Ceiling for the auto-derived budget (no effect on an explicit budget;
-            # No-op when the user has an explicit `agent_input_token_budget`
+            # see #1230). Falls back to DEFAULT_HARD_MAX on missing/malformed values
-            # (that branch ignores hard_max). Falls back to DEFAULT_HARD_MAX
+            # so misconfig can't zero the budget.
-            # on missing/malformed values so misconfig can't zero the budget.
             try:
                 hard_max = int(get_setting("agent_input_token_hard_max", DEFAULT_HARD_MAX) or DEFAULT_HARD_MAX)
             except (TypeError, ValueError):
                 hard_max = DEFAULT_HARD_MAX
             if hard_max <= 0:
                 hard_max = DEFAULT_HARD_MAX
-            # Scale the default budget to the model's context window so long-context
+            # Default value = auto sentinel (scale to the window); any other value =
-            # models aren't silently capped at 6000; an explicit user setting is
+            # explicit cap. Value-based, not presence-based, because the save path
-            # still honoured (clamped to the window). (#1170)
+            # materializes defaults so a persisted default must still read as auto (#4121).
+            budget_is_explicit = _budget_is_explicit(soft_budget)
+            # Scale only off a window we actually discovered, bound to the value it
+            # proves (else 0) — not the passed-in context_length, which can be stale
+            # or unset for some callers (#4122 review).
+            ctx_for_budget = budget_context_for_model(endpoint_url, model, fallback=context_length)
             effective_budget = compute_input_token_budget(
                 soft_budget,
-                context_length,
+                ctx_for_budget,
-                is_setting_overridden("agent_input_token_budget"),
+                budget_is_explicit,
                 hard_max=hard_max,
             )
             trimmed_messages = trim_for_context(
@@ -2096,11 +2159,12 @@ async def stream_agent_loop(
     # tool, so we don't nudge on harmless transitional text like "let me
     # know what you think".
     _INTENT_RE = re.compile(
-        r"(?:^|\n)\s*(?:let me|i'?ll|i will|going to|let's)\s+"
+        r"(?:^|\n)\s*(?:let me|i'?ll|i will|i need to|we need to|need to|"
+        r"i should|we should|i must|we must|going to|let's)\s+"
         r"(?:tail|check|investigate|look at|see|tail|read|fetch|inspect|"
         r"verify|diagnose|examine|debug|capture|grab|pull|view|run|call|"
         r"trigger|launch|start|kick off|stop|kill|restart|adopt|serve|"
-        r"register|adopt|list|search|find|query|hit|ping|test)"
+        r"register|adopt|list|search|find|query|hit|ping|test|use|perform|do)"
         r"\b[^.\n]{0,140}",
         re.IGNORECASE,
     )
@@ -2141,9 +2205,17 @@ async def stream_agent_loop(
         elif _is_api_model:
             # Filter schemas by RAG-selected tools (if available)
             if _relevant_tools:
+                # _build_base_prompt unions _ADMIN_TOOLS into the prompt
+                # sections when admin intent fires — the schema list must
+                # offer the same names, or the model reads prose describing
+                # tools it cannot call and substitutes the nearest schema
+                # it does have (e.g. manage_memory for manage_skills).
+                _schema_names = set(_relevant_tools)
+                if _needs_admin:
+                    _schema_names |= _ADMIN_TOOLS
                 base_schemas = [
                     s for s in FUNCTION_TOOL_SCHEMAS
-                    if s.get("function", {}).get("name") in _relevant_tools
+                    if s.get("function", {}).get("name") in _schema_names
                 ]
                 _mcp_filtered = [
                     s for s in mcp_schemas
@@ -2679,6 +2751,46 @@ async def stream_agent_loop(
                     )
                 desc, result = await _tool_task
 
+            # A skill the model just loaded can prescribe tools that weren't
+            # RAG-selected this turn (declared via requires_toolsets in its
+            # frontmatter). Union them into the selection so the NEXT round's
+            # schema list includes them — otherwise the model reads "use
+            # grep" from the skill it fetched but has no grep schema to call.
+            if (
+                block.tool_type == "manage_skills"
+                and _relevant_tools is not None
+                and not result.get("error")
+            ):
+                _ms_args = {}
+                _ms_raw = (block.content or "").strip()
+                if _ms_raw.startswith("{"):
+                    try:
+                        _ms_args = json.loads(_ms_raw)
+                    except json.JSONDecodeError:
+                        _ms_args = {}
+                _ms_name = str(_ms_args.get("name", "") or "").strip()
+                if _ms_name and _ms_args.get("action") in ("view", "view_ref"):
+                    try:
+                        from services.memory.skills import SkillsManager as _SkM
+                        from src.constants import DATA_DIR as _DD
+                        from src.tool_policy import known_tool_names as _ktn
+                        _known = _ktn()
+                        for _sk in _SkM(_DD).load(owner=owner):
+                            if _sk.get("name") == _ms_name:
+                                _new = {
+                                    t for t in (_sk.get("requires_toolsets") or [])
+                                    if t in _known and t not in _relevant_tools
+                                }
+                                if _new:
+                                    _relevant_tools.update(_new)
+                                    logger.info(
+                                        "[tool-rag] skill '%s' unlocked tools for next round: %s",
+                                        _ms_name, sorted(_new),
+                                    )
+                                break
+                    except Exception as _e:
+                        logger.debug(f"skill requires_toolsets unlock skipped: {_e}")
+
             # Extract structured web sources from web_search tool output.
             # web_search returns {"output": ..., "exit_code": 0}; check "output"
             # first so the <!-- SOURCES:…--> marker is found and stripped even

src/ai_interaction.py

@@ -972,16 +972,15 @@ async def do_manage_memory(content: str, session_id: Optional[str] = None, owner
             memories = [m for m in memories if m.get("category", "").lower() == category_filter]
         if not memories:
             return {"results": "No memories found" + (f" in category '{category_filter}'" if category_filter else "") + "."}
+
         result_lines = [f"Found {len(memories)} memory entries:\n"]
-        for m in memories[:100]:
+        for m in memories:
             cat = m.get("category", "fact")
             mid = m.get("id", "?")[:8]
             text = m.get("text", "")
             if len(text) > 150:
                 text = text[:150] + "..."
             result_lines.append(f"- [{cat}] `{mid}` — {text}")
-        if len(memories) > 100:
-            result_lines.append(f"... and {len(memories) - 100} more")
         return {"results": "\n".join(result_lines)}
 
     elif action == "add":

src/api_key_manager.py

@@ -4,6 +4,8 @@ import logging
 from typing import Dict
 from cryptography.fernet import Fernet, InvalidToken
 
+from core.platform_compat import safe_chmod
+
 logger = logging.getLogger(__name__)
 
 class APIKeyManager:
@@ -15,12 +17,20 @@ class APIKeyManager:
     def get_or_create_key(self) -> bytes:
         """Get or create encryption key for API keys"""
         if os.path.exists(self.key_file):
+            # Older versions wrote .key with the process umask (often 0o644,
+            # i.e. group/world-readable). Re-restrict on read so existing
+            # installs heal without needing the key to be regenerated.
+            safe_chmod(self.key_file, 0o600)
             with open(self.key_file, 'rb') as f:
                 return f.read()
         else:
             key = Fernet.generate_key()
             with open(self.key_file, 'wb') as f:
                 f.write(key)
+            # This key decrypts every stored provider credential, so restrict it
+            # to the owner (0o600) — it must not be group/world-readable. No-op
+            # on Windows (files there are ACL-restricted to the user already).
+            safe_chmod(self.key_file, 0o600)
             return key
     
     def encrypt_api_key(self, api_key: str) -> str:

src/bg_monitor.py

@@ -55,6 +55,8 @@ async def _drain_agent(sess, messages):
         if "delta" in d:
             delta = d.get("delta")
             if isinstance(delta, str):
+                if d.get("thinking"):
+                    continue
                 full += delta
         elif d.get("type") == "agent_step":
             round_num = d.get("round", round_num)

src/builtin_mcp.py

@@ -5,12 +5,13 @@ Auto-registration of built-in MCP servers on startup.
 Each server runs as a stdio subprocess managed by McpManager.
 """
 
+import asyncio
+import json
 import logging
 import os
 import shutil
 import subprocess
 import sys
-import asyncio
 
 from core.platform_compat import IS_WINDOWS, which_tool
 
@@ -197,12 +198,13 @@ def _npx_package_from_args(args):
 async def _is_npx_package_cached(npx_path, package_spec, timeout_s=5):
     """Probe whether an npx package is already in the local cache.
 
-    Runs `npx --no-install <pkg> --version`. --no-install tells npx to
+    First checks the local `_npx` cache for an installed package. If the
-    fail instead of downloading, so a cache miss returns fast. We treat
+    package is not found there, falls back to `npx --no-install <pkg>
-    "exited 0 with non-empty stdout" as proof of a working cached copy.
+    --version` so older npm layouts still work without downloading.
-    Anything else (non-zero exit, empty stdout, timeout, missing npx,
-    network error) means we should skip the server.
     """
+    if _is_package_in_npx_cache(package_spec):
+        return True
+
     try:
         proc = await asyncio.create_subprocess_exec(
             npx_path, "--no-install", package_spec, "--version",
@@ -231,3 +233,68 @@ async def _is_npx_package_cached(npx_path, package_spec, timeout_s=5):
             pass
         return False
     return proc.returncode == 0 and bool(stdout.strip())
+
+
+def _is_package_in_npx_cache(package_spec):
+    """Return True when npm's `_npx` cache already contains package_spec."""
+    package_name = _npx_package_name(package_spec)
+    if not package_name:
+        return False
+
+    for cache_root in _npm_cache_roots():
+        npx_root = os.path.join(cache_root, "_npx")
+        if _npx_cache_contains_package(npx_root, package_name):
+            return True
+    return False
+
+
+def _npx_package_name(package_spec):
+    """Strip a version/range suffix from an npm package spec."""
+    if not package_spec:
+        return ""
+    if package_spec.startswith("@"):
+        parts = package_spec.split("@", 2)
+        if len(parts) >= 3:
+            return f"@{parts[1]}"
+        return package_spec
+    return package_spec.split("@", 1)[0]
+
+
+def _npm_cache_roots():
+    roots = []
+    configured = os.environ.get("npm_config_cache")
+    if configured:
+        roots.append(os.path.expanduser(configured))
+    roots.append(os.path.join(os.path.expanduser("~"), ".npm"))
+    local_app_data = os.environ.get("LOCALAPPDATA")
+    if local_app_data:
+        roots.append(os.path.join(local_app_data, "npm-cache"))
+    return list(dict.fromkeys(roots))
+
+
+def _npx_cache_contains_package(npx_root, package_name):
+    if not os.path.isdir(npx_root):
+        return False
+    package_path = os.path.join("node_modules", *package_name.split("/"), "package.json")
+    try:
+        entries = list(os.scandir(npx_root))
+    except OSError:
+        return False
+    for entry in entries:
+        try:
+            is_dir = entry.is_dir()
+        except OSError:
+            continue
+        cached_name = _cached_package_name(os.path.join(entry.path, package_path))
+        if is_dir and cached_name == package_name:
+            return True
+    return False
+
+
+def _cached_package_name(package_json_path):
+    try:
+        with open(package_json_path, encoding="utf-8") as fh:
+            data = json.load(fh)
+    except (OSError, ValueError):
+        return ""
+    return str(data.get("name", "")).strip()

src/caldav_sync.py

@@ -128,6 +128,17 @@ def validate_caldav_url(raw_url: str) -> str:
     return urlunparse(parsed._replace(fragment="")).rstrip("/")
 
 
+def _event_etag(obj) -> str:
+    """Best-effort ETag extraction from python-caldav resources."""
+    try:
+        etag = getattr(obj, "etag", None)
+        if callable(etag):
+            etag = etag()
+        return str(etag or "")
+    except Exception:
+        return ""
+
+
 def _stable_cal_id(remote_url: str, owner: str = "", account_id: str = "") -> str:
     """Deterministic local id for a remote CalDAV calendar, scoped to owner
     and account so two users — or one user with two accounts — pointing at
@@ -316,11 +327,12 @@ def _sync_blocking(owner: str, url: str, username: str, password: str, account_i
                         color="#5b8abf",
                         source="caldav",
                         account_id=account_id or None,
+                        caldav_base_url=remote_url,
                     )
                     db.add(local_cal)
                     db.commit()
                 else:
-                    # Refresh display name and stamp account_id if missing.
+                    # Refresh display name and stamp CalDAV metadata if missing.
                     changed = False
                     if local_cal.name != display_name:
                         local_cal.name = display_name
@@ -328,6 +340,9 @@ def _sync_blocking(owner: str, url: str, username: str, password: str, account_i
                     if account_id and not local_cal.account_id:
                         local_cal.account_id = account_id
                         changed = True
+                    if local_cal.caldav_base_url != remote_url:
+                        local_cal.caldav_base_url = remote_url
+                        changed = True
                     if changed:
                         db.commit()
                 result["calendars"] += 1
@@ -395,6 +410,9 @@ def _sync_blocking(owner: str, url: str, username: str, password: str, account_i
 
                         existing = _find_existing_event(db, pending, uid_val, local_cal.id)
                         if existing:
+                            if existing.caldav_sync_pending in {"create", "update"}:
+                                result["events"] += 1
+                                continue
                             existing.calendar_id = local_cal.id
                             existing.summary = summary
                             existing.description = description
@@ -405,6 +423,9 @@ def _sync_blocking(owner: str, url: str, username: str, password: str, account_i
                             existing.is_utc = row_is_utc
                             existing.rrule = rrule
                             existing.origin = "caldav"
+                            existing.remote_href = str(getattr(obj, "url", "") or "") or None
+                            existing.remote_etag = _event_etag(obj) or None
+                            existing.caldav_sync_pending = None
                         else:
                             new_ev = CalendarEvent(
                                 uid=uid_val,
@@ -418,6 +439,8 @@ def _sync_blocking(owner: str, url: str, username: str, password: str, account_i
                                 is_utc=row_is_utc,
                                 rrule=rrule,
                                 origin="caldav",
+                                remote_href=str(getattr(obj, "url", "") or "") or None,
+                                remote_etag=_event_etag(obj) or None,
                             )
                             db.add(new_ev)
                             pending[uid_val] = new_ev
@@ -442,6 +465,8 @@ def _sync_blocking(owner: str, url: str, username: str, password: str, account_i
                         CalendarEvent.origin == "caldav",
                         CalendarEvent.dtstart >= start,
                         CalendarEvent.dtstart <= end,
+                        CalendarEvent.remote_href.isnot(None),
+                        CalendarEvent.caldav_sync_pending.is_(None),
                         ~CalendarEvent.uid.in_(seen_uids) if seen_uids else CalendarEvent.uid.isnot(None),
                     ).all()
                     for ev in stale:
@@ -458,6 +483,92 @@ def _sync_blocking(owner: str, url: str, username: str, password: str, account_i
     return result
 
 
+def _event_payload(ev) -> dict:
+    return {
+        "uid": ev.uid,
+        "summary": ev.summary,
+        "description": ev.description,
+        "location": ev.location,
+        "dtstart": ev.dtstart,
+        "dtend": ev.dtend,
+        "all_day": ev.all_day,
+        "is_utc": ev.is_utc,
+        "rrule": ev.rrule or "",
+    }
+
+
+def _load_event_for_writeback(owner: str, uid: str) -> tuple[str, str, dict] | None:
+    from core.database import CalendarCal, CalendarEvent, SessionLocal
+
+    db = SessionLocal()
+    try:
+        ev = (
+            db.query(CalendarEvent)
+            .join(CalendarCal)
+            .filter(CalendarEvent.uid == uid, CalendarCal.owner == owner)
+            .first()
+        )
+        if not ev or not ev.calendar or ev.calendar.source != "caldav":
+            return None
+        return ev.calendar.source, ev.calendar.id, _event_payload(ev)
+    finally:
+        db.close()
+
+
+def _load_delete_for_writeback(owner: str, uid: str) -> tuple[str, str, dict] | None:
+    from core.database import CalendarCal, CalendarDeletedEvent, CalendarEvent, SessionLocal
+
+    db = SessionLocal()
+    try:
+        tombstone = db.query(CalendarDeletedEvent).filter(
+            CalendarDeletedEvent.uid == uid,
+            CalendarDeletedEvent.owner == owner,
+        ).first()
+        if tombstone:
+            return "caldav", tombstone.calendar_id, {"uid": uid}
+
+        ev = (
+            db.query(CalendarEvent)
+            .join(CalendarCal)
+            .filter(CalendarEvent.uid == uid, CalendarCal.owner == owner)
+            .first()
+        )
+        if not ev or not ev.calendar or ev.calendar.source != "caldav":
+            return None
+        return ev.calendar.source, ev.calendar.id, {"uid": uid}
+    finally:
+        db.close()
+
+
+def _pending_writeback_uids(owner: str) -> tuple[list[str], list[str]]:
+    from core.database import CalendarCal, CalendarDeletedEvent, CalendarEvent, SessionLocal
+
+    db = SessionLocal()
+    try:
+        rows = (
+            db.query(CalendarEvent.uid)
+            .join(CalendarCal)
+            .filter(
+                CalendarCal.owner == owner,
+                CalendarCal.source == "caldav",
+                CalendarEvent.status != "cancelled",
+                (
+                    (CalendarEvent.caldav_sync_pending.isnot(None))
+                    | (CalendarEvent.remote_href.is_(None))
+                ),
+            )
+            .all()
+        )
+        delete_rows = (
+            db.query(CalendarDeletedEvent.uid)
+            .filter(CalendarDeletedEvent.owner == owner)
+            .all()
+        )
+        return [row[0] for row in rows], [row[0] for row in delete_rows]
+    finally:
+        db.close()
+
+
 def _load_caldav_accounts(owner: str) -> list:
     """Return the list of CalDAV accounts for *owner*, auto-migrating the legacy
     single-account ``caldav`` key to the new ``caldav_accounts`` list on first call.
@@ -533,3 +644,69 @@ async def sync_caldav(owner: str) -> dict:
         for err in result.get("errors", []):
             totals["errors"].append(f"{label}: {err}")
     return totals
+
+
+async def push_event_create(owner: str, uid: str) -> dict:
+    loaded = _load_event_for_writeback(owner, uid)
+    if not loaded:
+        return {"ok": True, "skipped": True}
+    source, calendar_id, payload = loaded
+    from src.caldav_writeback import writeback_event
+    return await writeback_event(owner, source, calendar_id, payload)
+
+
+async def push_event_update(owner: str, uid: str) -> dict:
+    return await push_event_create(owner, uid)
+
+
+async def push_event_delete(owner: str, uid: str) -> dict:
+    loaded = _load_delete_for_writeback(owner, uid)
+    if not loaded:
+        return {"ok": True, "skipped": True}
+    source, calendar_id, payload = loaded
+    from src.caldav_writeback import writeback_event
+    return await writeback_event(owner, source, calendar_id, payload, delete=True)
+
+
+async def push_pending_events(owner: str) -> dict:
+    result = {"events": 0, "errors": []}
+    uids, delete_uids = _pending_writeback_uids(owner)
+    for event_uid in uids:
+        try:
+            out = await push_event_update(owner, event_uid)
+            if out.get("ok"):
+                result["events"] += 1
+            elif not out.get("skipped"):
+                result["errors"].append(f"{event_uid}: {str(out.get('error') or out)[:160]}")
+        except Exception as e:
+            logger.warning("CalDAV pending push failed for uid=%s: %s", event_uid, e)
+            result["errors"].append(f"{event_uid}: {str(e)[:160]}")
+    for event_uid in delete_uids:
+        try:
+            out = await push_event_delete(owner, event_uid)
+            if out.get("ok"):
+                result["events"] += 1
+            elif not out.get("skipped"):
+                result["errors"].append(f"{event_uid}: {str(out.get('error') or out)[:160]}")
+        except Exception as e:
+            logger.warning("CalDAV pending delete failed for uid=%s: %s", event_uid, e)
+            result["errors"].append(f"{event_uid}: {str(e)[:160]}")
+    return result
+
+
+async def sync_caldav_direction(owner: str, direction: str = "pull") -> dict:
+    direction = (direction or "pull").strip().lower()
+    if direction == "pull":
+        return await sync_caldav(owner)
+    if direction == "push":
+        return await push_pending_events(owner)
+    if direction == "both":
+        pushed = await push_pending_events(owner)
+        pulled = await sync_caldav(owner)
+        return {"push": pushed, "pull": pulled}
+    return {
+        "calendars": 0,
+        "events": 0,
+        "deleted": 0,
+        "errors": [f"Unsupported CalDAV sync direction: {direction}"],
+    }

src/caldav_writeback.py

@@ -89,6 +89,23 @@ def find_remote_calendar(calendars, local_cal_id: str, owner: str = "", account_
     return None
 
 
+def _resource_href(obj) -> str:
+    try:
+        return str(getattr(obj, "url", "") or "")
+    except Exception:
+        return ""
+
+
+def _resource_etag(obj) -> str:
+    try:
+        etag = getattr(obj, "etag", None)
+        if callable(etag):
+            etag = etag()
+        return str(etag or "")
+    except Exception:
+        return ""
+
+
 def push_event(calendars, local_cal_id: str, ev: dict, *, delete: bool = False,
                owner: str = "", account_id: str = "") -> dict:
     """Create/update (or delete) ``ev`` on the matching remote calendar.
@@ -105,6 +122,7 @@ def push_event(calendars, local_cal_id: str, ev: dict, *, delete: bool = False,
     remote = find_remote_calendar(calendars, local_cal_id, owner=owner, account_id=account_id)
     if remote is None:
         return {"ok": False, "error": "remote calendar not found"}
+    remote_url = str(getattr(remote, "url", "") or "")
 
     try:
         existing = remote.event_by_uid(uid)
@@ -113,17 +131,34 @@ def push_event(calendars, local_cal_id: str, ev: dict, *, delete: bool = False,
 
     if delete:
         if existing is None:
-            return {"ok": True, "note": "already absent on remote"}
+            return {"ok": True, "note": "already absent on remote", "calendar_url": remote_url}
         existing.delete()
-        return {"ok": True}
+        return {
+            "ok": True,
+            "calendar_url": remote_url,
+            "remote_href": _resource_href(existing),
+            "remote_etag": _resource_etag(existing),
+        }
 
     ical = build_event_ical(ev)
     if existing is not None:
         existing.data = ical
         existing.save()
-        return {"ok": True, "updated": True}
+        return {
-    remote.save_event(ical)
+            "ok": True,
-    return {"ok": True, "created": True}
+            "updated": True,
+            "calendar_url": remote_url,
+            "remote_href": _resource_href(existing),
+            "remote_etag": _resource_etag(existing),
+        }
+    created = remote.save_event(ical)
+    return {
+        "ok": True,
+        "created": True,
+        "calendar_url": remote_url,
+        "remote_href": _resource_href(created),
+        "remote_etag": _resource_etag(created),
+    }
 
 
 def _discover_calendars(client):
@@ -154,6 +189,54 @@ def _writeback_blocking(local_cal_id, ev, delete, url, username, password,
                       owner=owner, account_id=account_id)
 
 
+def _persist_writeback_result(owner: str, calendar_id: str, uid: str, result: dict, *, delete: bool) -> None:
+    from core.database import CalendarCal, CalendarDeletedEvent, CalendarEvent, SessionLocal
+
+    if not uid or not isinstance(result, dict):
+        return
+
+    db = SessionLocal()
+    try:
+        calendar = db.query(CalendarCal).filter(
+            CalendarCal.id == calendar_id,
+            CalendarCal.owner == owner,
+        ).first()
+        if calendar and result.get("calendar_url"):
+            calendar.caldav_base_url = result.get("calendar_url")
+
+        if delete:
+            tombstone = db.query(CalendarDeletedEvent).filter(
+                CalendarDeletedEvent.uid == uid,
+                CalendarDeletedEvent.owner == owner,
+            ).first()
+            if result.get("ok"):
+                if tombstone:
+                    db.delete(tombstone)
+            elif tombstone:
+                tombstone.last_error = str(result.get("error") or result)[:500]
+            db.commit()
+            return
+
+        event = (
+            db.query(CalendarEvent)
+            .join(CalendarCal)
+            .filter(CalendarEvent.uid == uid, CalendarCal.owner == owner)
+            .first()
+        )
+        if event and result.get("ok"):
+            if result.get("remote_href"):
+                event.remote_href = result.get("remote_href")
+            if result.get("remote_etag"):
+                event.remote_etag = result.get("remote_etag")
+            event.caldav_sync_pending = None
+        db.commit()
+    except Exception:
+        db.rollback()
+        logger.exception("CalDAV write-back metadata persistence failed")
+    finally:
+        db.close()
+
+
 async def writeback_event(owner: str, calendar_source: str, calendar_id: str,
                           ev: dict, *, delete: bool = False) -> dict:
     """Best-effort push of a local change to the remote CalDAV server.
@@ -204,9 +287,12 @@ async def writeback_event(owner: str, calendar_source: str, calendar_id: str,
         result = await asyncio.to_thread(
             _writeback_blocking, calendar_id, ev, delete, url, user, pw, owner, acc_id
         )
+        _persist_writeback_result(owner, calendar_id, (ev or {}).get("uid", ""), result, delete=delete)
         if not result.get("ok"):
             logger.warning("CalDAV write-back did not apply: %s", result.get("error") or result)
         return result
     except Exception as e:
         logger.exception("CalDAV write-back raised")
-        return {"ok": False, "error": str(e)[:200]}
+        result = {"ok": False, "error": str(e)[:200]}
+        _persist_writeback_result(owner, calendar_id, (ev or {}).get("uid", ""), result, delete=delete)
+        return result

src/context_budget.py

@@ -31,16 +31,22 @@ def compute_input_token_budget(
 
     Args:
         configured: the value read from settings (may be the default).
-        context_length: the model's discovered context window (0/unknown if none).
+        context_length: the model's discovered context window. Pass 0 when the
-        explicit: True if the user explicitly set ``agent_input_token_budget``.
+            window is unknown / only a bare fallback — auto-scaling then stays
+            conservative instead of trusting an unproven window (review on #4122).
+        explicit: True if the user set a NON-default budget. The default value is
+            the "auto" sentinel (scale to the window); any other value is an
+            explicit cap. (A deliberately-chosen default can't be distinguished
+            from a materialized default by value, so the default reads as auto.)
 
     Rules:
         - Explicit user budget is honoured exactly, only clamped to the model's
-          window when that window is known (never send more than the model holds).
+          window when that window is known (the user's deliberate choice wins;
-        - Otherwise (default), scale to ``headroom`` of the context window, capped
+          ``hard_max`` is an auto-budget ceiling only — see #1230).
-          at ``hard_max`` — so long-context models use their capacity.
+        - Otherwise (auto), scale to ``headroom`` of the context window, capped at
-        - When the window is unknown, fall back to the configured/default value
+          ``hard_max`` — so long-context models use their capacity.
-          (preserving the previous behaviour).
+        - When the window is unknown (context_length <= 0), use the conservative
+          ``default`` budget and do NOT scale off the fallback.
     """
     configured = int(configured or 0)
     context_length = int(context_length or 0)
@@ -53,3 +59,17 @@ def compute_input_token_budget(
         return max(1, min(scaled, hard_max))
 
     return configured if configured > 0 else default
+
+
+def budget_is_explicit(configured: int, *, default: int = DEFAULT_BUDGET) -> bool:
+    """Whether a configured agent_input_token_budget is a deliberate explicit cap.
+
+    The default value is the "auto" sentinel (scale to the model's window), so only
+    a NON-default positive value counts as explicit. This keys off the VALUE, not
+    settings *presence* — the settings-save path materializes every default into
+    settings.json, so a persisted default must still read as auto (the regression
+    #4121 / #1230 are about). Centralised here so the materialized-default contract
+    is unit-testable and can't silently regress to a presence check.
+    """
+    configured = int(configured or 0)
+    return configured > 0 and configured != default

src/context_compactor.py

@@ -244,9 +244,17 @@ def trim_for_context(messages: List[Dict], context_length: int, reserve_tokens:
     protected_tokens = estimate_tokens(protected_msgs)
     budget -= protected_tokens
 
-    # Priority: keep first system msg (preset prompt), drop others (memory, RAG, memo)
+    # Priority: keep first system msg (preset prompt), drop others (memory, RAG, memo).
-    essential_system = system_msgs[:1] if system_msgs else []
+    # Exception: a research-spinoff primer (the seeded report that grounds a
-    extra_system = system_msgs[1:]
+    # "Discuss" chat) must never be dropped — it is the conversation's whole
+    # knowledge base. Treat any system message carrying research_spinoff_from
+    # metadata as essential alongside the leading system prompt.
+    def _is_research_primer(m):
+        return bool((m.get("metadata") or {}).get("research_spinoff_from"))
+    _primers = [m for m in system_msgs if _is_research_primer(m)]
+    _non_primer = [m for m in system_msgs if not _is_research_primer(m)]
+    essential_system = (_non_primer[:1] if _non_primer else []) + _primers
+    extra_system = _non_primer[1:]
 
     # Try dropping extra system messages one by one (from the end)
     trimmed = essential_system + convo_msgs

src/cookbook_serve_lifecycle.py

@@ -136,7 +136,8 @@ async def _tick() -> None:
         return
     try:
         state = json.loads(state_path.read_text(encoding="utf-8"))
-    except Exception:
+    except Exception as e:
+        logger.warning("cookbook_serve_lifecycle: state file unreadable (%s), skipping tick", e)
         return
     tasks = state.get("tasks") or []
     now_ms = int(time.time() * 1000)
@@ -178,8 +179,26 @@ async def _tick() -> None:
     if stopped_any:
         try:
             from core.atomic_io import atomic_write_json
-            state["tasks"] = tasks
+            # Re-read the state file so concurrent UI writes (task adds,
-            atomic_write_json(state_path, state)
+            # status flips, config edits) are not silently overwritten.
+            # Apply only our stop mutations to the fresh snapshot.
+            try:
+                fresh = json.loads(state_path.read_text(encoding="utf-8"))
+                fresh_tasks = fresh.get("tasks") or []
+            except Exception:
+                fresh = state
+                fresh_tasks = tasks
+            stopped_sids = {sid for sid, _, _ in to_stop}
+            for ft in fresh_tasks:
+                if not isinstance(ft, dict):
+                    continue
+                ft_sid = ft.get("sessionId") or ft.get("id")
+                if ft_sid in stopped_sids:
+                    ft["status"] = "stopped"
+                    ft["_scheduledStopAtMs"] = None
+                    ft["_lastStatusFlipAt"] = now_ms
+            fresh["tasks"] = fresh_tasks
+            atomic_write_json(state_path, fresh)
         except Exception as e:
             logger.warning(f"cookbook_serve_lifecycle: state write failed: {e}")
 

src/endpoint_resolver.py

@@ -12,7 +12,7 @@ from typing import Optional, Tuple, Dict
 from urllib.parse import urlparse, urlunparse
 
 from core.database import SessionLocal, ModelEndpoint
-from src.llm_core import _detect_provider, _host_match, _ollama_api_root
+from src.llm_core import _detect_provider, _host_match, _is_kimi_code_url, KIMI_CODE_USER_AGENT, _ollama_api_root
 
 logger = logging.getLogger(__name__)
 
@@ -183,7 +183,16 @@ def build_chat_url(base: str) -> str:
 
 
 def build_models_url(base: str) -> Optional[str]:
-    """Return the provider-specific model-list endpoint URL for a base."""
+    """Return the provider-specific model-list endpoint URL for a base.
+
+    For OpenAI-compatible servers (LM Studio, llama.cpp, vLLM,
+    text-generation-webui, etc.) the model list is exposed at ``/v1/models``.
+    When the user-supplied base has no path — e.g. ``http://localhost:1234`` —
+    we still need to land on ``/v1/models`` (issue #25); insert the ``/v1``
+    segment only when the path is empty, leaving any explicit non-empty path
+    untouched (so custom prefixes like ``/openai`` or ``/api/openai/v1`` keep
+    their semantics).
+    """
     base = normalize_base(resolve_url(base))
     provider = _detect_provider(base)
     if provider == "anthropic":
@@ -192,6 +201,12 @@ def build_models_url(base: str) -> Optional[str]:
         return _ollama_api_root(base) + "/tags"
     if provider == "chatgpt-subscription":
         return None
+    # Generic OpenAI-compatible fallback: ensure the path lands on /v1/models
+    # when the user omitted a path entirely. If a non-empty path is already
+    # present (e.g. /openai, /api/openai/v1, /v1), trust the caller — the
+    # /models suffix is appended as-is and the caller's prefix is preserved.
+    if not urlparse(base).path:
+        base = base + "/v1"
     return base + "/models"
 
 
@@ -215,6 +230,8 @@ def build_headers(api_key: Optional[str], base: str) -> Dict[str, str]:
     if provider == "openrouter":
         headers.setdefault("HTTP-Referer", "https://github.com/pewdiepie-archdaemon/odysseus")
         headers.setdefault("X-OpenRouter-Title", "Odysseus")
+    if _is_kimi_code_url(base):
+        headers.setdefault("User-Agent", KIMI_CODE_USER_AGENT)
     return headers
 
 
@@ -250,23 +267,19 @@ def resolve_endpoint(
     ep_id = _stg(f"{setting_prefix}_endpoint_id")
     model = _stg(f"{setting_prefix}_model")
 
-    # If the specific endpoint is not configured, but the caller provided a
+    # Fall back to utility model for task/research/auto-naming if not specifically configured.
+    if not ep_id and setting_prefix not in ("utility", "default"):
+        ep_id = _stg("utility_endpoint_id")
+        model = _stg("utility_model")
+
+    # If the endpoint is STILL not configured, but the caller provided a
     # valid fallback (e.g. the active session model), use that immediately.
     # This prevents background tasks from jumping to the global default_model
     # when the user is mid-conversation with a different model.
     if not ep_id and fallback_url and fallback_model:
         return fallback_url, fallback_model, fallback_headers
 
-    # Unset Utility means "same as Default Chat Model".
+    # Unset Utility (or anything else that didn't have a fallback) means "same as Default Chat Model".
-    if setting_prefix == "utility" and not ep_id:
-        ep_id = _stg("default_endpoint_id")
-        model = _stg("default_model")
-
-    # Fall back to utility model for task/research/auto-naming if not specifically configured.
-    # If Utility itself is unset, the block above makes that resolve to Default Chat.
-    if not ep_id and setting_prefix != "utility":
-        ep_id = _stg("utility_endpoint_id")
-        model = _stg("utility_model")
     if not ep_id:
         ep_id = _stg("default_endpoint_id")
         model = _stg("default_model")

src/integrations.py

@@ -6,6 +6,7 @@ import re
 from typing import Dict, List, Optional, Any
 
 import httpx
+from fastapi import HTTPException
 
 from core.atomic_io import atomic_write_json
 from core.platform_compat import safe_chmod
@@ -258,6 +259,11 @@ def add_integration(data: Dict[str, Any]) -> Dict[str, Any]:
     integration.setdefault("name", "")
     integration.setdefault("base_url", "")
 
+    if not isinstance(integration.get("name"), str) or not integration["name"].strip():
+        raise HTTPException(400, "Integration name is required")
+    if not isinstance(integration.get("base_url"), str) or not integration["base_url"].strip():
+        raise HTTPException(400, "Integration base URL is required")
+
     integrations = load_integrations()
     integrations.append(integration)
     save_integrations(integrations)
@@ -266,6 +272,11 @@ def add_integration(data: Dict[str, Any]) -> Dict[str, Any]:
 
 def update_integration(integration_id: str, data: Dict[str, Any]) -> Optional[Dict[str, Any]]:
     """Update fields on an existing integration. Returns updated integration or None."""
+    if "name" in data and (not isinstance(data["name"], str) or not data["name"].strip()):
+        raise HTTPException(400, "Integration name is required")
+    if "base_url" in data and (not isinstance(data["base_url"], str) or not data["base_url"].strip()):
+        raise HTTPException(400, "Integration base URL is required")
+
     integrations = load_integrations()
     for item in integrations:
         if item.get("id") == integration_id:

src/llm_core.py

@@ -7,6 +7,7 @@ import logging
 import hashlib
 import threading
 import re
+import os
 from fastapi import HTTPException
 from typing import Optional, Dict, List, Tuple
 from src.model_context import get_context_length, DEFAULT_CONTEXT
@@ -22,6 +23,24 @@ class LLMConfig:
     MAX_RETRIES = 3
     RETRY_DELAY = 0.5
     STREAM_TIMEOUT = 300
+    # TCP+TLS connect budget for a SINGLE attempt. The old hard-coded 3.0s
+    # assumed LAN/Tailscale peers ('SYN in <100ms'); it is too tight for public
+    # cloud endpoints (offshore APIs take ~0.5-1.5s cold, with jitter), so a
+    # brief blip on the first connect of an idle chat surfaced as a 503 on the
+    # streaming path (which, unlike llm_call, does not retry the connect). A
+    # genuinely dead upstream stays bounded by the dead-host cooldown. Override
+    # with env LLM_CONNECT_TIMEOUT (seconds).
+    CONNECT_TIMEOUT = float(os.getenv('LLM_CONNECT_TIMEOUT', '10') or '10')
+
+
+def _call_timeout(read_timeout) -> httpx.Timeout:
+    """Per-request timeout for non-streaming LLM calls (connect from config)."""
+    return httpx.Timeout(connect=LLMConfig.CONNECT_TIMEOUT, read=float(read_timeout), write=10.0, pool=5.0)
+
+
+def _stream_timeout(read_timeout) -> httpx.Timeout:
+    """Per-request timeout for streaming LLM calls (connect from config)."""
+    return httpx.Timeout(connect=LLMConfig.CONNECT_TIMEOUT, read=float(read_timeout), write=30.0, pool=5.0)
 
 
 # Cache for LLM responses
@@ -423,6 +442,146 @@ def _host_match(url: str, *domains: str) -> bool:
     return any(host == d or host.endswith("." + d) for d in domains)
 
 
+# Kimi Code subscription keys (api.kimi.com/coding/v1) require a whitelisted
+# coding-agent User-Agent; otherwise the API returns 403 access_terminated_error.
+# Tried in order; first success is cached per base URL for later requests.
+KIMI_CODE_USER_AGENTS: tuple[str, ...] = (
+    "claude-code/0.1.0",
+    "claude-code/1.0.0",
+    "KimiCLI/1.0",
+    "Kilo-Code/1.0",
+    "Roo-Code/1.0",
+    "Cursor/1.0",
+)
+KIMI_CODE_USER_AGENT = KIMI_CODE_USER_AGENTS[0]
+_kimi_code_ua_cache: dict[str, str] = {}
+
+
+def _is_kimi_code_url(url: str) -> bool:
+    if not url or not _host_match(url, "kimi.com"):
+        return False
+    try:
+        return "/coding" in (urlparse(url).path or "")
+    except Exception:
+        return False
+
+
+def _kimi_code_base_key(url: str) -> str:
+    """Normalize a Kimi Code chat/models URL to its OpenAI base (.../coding/v1)."""
+    parsed = urlparse(url)
+    path = (parsed.path or "").rstrip("/")
+    for suffix in ("/chat/completions", "/models", "/completions"):
+        if path.endswith(suffix):
+            path = path[: -len(suffix)]
+    path = path.rstrip("/") or "/coding/v1"
+    return f"{parsed.scheme}://{parsed.netloc}{path}"
+
+
+def _is_kimi_code_access_denied(status: int, body: bytes | str) -> bool:
+    if status != 403:
+        return False
+    text = body.decode("utf-8", errors="replace") if isinstance(body, bytes) else (body or "")
+    lower = text.lower()
+    return (
+        "access_terminated_error" in lower
+        or "coding agents" in lower
+        or "only available for coding" in lower
+    )
+
+
+def _kimi_code_ua_candidates(url: str) -> list[str]:
+    if not _is_kimi_code_url(url):
+        return []
+    base_key = _kimi_code_base_key(url)
+    cached = _kimi_code_ua_cache.get(base_key)
+    if cached:
+        return [cached] + [ua for ua in KIMI_CODE_USER_AGENTS if ua != cached]
+    return list(KIMI_CODE_USER_AGENTS)
+
+
+def _remember_kimi_code_user_agent(url: str, user_agent: str) -> None:
+    _kimi_code_ua_cache[_kimi_code_base_key(url)] = user_agent
+
+
+def apply_kimi_code_headers(headers: Optional[Dict], url: str) -> Dict[str, str]:
+    """Pick a Kimi Code User-Agent (cached probe when possible)."""
+    h = dict(headers or {})
+    if not _is_kimi_code_url(url):
+        return h
+    base_key = _kimi_code_base_key(url)
+    cached = _kimi_code_ua_cache.get(base_key)
+    if cached:
+        h["User-Agent"] = cached
+        return h
+    models_url = base_key.rstrip("/") + "/models"
+    from src.tls_overrides import llm_verify
+    for ua in KIMI_CODE_USER_AGENTS:
+        trial = dict(h)
+        trial["User-Agent"] = ua
+        try:
+            r = httpx.get(models_url, headers=trial, timeout=8, verify=llm_verify())
+        except Exception:
+            continue
+        if _is_kimi_code_access_denied(r.status_code, r.content):
+            logger.debug("Kimi Code rejected User-Agent %s (403), trying next", ua)
+            continue
+        if r.status_code < 400:
+            _remember_kimi_code_user_agent(url, ua)
+            h["User-Agent"] = ua
+            return h
+        break
+    h.setdefault("User-Agent", KIMI_CODE_USER_AGENT)
+    return h
+
+
+def httpx_get_kimi_aware(url: str, headers: Optional[Dict], **kwargs):
+    h = apply_kimi_code_headers(headers, url)
+    if not _is_kimi_code_url(url):
+        return httpx.get(url, headers=h, **kwargs)
+    last = None
+    for ua in _kimi_code_ua_candidates(url):
+        trial = dict(h)
+        trial["User-Agent"] = ua
+        last = httpx.get(url, headers=trial, **kwargs)
+        if not _is_kimi_code_access_denied(last.status_code, last.content):
+            if last.status_code < 400:
+                _remember_kimi_code_user_agent(url, ua)
+            return last
+    return last
+
+
+def httpx_post_kimi_aware(url: str, headers: Optional[Dict], **kwargs):
+    h = apply_kimi_code_headers(headers, url)
+    if not _is_kimi_code_url(url):
+        return httpx.post(url, headers=h, **kwargs)
+    last = None
+    for ua in _kimi_code_ua_candidates(url):
+        trial = dict(h)
+        trial["User-Agent"] = ua
+        last = httpx.post(url, headers=trial, **kwargs)
+        if not _is_kimi_code_access_denied(last.status_code, last.content):
+            if last.status_code < 400:
+                _remember_kimi_code_user_agent(url, ua)
+            return last
+    return last
+
+
+async def httpx_post_kimi_aware_async(client, url: str, headers: Optional[Dict], **kwargs):
+    h = apply_kimi_code_headers(headers, url)
+    if not _is_kimi_code_url(url):
+        return await client.post(url, headers=h, **kwargs)
+    last = None
+    for ua in _kimi_code_ua_candidates(url):
+        trial = dict(h)
+        trial["User-Agent"] = ua
+        last = await client.post(url, headers=trial, **kwargs)
+        if not _is_kimi_code_access_denied(last.status_code, last.content):
+            if last.status_code < 400:
+                _remember_kimi_code_user_agent(url, ua)
+            return last
+    return last
+
+
 def _detect_provider(url: str) -> str:
     """Detect the API provider from a configured endpoint URL.
 
@@ -446,6 +605,8 @@ def _detect_provider(url: str) -> str:
         return "groq"
     if _host_match(url, "nvidia.com"):
         return "nvidia"
+    if _host_match(url, "moonshot.ai") or _host_match(url, "moonshot.cn"):
+        return "moonshot"
     from src.chatgpt_subscription import is_chatgpt_subscription_base
     if is_chatgpt_subscription_base(url):
         return "chatgpt-subscription"
@@ -542,6 +703,12 @@ def _provider_label(url: str) -> str:
     if _host_match(url, "googleapis.com"): return "Google"
     if _host_match(url, "together.xyz", "together.ai"): return "Together"
     if _host_match(url, "fireworks.ai"): return "Fireworks"
+    if _host_match(url, "kimi.com"):
+        try:
+            if "/coding" in (urlparse(url).path or ""):
+                return "Kimi Code"
+        except Exception:
+            pass
     if _is_ollama_native_url(url): return "Ollama"
     try:
         host = (urlparse(url).hostname or "").lower()
@@ -682,7 +849,7 @@ def _uses_max_completion_tokens(model: str) -> bool:
 # perfectly good model as failing. For these models we omit the field and let
 # the API use its required default. (gpt-4.5 is intentionally excluded — it is
 # not a reasoning model and accepts temperature normally.)
-_FIXED_TEMPERATURE_MODELS = ("o1", "o3", "o4", "gpt-5")
+_FIXED_TEMPERATURE_MODELS = ("o1", "o3", "o4", "gpt-5", "kimi-for-coding")
 
 def _restricts_temperature(model: str) -> bool:
     """Check if a model rejects any non-default temperature."""
@@ -691,6 +858,28 @@ def _restricts_temperature(model: str) -> bool:
     m = model.lower()
     return any(m.startswith(p) or f"/{p}" in m for p in _FIXED_TEMPERATURE_MODELS)
 
+
+# The official Moonshot API fixes temperature at 1.0 in thinking mode and 0.6
+# when thinking is explicitly disabled for Kimi K2.5/K2.6. Any other explicit
+# value returns HTTP 400. Odysseus does not currently send the `thinking` mode
+# control, so omit temperature and let Moonshot use its default thinking mode.
+# Keep the gate provider-specific: self-hosted Kimi deployments may accept
+# custom sampling values, and older Moonshot models have different defaults.
+def _moonshot_rejects_custom_temperature(provider: str, model: str) -> bool:
+    """Check if the official Moonshot API fixes temperature for this model."""
+    if provider != "moonshot" or not isinstance(model, str):
+        return False
+    model_id = model.lower().rsplit("/", 1)[-1]
+    return bool(re.match(r"^kimi-k2\.(?:5|6)(?:$|[-_:])", model_id))
+
+
+def _omit_temperature(provider: str, model: str) -> bool:
+    """Check if a request should use the provider's default temperature."""
+    return _restricts_temperature(model) or _moonshot_rejects_custom_temperature(
+        provider, model
+    )
+
+
 # Anthropic removed the sampling parameters (temperature, top_p, top_k) starting
 # with Claude Opus 4.7. On Opus 4.7 and later, sending `temperature` at all —
 # even 0.0 — returns HTTP 400. Earlier Claude models (Opus 4.6 and below, every
@@ -1138,7 +1327,7 @@ def list_model_ids(
             from src.endpoint_resolver import build_models_url
 
             models_url = build_models_url(base_chat_url)
-        r = httpx.get(models_url, headers=h, timeout=timeout)
+        r = httpx_get_kimi_aware(models_url, h, timeout=timeout)
         r.raise_for_status()
         data = r.json()
         model_ids = [m.get("id") for m in (data.get("data") or []) if m.get("id")]
@@ -1239,14 +1428,14 @@ def llm_call(url: str, model: str, messages: List[Dict], temperature: float = LL
             "messages": messages_copy,
             "temperature": temperature,
         }
-        if _restricts_temperature(model):
+        if _omit_temperature(provider, model):
             payload.pop("temperature", None)
         if max_tokens and max_tokens > 0:
             tok_key = "max_completion_tokens" if _uses_max_completion_tokens(model) else "max_tokens"
             payload[tok_key] = max_tokens
     try:
         note_model_activity(target_url, model)
-        r = httpx.post(target_url, headers=h, json=payload, timeout=timeout)
+        r = httpx_post_kimi_aware(target_url, h, json=payload, timeout=timeout)
     except Exception as e:
         raise HTTPException(502, f"POST {target_url} failed: {e}")
     if not r.is_success:
@@ -1433,7 +1622,7 @@ async def llm_call_async(
             "messages": messages_copy,
             "temperature": temperature,
         }
-        if _restricts_temperature(model):
+        if _omit_temperature(provider, model):
             payload.pop("temperature", None)
         if max_tokens and max_tokens > 0:
             tok_key = "max_completion_tokens" if _uses_max_completion_tokens(model) else "max_tokens"
@@ -1446,7 +1635,7 @@ async def llm_call_async(
     if _is_host_dead(target_url):
         raise HTTPException(503, f"Upstream {_host_key(target_url)} marked unreachable (cooldown active)")
 
-    call_timeout = httpx.Timeout(connect=3.0, read=float(timeout), write=10.0, pool=5.0)
+    call_timeout = _call_timeout(timeout)
     attempt = 0
     while attempt < max_retries:
         attempt += 1
@@ -1454,7 +1643,7 @@ async def llm_call_async(
         try:
             note_model_activity(target_url, model)
             client = _get_http_client()
-            r = await client.post(target_url, headers=h, json=payload, timeout=call_timeout)
+            r = await httpx_post_kimi_aware_async(client, target_url, h, json=payload, timeout=call_timeout)
             duration = time.time() - start
             if not r.is_success:
                 friendly = _format_upstream_error(r.status_code, r.text, target_url)
@@ -1550,7 +1739,7 @@ async def stream_llm(url: str, model: str, messages: List[Dict], temperature: fl
             "temperature": temperature,
             "stream": True,
         }
-        if _restricts_temperature(model):
+        if _omit_temperature(provider, model):
             payload.pop("temperature", None)
         if provider not in {"openrouter", "groq"}:
             payload["stream_options"] = {"include_usage": True}
@@ -1570,9 +1759,12 @@ async def stream_llm(url: str, model: str, messages: List[Dict], temperature: fl
             from src.copilot import apply_request_headers
             apply_request_headers(h, messages_copy)
 
-    # Short connect timeout: a reachable peer answers SYN in <100ms even on
+    # Connect budget from LLMConfig.CONNECT_TIMEOUT (env LLM_CONNECT_TIMEOUT).
-    # Tailscale. 3s is plenty; 30s let one dead upstream wedge the UI.
+    # The dead-host cooldown still bounds a genuinely unreachable upstream, so a
-    stream_timeout = httpx.Timeout(connect=3.0, read=float(timeout), write=30.0, pool=5.0)
+    # wider connect budget only affects first contact and stops a brief cold
+    # connect blip (offshore/public endpoints) surfacing as a 503 on this stream
+    # path, which -- unlike llm_call -- does not retry the connect.
+    stream_timeout = _stream_timeout(timeout)
 
     if _is_host_dead(target_url):
         yield f'event: error\ndata: {json.dumps({"error": f"Upstream {_host_key(target_url)} unreachable (cooldown active)", "status": 503})}\n\n'
@@ -1848,6 +2040,7 @@ async def stream_llm(url: str, model: str, messages: List[Dict], temperature: fl
             events.append(_stream_delta_event(part))
         return events
 
+    h = apply_kimi_code_headers(h, target_url)
     try:
         client = _get_http_client()
         async with client.stream('POST', target_url, json=payload, headers=h, timeout=stream_timeout) as r:

src/model_context.py

@@ -222,16 +222,12 @@ KNOWN_CONTEXT_WINDOWS = {
 # ---------------------------------------------------------------------------
 # Cache
 # ---------------------------------------------------------------------------
-_context_cache: Dict[Tuple[str, str], int] = {}
+_context_cache: Dict[Tuple[str, str], Tuple[int, bool]] = {}
 
 
-def get_context_length(endpoint_url: str, model: str) -> int:
+def _get_context_length_cached(endpoint_url: str, model: str) -> Tuple[int, bool]:
-    """Get the context window size for a model.
+    """Return (context_length, known). ``known`` is False only when the value is a
-
+    bare DEFAULT_CONTEXT fallback (no endpoint report and not in the known table)."""
-    Queries /v1/models on the endpoint and looks for context_length
-    or context_window fields. Caches result per (endpoint, model).
-    Falls back to DEFAULT_CONTEXT if unavailable.
-    """
     configured_kind = _configured_endpoint_kind(endpoint_url)
     is_local = is_local_endpoint(endpoint_url)
     # Key on (endpoint_url, model): the same model id can be served by two
@@ -242,14 +238,50 @@ def get_context_length(endpoint_url: str, model: str) -> int:
     if not is_local and cache_key in _context_cache:
         return _context_cache[cache_key]
 
-    ctx = _query_context_length(endpoint_url, model)
+    ctx, known = _query_context_length(endpoint_url, model)
     # Only cache non-default values to allow retry on next request.
     # Local endpoints can restart with a different --max-model-len while keeping
     # the same model id, so always re-query them instead of serving stale cache.
     if not is_local and (ctx != DEFAULT_CONTEXT or configured_kind in ("api", "proxy")):
-        _context_cache[cache_key] = ctx
+        _context_cache[cache_key] = (ctx, known)
     logger.info(f"Context length for {model}: {ctx}")
-    return ctx
+    return ctx, known
+
+
+def get_context_length(endpoint_url: str, model: str) -> int:
+    """Get the context window size for a model.
+
+    Queries /v1/models on the endpoint and looks for context_length
+    or context_window fields. Caches result per (endpoint, model).
+    Falls back to DEFAULT_CONTEXT if unavailable.
+    """
+    return _get_context_length_cached(endpoint_url, model)[0]
+
+
+def get_context_length_known(endpoint_url: str, model: str) -> Tuple[int, bool]:
+    """Like ``get_context_length`` but also returns whether the window was actually
+    discovered (endpoint-reported or in the known-models table) rather than the bare
+    DEFAULT_CONTEXT fallback. Callers that *scale* a budget off the window must not
+    trust an unknown value — a fallback 128K isn't proof the model holds 128K
+    (review on #4122)."""
+    return _get_context_length_cached(endpoint_url, model)
+
+
+def budget_context_for_model(endpoint_url: str, model: str, *, fallback: int = 0) -> int:
+    """Context window to scale the agent input budget against.
+
+    Returns the *freshly discovered* window when it was actually proven
+    (endpoint-reported / known table), else 0 so auto-scaling stays conservative.
+    Crucially this binds the ``known`` flag to the value it proves — callers must
+    not pair this flag with a context length from a *different* lookup (a stale
+    local re-query, or a caller that didn't pass one), which would budget off an
+    unproven number (review on #4122). On probe error, returns ``fallback`` (the
+    caller's best-known value) to preserve prior behaviour."""
+    try:
+        ctx, known = get_context_length_known(endpoint_url, model)
+        return ctx if known else 0
+    except Exception:
+        return fallback
 
 
 def _lookup_known(model: str) -> Optional[int]:
@@ -271,8 +303,9 @@ def _lookup_known(model: str) -> Optional[int]:
     return best_ctx
 
 
-def _query_context_length(endpoint_url: str, model: str) -> int:
+def _query_context_length(endpoint_url: str, model: str) -> Tuple[int, bool]:
-    """Query the model API for context length."""
+    """Query the model API for context length. Returns (context_length, known) where
+    ``known`` is False only for the bare DEFAULT_CONTEXT fallback."""
     known = _lookup_known(model)
     api_ctx = None
     configured_kind = _configured_endpoint_kind(endpoint_url)
@@ -283,8 +316,8 @@ def _query_context_length(endpoint_url: str, model: str) -> int:
     if configured_kind in ("api", "proxy"):
         if known:
             logger.info(f"Using known context window for {model}: {known}")
-            return known
+            return known, True
-        return DEFAULT_CONTEXT
+        return DEFAULT_CONTEXT, False
 
     # Try llama.cpp /slots endpoint first — reports actual serving context
     if is_local_endpoint(endpoint_url):
@@ -297,7 +330,7 @@ def _query_context_length(endpoint_url: str, model: str) -> int:
                     n_ctx = slots[0].get("n_ctx")
                     if n_ctx and isinstance(n_ctx, int) and n_ctx > 0:
                         logger.info(f"llama.cpp /slots reports n_ctx={n_ctx} for {model}")
-                        return n_ctx
+                        return n_ctx, True
         except Exception:
             pass
 
@@ -309,7 +342,8 @@ def _query_context_length(endpoint_url: str, model: str) -> int:
     if is_copilot_base(endpoint_url):
         if known:
             logger.info(f"Using known context window for {model}: {known}")
-        return known or DEFAULT_CONTEXT
+            return known, True
+        return DEFAULT_CONTEXT, False
 
     from src.endpoint_resolver import build_models_url
 
@@ -354,18 +388,18 @@ def _query_context_length(endpoint_url: str, model: str) -> int:
         _is_local = is_local_endpoint(endpoint_url)
         if _is_local and api_ctx < known:
             logger.info(f"Local endpoint reports {api_ctx} for {model} (known max: {known}) — using API value")
-            return api_ctx
+            return api_ctx, True
         result = max(api_ctx, known)
         if api_ctx < known:
             logger.info(f"API reported {api_ctx} for {model}, using known {known} instead")
-        return result
+        return result, True
     if api_ctx:
-        return api_ctx
+        return api_ctx, True
     if known:
         logger.info(f"Using known context window for {model}: {known}")
-        return known
+        return known, True
 
-    return DEFAULT_CONTEXT
+    return DEFAULT_CONTEXT, False
 
 
 def estimate_tokens(messages: List[Dict]) -> int:

src/optional_deps.py

@@ -0,0 +1,32 @@
+"""Compatibility helpers for optional third-party dependencies."""
+
+from __future__ import annotations
+
+import sys
+import types
+
+
+def patch_realesrgan_torchvision_compat() -> None:
+    """Restore the torchvision import path expected by BasicSR/Real-ESRGAN."""
+    module_name = "torchvision.transforms.functional_tensor"
+    if module_name in sys.modules:
+        return
+    try:
+        from torchvision.transforms import functional
+    except Exception:
+        return
+
+    rgb_to_grayscale = getattr(functional, "rgb_to_grayscale", None)
+    if rgb_to_grayscale is None:
+        return
+
+    shim = types.ModuleType(module_name)
+    shim.rgb_to_grayscale = rgb_to_grayscale
+    shim.__getattr__ = lambda name: getattr(functional, name)
+    sys.modules[module_name] = shim
+
+
+def prepare_optional_dependency_import(name: str) -> None:
+    """Apply known import-time compatibility shims before probing a package."""
+    if name == "realesrgan":
+        patch_realesrgan_torchvision_compat()

src/settings.py

@@ -101,14 +101,22 @@ DEFAULT_SETTINGS = {
     "research_run_timeout_seconds": 1800,
     "agent_max_tool_calls": 0,
     "agent_max_rounds": 20,  # per-message agent step cap (clamped 1..200)
+    # Soft input-token budget for the agent loop. The DEFAULT value (6000) is the
+    # "auto" sentinel: it means "scale the budget to the model's context window"
+    # (#1230) — so long-context models aren't capped at 6000. Set ANY OTHER value
+    # to enforce an explicit cap (clamped to the window only — hard_max does not
+    # apply to explicit budgets, #1230); set 0 to disable soft-trimming. The
+    # default is treated as auto because the settings-save path materializes
+    # defaults, so a persisted 6000 can't be told apart from a deliberate 6000 —
+    # to pin a budget near the default, use a nearby value (e.g. 5999).
     "agent_input_token_budget": 6000,
-    # Ceiling on the *auto-derived* input budget that #1230 introduced. Has
+    # Ceiling on the *auto-derived* input budget; a configurable setting since #1273
-    # no effect when `agent_input_token_budget` is explicitly set (the user's
+    # (the merged #1230 left it a module constant). No effect on an explicit budget
-    # value is honoured regardless). Default matches
+    # — a deliberate value is honoured (#1230). Default matches
-    # `src.context_budget.DEFAULT_HARD_MAX`; lower this for cost-paranoid
+    # `src.context_budget.DEFAULT_HARD_MAX`; lower this for
-    # setups, raise it on premium APIs with very large windows that you
+    # cost-paranoid setups, raise it on premium APIs with very large windows you
     # want to actually use (e.g. 900_000 to fill a 1M-context model). See
-    # `compute_input_token_budget` in src/context_budget.py.
+    # `compute_input_token_budget`.
     "agent_input_token_hard_max": 200_000,
     "agent_stream_timeout_seconds": 300,
     # Extra directory roots that read_file / write_file may access, in
@@ -223,8 +231,10 @@ def is_setting_overridden(key: str) -> bool:
 
     ``load_settings`` merges DEFAULT_SETTINGS with the saved file, so a value
     equal to its default is indistinguishable from "never set" via get_setting.
-    Callers that need to treat an explicit user choice differently from the
+    Callers that must distinguish an explicit user choice from a default read
-    default (e.g. adaptive budgets) use this to read the raw saved file.
+    the raw saved file via this. (Note: a materialized default is also "present",
+    so value-sensitive callers should compare against the default — see
+    ``context_budget.budget_is_explicit``.)
     """
     try:
         with open(SETTINGS_FILE, "r", encoding="utf-8") as f:

src/task_scheduler.py

@@ -1649,6 +1649,8 @@ class TaskScheduler:
                     data = json.loads(event_str[6:])
                     # Capture text from all event types, not just delta
                     if "delta" in data:
+                        if data.get("thinking"):
+                            continue
                         full_text += data["delta"]
                     elif data.get("type") == "tool_output":
                         # Tool results — capture summary so we have SOMETHING even

src/teacher_escalation.py

@@ -42,7 +42,7 @@ _SOTA_HOSTS = frozenset({
     "api.together.xyz", "api.fireworks.ai",
     "api.perplexity.ai", "api.x.ai",
     "generativelanguage.googleapis.com", "api.groq.com",
-    "openrouter.ai", "ollama.com", "api.venice.ai",
+    "openrouter.ai", "ollama.com", "api.venice.ai", "api.kimi.com",
 })
 
 
@@ -594,6 +594,8 @@ async def run_teacher_inline(
                         "exit_code": payload.get("exit_code"),
                     })
                 if "delta" in payload and isinstance(payload["delta"], str):
+                    if payload.get("thinking"):
+                        continue
                     captured_text_parts.append(payload["delta"])
                 yield 'data: ' + json.dumps(payload) + '\n\n'
                 continue

src/tool_implementations.py

@@ -1445,7 +1445,15 @@ async def do_manage_calendar(content: str, owner: Optional[str] = None) -> Dict:
     """Handle manage_calendar tool calls: list/create/update/delete calendar events (local SQLite)."""
     from datetime import datetime, timedelta
     from core.database import SessionLocal, CalendarCal, CalendarEvent, Note
-    from routes.calendar_routes import _ensure_default_calendar, _parse_dt, _parse_dt_pair, parse_due_for_user, _resolve_base_uid
+    from routes.calendar_routes import (
+        _ensure_default_calendar,
+        _parse_dt,
+        _parse_dt_pair,
+        parse_due_for_user,
+        _resolve_base_uid,
+        _push_caldav_event_after_commit,
+        _record_caldav_delete_tombstone,
+    )
     import uuid as _uuid
 
     try:
@@ -1643,6 +1651,9 @@ async def do_manage_calendar(content: str, owner: Optional[str] = None) -> Dict:
             except ValueError as e:
                 return {"error": f"Invalid date format: {e}", "exit_code": 1}
 
+            if end_dt <= start_dt:
+                end_dt = start_dt + timedelta(days=1)
+
             q = _event_query().filter(
                 CalendarEvent.dtstart < end_dt,
                 CalendarEvent.dtend > start_dt,
@@ -1822,6 +1833,7 @@ async def do_manage_calendar(content: str, owner: Optional[str] = None) -> Dict:
                 rrule=args.get("rrule", "") or "",
                 event_type=event_type,
                 importance=importance,
+                caldav_sync_pending="create" if cal.source == "caldav" else None,
             )
             db.add(ev)
             reminder_note_id = None
@@ -1836,6 +1848,8 @@ async def do_manage_calendar(content: str, owner: Optional[str] = None) -> Dict:
                     dtstart_is_utc and not all_day,
                 )
             db.commit()
+            if cal.source == "caldav":
+                await _push_caldav_event_after_commit(owner, uid, "create")
             tag_blurb = f" [{event_type}]" if event_type else ""
             if minutes_before is None:
                 reminder_blurb = ""
@@ -1893,7 +1907,12 @@ async def do_manage_calendar(content: str, owner: Optional[str] = None) -> Dict:
                 ev.event_type = _tag or None
             if args.get("importance") is not None:
                 ev.importance = args["importance"]
+            is_caldav = ev.calendar and ev.calendar.source == "caldav"
+            if is_caldav:
+                ev.caldav_sync_pending = "update"
             db.commit()
+            if is_caldav:
+                await _push_caldav_event_after_commit(owner, base_uid, "update")
             return {"response": f"Updated event {uid}", "exit_code": 0}
 
         elif action == "delete_event":
@@ -1907,8 +1926,13 @@ async def do_manage_calendar(content: str, owner: Optional[str] = None) -> Dict:
             ev = _event_query().filter(CalendarEvent.uid == base_uid).first()
             if not ev:
                 return {"error": f"Event {uid} not found", "exit_code": 1}
+            is_caldav = ev.calendar and ev.calendar.source == "caldav" and ev.remote_href
+            if is_caldav:
+                _record_caldav_delete_tombstone(db, ev, owner)
             db.delete(ev)
             db.commit()
+            if is_caldav:
+                await _push_caldav_event_after_commit(owner, base_uid, "delete")
             return {"response": f"Deleted event {uid}", "exit_code": 0}
 
         else:

src/tool_index.py

@@ -384,6 +384,10 @@ class ToolIndex:
                    "delegate to", "have model"}):
             {"chat_with_model", "ask_teacher", "list_models"},
         # Deep research intent (incl. common typo "reserach")
+        frozenset({"web search", "search the web", "search online", "look up",
+                   "google", "latest", "current", "news", "weather",
+                   "forecast", "stock price", "price of"}):
+            {"web_search", "web_fetch"},
         frozenset({"research", "reserach", "reasearch", "look into", "investigate",
                    "deep dive", "deep research", "find out about", "study up on",
                    "report on", "do research", "look up everything"}):

src/tool_parsing.py

@@ -188,6 +188,12 @@ _MISFENCED_WEB_TOOL_NAMES = {
     "fetch_url": "web_fetch",
 }
 
+_RAW_WEB_JSON_TOOL_RE = re.compile(
+    r"\b(?:web_search|websearch|google_search|google_search_retrieval|google_search_grounding)\b",
+    re.IGNORECASE,
+)
+_RAW_WEB_JSON_ALLOWED_KEYS = {"query", "queries", "time_filter", "freshness", "max_pages"}
+
 
 # ---------------------------------------------------------------------------
 # Parsing functions
@@ -279,6 +285,73 @@ def _parse_misfenced_web_lookup(content: str) -> Optional[ToolBlock]:
         return None
     return ToolBlock("web_fetch", url)
 
+
+def _coerce_raw_web_query(value) -> Optional[str]:
+    if isinstance(value, str) and value.strip():
+        return value.strip()
+    if isinstance(value, list):
+        for item in value:
+            if isinstance(item, str) and item.strip():
+                return item.strip()
+    return None
+
+
+def _raw_web_json_to_tool_block(payload) -> Optional[ToolBlock]:
+    if not isinstance(payload, dict):
+        return None
+    if set(payload) - _RAW_WEB_JSON_ALLOWED_KEYS:
+        return None
+
+    query = _coerce_raw_web_query(payload.get("query"))
+    if not query:
+        query = _coerce_raw_web_query(payload.get("queries"))
+    if not query:
+        return None
+
+    content = {"query": query}
+    for key in ("time_filter", "freshness"):
+        value = payload.get(key)
+        if isinstance(value, str) and value.strip().lower() in ("day", "week", "month", "year"):
+            content[key] = value.strip().lower()
+
+    max_pages = payload.get("max_pages")
+    if isinstance(max_pages, int) and 1 <= max_pages <= 10:
+        content["max_pages"] = max_pages
+
+    if len(content) == 1:
+        return ToolBlock("web_search", query)
+    return ToolBlock("web_search", json.dumps(content))
+
+
+def _parse_raw_web_json_lookup(text: str) -> Optional[tuple[ToolBlock, tuple[int, int]]]:
+    """Recover local text-model web_search calls emitted as prose + bare JSON.
+
+    Some non-native tool models leak the intended call as:
+
+        Need to do web_search for ...
+        {"query": "...", "time_filter": "week"}
+
+    Keep this narrower than fenced/tool markup: it only runs when a known web
+    tool name appears shortly before a JSON object shaped like web_search args.
+    """
+    if not isinstance(text, str):
+        return None
+
+    decoder = json.JSONDecoder()
+    for mention in _RAW_WEB_JSON_TOOL_RE.finditer(text):
+        search_start = mention.end()
+        search_end = min(len(text), search_start + 1200)
+        for brace in re.finditer(r"\{", text[search_start:search_end]):
+            start = search_start + brace.start()
+            try:
+                parsed, end = decoder.raw_decode(text[start:])
+            except json.JSONDecodeError:
+                continue
+            block = _raw_web_json_to_tool_block(parsed)
+            if block:
+                return block, (start, start + end)
+    return None
+
 def _parse_tool_call_block(raw: str) -> Optional[ToolBlock]:
     """Parse a [TOOL_CALL] block into a ToolBlock.
 
@@ -436,6 +509,8 @@ def parse_tool_blocks(text: str, skip_fenced: bool = False) -> List[ToolBlock]:
     3. XML-style <tool_call>/<invoke> blocks
     4. <tool_code> blocks (MiniMax-M2.5 style)
     5. DeepSeek DSML markup (normalized to <invoke> first)
+    6. Non-native local model fallback: prose mentioning web_search followed by
+       bare JSON args, e.g. {"query":"...", "time_filter":"week"}
 
     `skip_fenced`: when True, Pattern 1 (fenced ```bash/```python/```json code
     blocks) is not matched at all. Native function-calling models (GPT/Claude/
@@ -509,6 +584,12 @@ def parse_tool_blocks(text: str, skip_fenced: bool = False) -> List[ToolBlock]:
             if block:
                 blocks.append(block)
 
+    # Pattern 6: local text-model web_search call leaked as prose + bare JSON.
+    if not blocks and not skip_fenced:
+        raw_web_json = _parse_raw_web_json_lookup(text)
+        if raw_web_json:
+            blocks.append(raw_web_json[0])
+
     return blocks
 
 
@@ -532,6 +613,11 @@ def strip_tool_blocks(text: str, skip_fenced: bool = False) -> str:
     cleaned = _TOOL_CALL_RE.sub('', cleaned)
     cleaned = _XML_TOOL_CALL_RE.sub('', cleaned)
     cleaned = _TOOL_CODE_RE.sub('', cleaned)
+    if not skip_fenced:
+        raw_web_json = _parse_raw_web_json_lookup(cleaned)
+        if raw_web_json:
+            _, (start, end) = raw_web_json
+            cleaned = cleaned[:start] + cleaned[end:]
     # Strip bare <invoke> blocks not wrapped in <tool_call>
     cleaned = re.sub(r'<invoke\s+name=["\'].*?</invoke>', '', cleaned, flags=re.DOTALL | re.IGNORECASE)
     cleaned = re.sub(r'\n{3,}', '\n\n', cleaned)

src/tool_security.py

@@ -177,13 +177,16 @@ def owner_is_admin_or_single_user(owner: Optional[str]) -> bool:
     defense-in-depth for callers that bypass it (e.g. trusted loopback).
     """
     try:
+        from src.auth_helpers import _auth_disabled
+
+        if _auth_disabled():
+            return True
+
         from core.auth import AuthManager
 
         auth = AuthManager()
         if not auth.is_configured:
-            from src.auth_helpers import _auth_disabled
+            return False
-
-            return _auth_disabled()
         return bool(owner and auth.is_admin(owner))
     except Exception as exc:
         logger.warning("Unable to evaluate owner admin status: %s", exc)

src/youtube_handler.py

@@ -1,278 +1,23 @@
-"""
+"""Compatibility wrapper for the canonical services.youtube.youtube_handler module.
-YouTube handling — transcript extraction, comment fetching (yt-dlp),
+
-and context formatting for LLM injection. Used by chat_handler.py.
+Odysseus historically carried two independent copies of the YouTube handler —
+one here under ``src`` and one under ``services.youtube``. They drifted: the
+comment-fetch timeout fix landed only in the ``src`` copy, while ``app.py``
+calls ``services.youtube.init_youtube()`` at startup. Because the chat flow
+imported ``extract_transcript_async`` from ``src.youtube_handler`` (a different
+module object), the ``YOUTUBE_AVAILABLE`` / ``YouTubeTranscriptApi`` globals set
+by ``init_youtube`` never reached it and transcript extraction always reported
+"YouTube transcript API not available".
+
+Keep the old ``src.youtube_handler`` import path working, but make it resolve to
+the single source of truth so module state and behavior can't diverge again.
 """
 
-import asyncio
+import importlib
-import json
-import logging
-import shutil
 import sys
-import urllib.parse
-from pathlib import Path
-from typing import Dict, Any, Optional
 
-logger = logging.getLogger(__name__)
+# Import the canonical module directly (services.youtube.youtube_handler)
+# without triggering the heavy services/__init__.py top-level imports.
+_youtube_handler = importlib.import_module("services.youtube.youtube_handler")
 
-# ---------------------------------------------------------------------------
+sys.modules[__name__] = _youtube_handler
-# Constants
-# ---------------------------------------------------------------------------
-
-YOUTUBE_INSTRUCTION_PROMPT = """When the user shares a YouTube video, respond with a structured breakdown:
-
-1. **Summary** — Concise overview of the video's content and main thesis (2-4 sentences)
-2. **Key Points** — Bullet list of the most important topics, arguments, or moments
-3. **Notable Timestamps** — If timestamps are available from the transcript, highlight 3-5 interesting moments with their approximate timestamps (e.g. "03:45 — discusses X")
-4. **Audience Reception** — If comments are available, summarize what viewers think: general sentiment, top reactions, any debate or controversy
-
-Keep it conversational and concise. Do NOT web search for this video — use only the transcript and comments provided."""
-
-# ---------------------------------------------------------------------------
-# Init / helpers
-# ---------------------------------------------------------------------------
-
-# Will be set at startup by init_youtube()
-YouTubeTranscriptApi = None
-YOUTUBE_AVAILABLE = False
-
-
-def _find_ytdlp() -> str:
-    """Find the yt-dlp binary: venv bin first, then system PATH."""
-    venv_bin = Path(sys.executable).parent / "yt-dlp"
-    if venv_bin.exists():
-        return str(venv_bin)
-    found = shutil.which("yt-dlp")
-    return found or "yt-dlp"
-
-
-def init_youtube():
-    """Import and cache the YouTube transcript API."""
-    global YouTubeTranscriptApi, YOUTUBE_AVAILABLE
-    try:
-        from youtube_transcript_api import YouTubeTranscriptApi as _Api
-        YouTubeTranscriptApi = _Api
-        YOUTUBE_AVAILABLE = True
-        logger.info("YouTube transcript API available")
-    except ImportError as e:
-        logger.warning(f"youtube-transcript-api not installed: {e}")
-        YOUTUBE_AVAILABLE = False
-
-
-def is_youtube_url(url: str) -> bool:
-    if not isinstance(url, str):
-        return False
-    return "youtube.com" in url or "youtu.be" in url
-
-
-def extract_youtube_id(url: str) -> Optional[str]:
-    """Extract YouTube video ID from various URL formats."""
-    parsed = urllib.parse.urlparse(url)
-    if parsed.hostname in ("www.youtube.com", "youtube.com", "m.youtube.com"):
-        if parsed.path == "/watch":
-            params = urllib.parse.parse_qs(parsed.query)
-            if "v" in params:
-                return params["v"][0]
-        elif parsed.path.startswith("/embed/"):
-            return parsed.path.split("/")[-1]
-    elif parsed.hostname == "youtu.be":
-        return parsed.path[1:]
-    return None
-
-
-async def extract_transcript_async(
-    url: str, video_id: str, max_retries: int = 3
-) -> Dict[str, Any]:
-    """
-    Async YouTube transcript extraction with retries.
-
-    Args:
-        url: Full YouTube URL
-        video_id: Extracted video ID
-        max_retries: Number of attempts
-
-    Returns:
-        Dict with success/error/transcript keys
-    """
-    if not YOUTUBE_AVAILABLE or YouTubeTranscriptApi is None:
-        return {"success": False, "error": "YouTube transcript API not available", "transcript": None}
-
-    for attempt in range(max_retries):
-        try:
-            api = YouTubeTranscriptApi()
-            transcript = api.fetch(video_id)
-            transcript_list = list(transcript)
-
-            formatted = []
-            for snippet in transcript_list:
-                text = snippet.text.strip()
-                if not text:
-                    continue
-                start = snippet.start
-                formatted.append({
-                    "text": text,
-                    "start": start,
-                    "duration": snippet.duration,
-                    "timestamp": f"{int(start // 60):02d}:{int(start % 60):02d}",
-                })
-
-            full_text = " ".join(e["text"] for e in formatted)
-            max_len = 8000
-            if len(full_text) > max_len:
-                full_text = full_text[:max_len] + "... [transcript truncated]"
-
-            return {
-                "success": True,
-                "transcript": full_text,
-                "video_id": video_id,
-                "language": "en",
-                "is_generated": False,
-                "segments": formatted,
-            }
-        except Exception as e:
-            logger.warning(f"Transcript attempt {attempt + 1} failed: {e}")
-            if attempt < max_retries - 1:
-                await asyncio.sleep(1 * (attempt + 1))
-
-    return {"success": False, "error": f"Failed after {max_retries} attempts", "transcript": None}
-
-
-def format_transcript_for_context(
-    transcript_data: Dict[str, Any], url: str,
-    title: str = "", channel: str = ""
-) -> str:
-    """Format transcript data for inclusion in LLM context."""
-    if not transcript_data.get("success"):
-        header = ""
-        if title:
-            header = f" \"{title}\""
-            if channel:
-                header += f" by {channel}"
-        return f"\n[YouTube Video{header}: Transcript unavailable ({transcript_data.get('error', 'Unknown error')}). Use the comments below if available, do NOT web search for this video.]"
-
-    transcript = transcript_data.get("transcript", "")
-    video_id = transcript_data.get("video_id", "")
-    language = transcript_data.get("language", "unknown")
-    is_generated = transcript_data.get("is_generated", False)
-    segments = transcript_data.get("segments", [])
-
-    ctx = "\n[YOUTUBE VIDEO TRANSCRIPT]\n"
-    if title:
-        ctx += f"Title: {title}\n"
-    if channel:
-        ctx += f"Channel: {channel}\n"
-    ctx += f"Video ID: {video_id}\n"
-    ctx += f"Language: {language}\n"
-    ctx += f"Source: {'Auto-generated' if is_generated else 'Manual'}\n"
-    ctx += f"URL: {url}\n\n"
-    # Include timestamped segments for the LLM to reference
-    if segments:
-        ctx += "Timestamped Transcript:\n"
-        for seg in segments:
-            if not isinstance(seg, dict):
-                continue
-            ctx += f"[{seg['timestamp']}] {seg['text']}\n"
-        # Check length — fall back to plain text if too long
-        if len(ctx) > 12000:
-            ctx = ctx[:ctx.index("Timestamped Transcript:\n")]
-            ctx += "Transcript:\n"
-            ctx += transcript
-    else:
-        ctx += "Transcript:\n"
-        ctx += transcript
-    ctx += "\n[END TRANSCRIPT]\n"
-    return ctx
-
-
-async def fetch_youtube_comments(
-    video_id: str, max_comments: int = 25, timeout: int = 30
-) -> Dict[str, Any]:
-    """Fetch top comments for a YouTube video using yt-dlp.
-
-    Returns dict with 'success', 'comments' list, 'error'.
-    """
-    try:
-        cmd = [
-            _find_ytdlp(),
-            "--skip-download",
-            "--write-comments",
-            "--extractor-args", f"youtube:max_comments={max_comments},all,100,0",
-            "--dump-json",
-            "--js-runtimes", "node",
-            "--remote-components", "ejs:github",
-            f"https://www.youtube.com/watch?v={video_id}",
-        ]
-
-        proc = await asyncio.create_subprocess_exec(
-            *cmd,
-            stdout=asyncio.subprocess.PIPE,
-            stderr=asyncio.subprocess.PIPE,
-        )
-        # Bound the wait on the process actually finishing, not on spawning it.
-        # create_subprocess_exec returns as soon as the child starts, so wrapping
-        # it in wait_for never enforces the timeout — proc.communicate() is the
-        # blocking step. Kill and reap the child if it overruns so it does not
-        # linger after we return.
-        try:
-            stdout, stderr = await asyncio.wait_for(
-                proc.communicate(), timeout=timeout
-            )
-        except asyncio.TimeoutError:
-            proc.kill()
-            await proc.wait()
-            raise
-
-        if proc.returncode != 0:
-            return {"success": False, "error": f"yt-dlp failed: {stderr.decode()[:200]}", "comments": []}
-
-        data = json.loads(stdout.decode())
-        title = data.get("title", "")
-        channel = data.get("channel", "") or data.get("uploader", "")
-        raw_comments = data.get("comments", [])
-
-        comments = []
-        for c in raw_comments[:max_comments]:
-            text = (c.get("text") or "").strip()
-            if not text:
-                continue
-            comments.append({
-                "author": c.get("author", "Unknown"),
-                "text": text,
-                "likes": c.get("like_count", 0),
-            })
-
-        # Sort by likes descending — most popular comments first
-        comments.sort(key=lambda x: x.get("likes", 0), reverse=True)
-
-        return {"success": True, "comments": comments, "count": len(comments),
-                "title": title, "channel": channel}
-
-    except asyncio.TimeoutError:
-        logger.warning(f"Comment fetch timed out for {video_id}")
-        return {"success": False, "error": "Comment fetch timed out", "comments": []}
-    except FileNotFoundError:
-        logger.warning("yt-dlp not installed — cannot fetch comments")
-        return {"success": False, "error": "yt-dlp not installed", "comments": []}
-    except Exception as e:
-        logger.warning(f"Failed to fetch comments for {video_id}: {e}")
-        return {"success": False, "error": str(e), "comments": []}
-
-
-def format_comments_for_context(comments_data: Dict[str, Any], url: str) -> str:
-    """Format YouTube comments for inclusion in LLM context."""
-    if not comments_data.get("success") or not comments_data.get("comments"):
-        return ""
-
-    comments = comments_data["comments"]
-    ctx = f"\n[YOUTUBE VIDEO COMMENTS — Top {len(comments)} by popularity]\n"
-    ctx += f"URL: {url}\n\n"
-
-    for i, c in enumerate(comments, 1):
-        likes = c.get("likes", 0)
-        likes_str = f" [{likes} likes]" if likes else ""
-        ctx += f"{i}. @{c['author']}{likes_str}: {c['text']}\n\n"
-
-    if len(ctx) > 4000:
-        ctx = ctx[:4000] + "\n[Comments truncated]\n"
-
-    ctx += "[END COMMENTS]\n"
-    return ctx

start-macos.sh

@@ -130,11 +130,12 @@ fi
 # 3. Python environment + dependencies (kept inside the repo, in venv/).
 #    Named `venv` to match the manual steps and build-macos-app.sh, so the
 #    clickable .app reuses this same environment.
-if [ ! -d venv ]; then
+VENV_PY="./venv/bin/python3"
+if [ ! -x "$VENV_PY" ] || ! "$VENV_PY" -m pip --version >/dev/null 2>&1; then
+    [ -d venv ] && { echo "▶ Existing venv is incomplete (no working pip) — rebuilding…"; rm -rf venv; }
     echo "▶ Creating Python environment…"
     "$PY" -m venv venv
 fi
-VENV_PY="./venv/bin/python3"
 REQ_HASH="$(md5 -q requirements.txt 2>/dev/null || md5sum requirements.txt | cut -d' ' -f1)"
 REQ_HASH_FILE="venv/.requirements_hash"
 if [ ! -f "$REQ_HASH_FILE" ] || [ "$REQ_HASH" != "$(cat "$REQ_HASH_FILE" 2>/dev/null)" ]; then

static/app.js

@@ -3135,7 +3135,9 @@ function initializeEventListeners() {
       setTimeout(() => uiModule.autoResize(textarea), 1);
     });
     textarea.addEventListener('keydown', (e) => {
-      if (e.key === 'Enter' && !e.shiftKey && !e.isComposing) {
+      const isMobile = window.innerWidth <= 768
+
+      if (e.key === 'Enter' && !e.shiftKey && !e.isComposing && !isMobile) {
         // If ghost autocomplete is active, accept the suggestion instead of submitting
         if (window._ghostAutocomplete && window._ghostAutocomplete.isActive()) {
           e.preventDefault();
@@ -3708,7 +3710,9 @@ function startOdysseusApp() {
   // Enter to send (shift+enter for newline), or new chat when empty
   if (messageInput) {
     messageInput.addEventListener('keydown', (e) => {
-      if (e.key === 'Enter' && !e.shiftKey && !e.isComposing) {
+      const isMobile = window.innerWidth <= 768
+
+      if (e.key === 'Enter' && !e.shiftKey && !e.isComposing && !isMobile) {
         e.preventDefault();
         // Flush the debounced icon update so dataset.mode reflects the current
         // text state. Without this, a fast type-and-Enter would still see the

static/index.html

@@ -12,7 +12,7 @@
        in email bodies — was wrapping random digits in <a href="tel:..."> with
        browser-default styling that didn't match the Odysseus theme. -->
   <meta name="format-detection" content="telephone=no, date=no, address=no, email=no">
-  <link rel="apple-touch-icon" href="/static/icon-192.png">
+  <link rel="apple-touch-icon" href="/static/icons/icon-192.png">
   <script nonce="{{CSP_NONCE}}">
   window._odysseusLoadTime = Date.now();
   (function(){
@@ -2232,6 +2232,61 @@
         <!-- ═══ SYSTEM TAB ═══ -->
         <div data-settings-panel="system" class="hidden">
 
+          <div class="admin-card" id="settings-system-logs-card">
+            <h2>
+              <svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="settings-system-logs-svg">
+                <polyline points="4 17 10 11 4 5"></polyline>
+                <line x1="12" y1="19" x2="20" y2="19"></line>
+              </svg>
+              Terminal Logs
+            </h2>
+            <div class="admin-toggle-sub settings-system-logs-toggle-sub">Live diagnostic logs and system output from the Odysseus process.</div>
+
+            <div class="settings-col settings-system-logs-col">
+              <!-- Controls row -->
+              <div class="settings-system-logs-controls">
+                <!-- Search input -->
+                <input type="text" id="log-search-input" placeholder="Search logs..." class="settings-system-logs-search">
+
+                <!-- Level select -->
+                <select id="log-level-select" class="settings-system-logs-select">
+                  <option value="ALL">All Levels</option>
+                  <option value="INFO">INFO</option>
+                  <option value="WARNING">WARNING</option>
+                  <option value="ERROR">ERROR</option>
+                  <option value="DEBUG">DEBUG</option>
+                </select>
+
+                <!-- Limit select -->
+                <select id="log-limit-select" class="settings-system-logs-select">
+                  <option value="100">100 lines</option>
+                  <option value="200" selected>200 lines</option>
+                  <option value="500">500 lines</option>
+                  <option value="1000">1000 lines</option>
+                </select>
+
+                <!-- Refresh Button -->
+                <button type="button" class="admin-btn-sm" id="log-refresh-btn">
+                  <svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="settings-system-logs-refresh-svg"><path d="M21.5 2v6h-6M21.34 15.57a10 10 0 1 1-.57-8.38l5.67-5.67"/></svg>
+                  Refresh
+                </button>
+
+                <!-- Auto-refresh switch -->
+                <div class="settings-system-logs-autopoll-container">
+                  <label class="admin-switch" title="Auto-polling every 3 seconds">
+                    <input type="checkbox" id="log-auto-refresh-toggle">
+                    <span class="admin-slider"></span>
+                  </label>
+                  <span>Auto-poll</span>
+                </div>
+              </div>
+
+              <!-- Console container -->
+              <div id="log-console-container">
+                <div class="settings-system-logs-placeholder">Initializing logs terminal viewer...</div>
+              </div>
+            </div>
+          </div>
           <div class="admin-card">
             <h2><svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" style="vertical-align:-2px;margin-right:5px;opacity:0.6"><path d="M21 15v4a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2v-4"/><polyline points="17 8 12 3 7 8"/><line x1="12" y1="3" x2="12" y2="15"/></svg>Data Backup</h2>
             <div class="admin-toggle-sub" style="margin-bottom:8px">Export or import your user data (memories, presets, settings, skills, preferences) as a JSON file.</div>

static/js/admin.js

@@ -55,6 +55,7 @@ async function loadUsers() {
           </div>
         </div>
         <div style="display:flex;gap:8px;align-items:center;">
+          <button class="admin-btn-sm" data-adm-toggle-admin="${esc(u.username)}" data-make-admin="${u.is_admin ? '0' : '1'}" style="font-size:11px;">${u.is_admin ? 'Revoke admin' : 'Make admin'}</button>
           <button class="admin-btn-sm" data-adm-rename-user="${esc(u.username)}" style="font-size:11px;">Rename</button>
           ${u.is_admin ? '' : `<button class="admin-btn-delete" data-adm-del-user="${esc(u.username)}" style="font-size:11px;">Remove</button>`}
           ${u.is_admin ? '' : '<svg class="admin-user-chevron" width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2.5" stroke-linecap="round" stroke-linejoin="round" style="opacity:0.3;transition:transform 0.2s,opacity 0.2s;"><polyline points="6 9 12 15 18 9"/></svg>'}
@@ -113,7 +114,7 @@ async function loadUsers() {
         // Toggle panel visibility + rotate chevron + load models
         let _modelsLoaded = false;
         header.addEventListener('click', (e) => {
-          if (e.target.closest('.admin-btn-delete, [data-adm-rename-user]')) return;
+          if (e.target.closest('.admin-btn-delete, [data-adm-rename-user], [data-adm-toggle-admin]')) return;
           privPanel.classList.toggle('hidden');
           const chevron = header.querySelector('.admin-user-chevron');
           if (chevron) {
@@ -199,6 +200,42 @@ async function loadUsers() {
         });
       }
 
+      // Promote / demote (admin toggle) — present on every row
+      const adminToggleBtn = row.querySelector('[data-adm-toggle-admin]');
+      if (adminToggleBtn) {
+        adminToggleBtn.addEventListener('click', async (e) => {
+          e.stopPropagation();
+          const username = adminToggleBtn.dataset.admToggleAdmin;
+          const makeAdmin = adminToggleBtn.dataset.makeAdmin === '1';
+          const confirmMsg = makeAdmin
+            ? `Grant admin rights to "${username}"? They'll get full access to all settings and users — including the power to demote or remove other admins (you included).`
+            : `Revoke admin rights from "${username}"? They'll lose access to the admin panel.`;
+          if (!await uiModule.styledConfirm(confirmMsg, { confirmText: makeAdmin ? 'Make admin' : 'Revoke admin', danger: !makeAdmin })) return;
+          adminToggleBtn.disabled = true;
+          try {
+            const res = await fetch(`/api/auth/users/${encodeURIComponent(username)}/admin`, {
+              method: 'PUT',
+              credentials: 'same-origin',
+              headers: { 'Content-Type': 'application/json' },
+              body: JSON.stringify({ is_admin: makeAdmin }),
+            });
+            const data = await res.json().catch(() => ({}));
+            if (!res.ok) {
+              uiModule.showError(data.detail || 'Failed to change admin status');
+              adminToggleBtn.disabled = false;
+              return;
+            }
+            // Demoting yourself drops your own admin access — reload into the
+            // normal-user view (mirrors the rename-self reload above).
+            if (data.self) { window.location.reload(); return; }
+            loadUsers();
+          } catch (err) {
+            uiModule.showError('Failed to change admin status');
+            adminToggleBtn.disabled = false;
+          }
+        });
+      }
+
       list.appendChild(row);
     });
   } catch (e) { list.innerHTML = '<div class="admin-error">Failed to load users</div>'; }
@@ -2488,12 +2525,206 @@ function initDangerZone() {
   });
 }
 
+/* ═══════════════════════════════════════════
+   TERMINAL LOGS VIEWER
+   ═══════════════════════════════════════════ */
+let logsPollInterval = null;
+let isLogsPolling = false;
+let cachedLogs = [];
+let logsAbortController = null;
+
+function renderLogs(isAutoPoll = false) {
+  const consoleContainer = el('log-console-container');
+  const levelSelect = el('log-level-select');
+  const searchInput = el('log-search-input');
+
+  if (!consoleContainer) return;
+
+  const levelFilter = levelSelect ? levelSelect.value : 'ALL';
+  const searchQuery = searchInput ? searchInput.value.trim().toLowerCase() : '';
+
+  let logs = cachedLogs;
+
+  // Filter by level locally
+  if (levelFilter !== 'ALL') {
+    logs = logs.filter(line => line.includes(` - ${levelFilter} - `));
+  }
+
+  // Filter by search query locally
+  if (searchQuery) {
+    logs = logs.filter(line => line.toLowerCase().includes(searchQuery));
+  }
+
+  if (logs.length === 0) {
+    consoleContainer.innerHTML = '<div class="settings-system-logs-placeholder">No logs found matching current filters.</div>';
+    return;
+  }
+
+  // Preserve scroll position if user is reading previous logs
+  const atBottom = consoleContainer.scrollHeight - consoleContainer.scrollTop - consoleContainer.clientHeight < 40;
+
+  consoleContainer.innerHTML = logs.map(line => {
+    let levelClass = 'log-line-default';
+
+    if (line.includes(' - INFO - ')) {
+      levelClass = 'log-line-info';
+    } else if (line.includes(' - WARNING - ')) {
+      levelClass = 'log-line-warning';
+    } else if (line.includes(' - ERROR - ') || line.includes(' - CRITICAL - ')) {
+      levelClass = 'log-line-error';
+    } else if (line.includes(' - DEBUG - ')) {
+      levelClass = 'log-line-debug';
+    }
+
+    // XSS safe escape
+    const escaped = line
+      .replace(/&/g, '&amp;')
+      .replace(/</g, '&lt;')
+      .replace(/>/g, '&gt;')
+      .replace(/"/g, '&quot;')
+      .replace(/'/g, '&#039;');
+
+    return `<div class="log-line ${levelClass}">${escaped}</div>`;
+  }).join('');
+
+  if (!isAutoPoll || atBottom) {
+    consoleContainer.scrollTop = consoleContainer.scrollHeight;
+  }
+}
+
+async function loadLogs(isAutoPoll = false) {
+  const consoleContainer = el('log-console-container');
+  const limitSelect = el('log-limit-select');
+
+  if (!consoleContainer) return;
+
+  const limit = limitSelect ? limitSelect.value : 200;
+
+  if (logsAbortController) {
+    logsAbortController.abort();
+  }
+  logsAbortController = new AbortController();
+  const { signal } = logsAbortController;
+
+  try {
+    const res = await fetch(`/api/diagnostics/logs?limit=${limit}`, {
+      credentials: 'same-origin',
+      signal
+    });
+
+    if (!res.ok) {
+      if (!isAutoPoll) {
+        consoleContainer.innerHTML = '';
+        const errDiv = document.createElement('div');
+        errDiv.style.color = 'var(--red)';
+        errDiv.style.fontWeight = '600';
+        errDiv.textContent = `Failed to load logs: HTTP ${res.status}`;
+        consoleContainer.appendChild(errDiv);
+      }
+      return;
+    }
+
+    const data = await res.json();
+    if (data.status !== 'success' || !data.logs) {
+      if (!isAutoPoll) {
+        consoleContainer.innerHTML = '';
+        const errDiv = document.createElement('div');
+        errDiv.style.color = 'var(--red)';
+        errDiv.style.fontWeight = '600';
+        errDiv.textContent = 'Failed to parse logs data';
+        consoleContainer.appendChild(errDiv);
+      }
+      return;
+    }
+
+    cachedLogs = data.logs;
+    renderLogs(isAutoPoll);
+  } catch (err) {
+    if (err.name === 'AbortError') {
+      return; // Silently ignore deliberate abort
+    }
+    if (!isAutoPoll) {
+      consoleContainer.innerHTML = '';
+      const errDiv = document.createElement('div');
+      errDiv.style.color = 'var(--red)';
+      errDiv.style.fontWeight = '600';
+      errDiv.textContent = `Error retrieving logs: ${err.message}`;
+      consoleContainer.appendChild(errDiv);
+    }
+  } finally {
+    if (logsAbortController?.signal === signal) {
+      logsAbortController = null;
+    }
+  }
+}
+
+function startLogsPolling() {
+  if (isLogsPolling) return;
+  isLogsPolling = true;
+  const toggle = el('log-auto-refresh-toggle');
+  if (toggle) toggle.checked = true;
+
+  logsPollInterval = setInterval(() => {
+    const modal = el('settings-modal');
+    const systemPanel = el('settings-modal')?.querySelector('[data-settings-panel="system"]');
+
+    // Safe self-cleanup if modal or panel is hidden/closed
+    if (!modal || modal.classList.contains('hidden') || !systemPanel || systemPanel.classList.contains('hidden')) {
+      stopLogsPolling();
+      return;
+    }
+
+    loadLogs(true);
+  }, 3000);
+}
+
+function stopLogsPolling() {
+  if (!isLogsPolling) return;
+  isLogsPolling = false;
+  if (logsPollInterval) {
+    clearInterval(logsPollInterval);
+    logsPollInterval = null;
+  }
+  const toggle = el('log-auto-refresh-toggle');
+  if (toggle) toggle.checked = false;
+}
+
+function initLogsView() {
+  const refreshBtn = el('log-refresh-btn');
+  const levelSelect = el('log-level-select');
+  const limitSelect = el('log-limit-select');
+  const searchInput = el('log-search-input');
+  const autoRefreshToggle = el('log-auto-refresh-toggle');
+
+  if (refreshBtn) refreshBtn.addEventListener('click', () => loadLogs(false));
+  if (levelSelect) levelSelect.addEventListener('change', () => renderLogs(false));
+  if (limitSelect) limitSelect.addEventListener('change', () => loadLogs(false));
+  if (searchInput) searchInput.addEventListener('input', () => renderLogs(false));
+
+  if (autoRefreshToggle) {
+    autoRefreshToggle.addEventListener('change', (e) => {
+      if (e.target.checked) {
+        startLogsPolling();
+      } else {
+        stopLogsPolling();
+      }
+    });
+  }
+
+  // Initial fetch on view loading
+  loadLogs(false);
+}
+
 /* ═══════════════════════════════════════════
    INIT & REFRESH
    ═══════════════════════════════════════════ */
 function initAll() {
   modalEl = el('settings-modal');
-  const inits = [initSignupToggle, initAddUser, initEndpointForm, initMcpForm, initCalDAV, initBackup, initDangerZone, initTokenForm, () => settingsModule.initIntegrations()];
+  const inits = [
+    initSignupToggle, initAddUser, initEndpointForm, initMcpForm,
+    initCalDAV, initBackup, initDangerZone, initTokenForm, initLogsView,
+    () => settingsModule.initIntegrations()
+  ];
   for (const fn of inits) {
     try { fn(); } catch (e) { console.error('Admin init error in', fn.name || 'anonymous', e); }
   }
@@ -2507,6 +2738,7 @@ function refreshAll() {
   loadBuiltinTools();
   loadMcpServers();
   loadTokens();
+  loadLogs(false);
 }
 
 /* ═══════════════════════════════════════════
@@ -2523,6 +2755,7 @@ export function open(tab) {
 }
 
 export function close() {
+  stopLogsPolling();
   settingsModule.close();
 }
 

static/js/calendar.js

@@ -9,7 +9,7 @@ import { makeWindowDraggable } from './windowDrag.js';
 import { attachColorPicker } from './colorPicker.js';
 import { bindMenuDismiss } from './escMenuStack.js';
 import {
-  WEEKDAYS, MONTHS, MON_SHORT,
+  WEEKDAYS, WEEKDAYS_SUN, MONTHS, MON_SHORT,
   CAL_PALETTE, CAL_COLORS, _CAL_CUSTOM_GRADIENT, _TYPE_PALETTE,
   _trashIcon, _moreIcon, _bellIcon,
   _isCalBgImage, _calBgImageUrl, _calBgCss,
@@ -64,6 +64,8 @@ let _hiddenTypes = new Set();   // event_type values to hide
 let _onlyImportant = false;
 
 let _filtersCollapsed = localStorage.getItem('cal-filters-collapsed') === '1';
+// Week-start preference: 'mon' (default, Mon=first col) or 'sun' (Sun=first col).
+let _weekStartSun = localStorage.getItem('cal-week-start') === 'sun';
 let _selectedDay = null;
 let _view = 'month';
 let _searchQuery = '';
@@ -360,14 +362,14 @@ function _today() { return _ds(new Date()); }
 function _monthRange(d) {
   const y = d.getFullYear(), m = d.getMonth();
   const first = new Date(y, m, 1);
-  const dow = (first.getDay() + 6) % 7;
+  const dow = _weekStartSun ? first.getDay() : (first.getDay() + 6) % 7;
   const gs = new Date(y, m, 1 - dow);
   const ge = new Date(gs); ge.setDate(gs.getDate() + 42);
   return [_ds(gs), _ds(ge)];
 }
 
 function _weekRange(d) {
-  const dow = (d.getDay() + 6) % 7;
+  const dow = _weekStartSun ? d.getDay() : (d.getDay() + 6) % 7;
   const s = new Date(d); s.setDate(d.getDate() - dow);
   const e = new Date(s); e.setDate(s.getDate() + 7);
   return [_ds(s), _ds(e)];
@@ -928,11 +930,11 @@ async function _renderMonth() {
   _slideDir = 0;
   let h = _headerHTML() + _filtersRowHTML() + `<div class="cal-grid${slideClass}">`;
   h += '<div class="cal-week-headers">';
-  for (const wd of WEEKDAYS) h += `<div class="cal-weekday">${wd}</div>`;
+  for (const wd of (_weekStartSun ? WEEKDAYS_SUN : WEEKDAYS)) h += `<div class="cal-weekday">${wd}</div>`;
   h += '</div>';
 
   const first = new Date(y, m, 1);
-  const dow = (first.getDay() + 6) % 7;
+  const dow = _weekStartSun ? first.getDay() : (first.getDay() + 6) % 7;
   const gs = new Date(y, m, 1 - dow);
 
   const multiDay = _events.filter(e => {
@@ -1141,13 +1143,13 @@ function _wkEventTopHeight(ev, dayStr) {
   // Date math if the string isn't shaped as expected.
   const _toMin = (iso, fallbackDate) => {
     if (!iso) return null;
-    const m = iso.match(/T(\d{2}):(\d{2})/);
+    const mins = _timeToMin(iso);
-    if (m) {
+    if (mins !== null && iso.includes('T')) {
       // If the event spans into a previous/next day, clamp to today's bounds.
-      const evDate = iso.slice(0, 10);
+      const evDate = _localDateOf(iso);
       if (evDate < fallbackDate) return 0;             // event started before today
       if (evDate > fallbackDate) return 24 * 60;       // event ends after today
-      return parseInt(m[1], 10) * 60 + parseInt(m[2], 10);
+      return mins;
     }
     // All-day or date-only — treat as start of day.
     return 0;
@@ -1204,8 +1206,8 @@ async function _renderWeek() {
     const timedEvents  = _eventsForDay(ds).filter(e => _eventVisible(e) && !e.all_day);
 
     const isSun = d.getDay() === 0;
-    colsHtml += `<div class="cal-wk-col${isToday ? ' cal-wk-today' : ''}${isSun ? ' cal-wk-sun' : ''}" data-date="${ds}">`;
+    colsHtml += `<div class="cal-wk-col${isToday ? ' cal-wk-today' : ''}${isSun && !_weekStartSun ? ' cal-wk-sun' : ''}" data-date="${ds}">`;
-    colsHtml += `<div class="cal-wk-col-head"><span class="cal-wk-dn">${WEEKDAYS[idx]}</span><span class="cal-wk-dt">${d.getDate()}</span></div>`;
+    colsHtml += `<div class="cal-wk-col-head"><span class="cal-wk-dn">${(_weekStartSun ? WEEKDAYS_SUN : WEEKDAYS)[idx]}</span><span class="cal-wk-dt">${d.getDate()}</span></div>`;
     // All-day strip
     colsHtml += `<div class="cal-wk-allday">`;
     for (const ev of allDayEvents) {
@@ -1286,12 +1288,17 @@ async function _renderWeek() {
       if (!ev) return;
       const cols = Array.from(body.querySelectorAll('.cal-wk-grid'));
       if (!cols.length) return;
-      // Original timing
+      // Local/display timing
-      const m1 = (ev.dtstart || '').match(/T(\d{2}):(\d{2})/);
+      const startMin0 = _timeToMin(ev.dtstart) ?? 0;
-      const m2 = (ev.dtend || '').match(/T(\d{2}):(\d{2})/);
+      const endMin0   = _timeToMin(ev.dtend) ?? startMin0 + 60;
-      const startMin0 = m1 ? parseInt(m1[1], 10) * 60 + parseInt(m1[2], 10) : 0;
+
-      const endMin0   = m2 ? parseInt(m2[1], 10) * 60 + parseInt(m2[2], 10) : startMin0 + 60;
+      let durationMin = endMin0 - startMin0;
-      const durationMin = Math.max(15, endMin0 - startMin0);
+      const startDs = _localDateOf(ev.dtstart);
+      const endDs = ev.dtend ? _localDateOf(ev.dtend) : startDs;
+      if (endDs > startDs && endMin0 <= startMin0) {
+        durationMin += 24 * 60;
+      }
+      durationMin = Math.max(15, durationMin);
 
       // Where did the cursor grab the block? (offset from block-top in px)
       const blockRect = block.getBoundingClientRect();
@@ -1365,7 +1372,7 @@ async function _renderWeek() {
         // a plain click (no movement) must still open the event.
         if (moved) block.dataset.justResized = '1';
         // Decide whether anything actually moved.
-        const oldDs = (ev.dtstart || '').slice(0, 10);
+        const oldDs = _localDateOf(ev.dtstart);
         if (!nextDs) return;
         if (nextDs === oldDs && nextStartMin === startMin0) return;
         // Snapshot the original times so we can offer an Undo.
@@ -1374,11 +1381,10 @@ async function _renderWeek() {
         const newEndMin = nextStartMin + durationMin;
         const hh = String(Math.floor(nextStartMin / 60)).padStart(2, '0');
         const mm = String(nextStartMin % 60).padStart(2, '0');
-        const hh2 = String(Math.floor(newEndMin / 60)).padStart(2, '0');
+        const newDtstartDate = new Date(`${nextDs}T${hh}:${mm}:00`);
-        const mm2 = String((newEndMin) % 60).padStart(2, '0');
+        const _tz = _tzOffsetForDate(newDtstartDate);
-        const _tz = _tzOffset();
         const newDtstart = `${nextDs}T${hh}:${mm}:00${_tz}`;
-        const newDtend   = `${nextDs}T${hh2}:${mm2}:00${_tz}`;
+        const newDtend = _addMinutesToLocalIso(newDtstart, durationMin);
         try {
           await _updateEvent(uid, { dtstart: newDtstart, dtend: newDtend });
           _render();
@@ -1410,10 +1416,7 @@ async function _renderWeek() {
       const uid = block.dataset.uid;
       const ev = _events.find(x => x.uid === uid);
       if (!ev || !grid || !ds) return;
-      const startMin = (() => {
+      const startMin = _timeToMin(ev.dtstart) ?? 0;
-        const m = (ev.dtstart || '').match(/T(\d{2}):(\d{2})/);
-        return m ? parseInt(m[1], 10) * 60 + parseInt(m[2], 10) : 0;
-      })();
       const initialTop = parseFloat(block.style.top || '0');
       const gridRect = grid.getBoundingClientRect();
       let newEndMin = startMin;
@@ -1438,9 +1441,8 @@ async function _renderWeek() {
         if (resized) block.dataset.justResized = '1';
         if (newEndMin === startMin) return;
         const prevDtend = ev.dtend;
-        const hh = String(Math.floor(newEndMin / 60)).padStart(2, '0');
+        const durationMin = newEndMin - startMin;
-        const mm = String(newEndMin % 60).padStart(2, '0');
+        const newDtend = _addMinutesToLocalIso(ev.dtstart, durationMin);
-        const newDtend = `${ds}T${hh}:${mm}:00${_tzOffset()}`;
         try {
           await _updateEvent(uid, { dtend: newDtend });
           _render();
@@ -1724,9 +1726,9 @@ async function _renderYear() {
   for (let m = 0; m < 12; m++) {
     h += `<div class="cal-year-month" data-month="${m}"><div class="cal-year-month-title">${MON_SHORT[m]}</div>`;
     h += '<div class="cal-year-grid">';
-    for (const wd of ['M', 'T', 'W', 'T', 'F', 'S', 'S']) h += `<div class="cal-year-wd">${wd}</div>`;
+    for (const wd of (_weekStartSun ? ['S','M','T','W','T','F','S'] : ['M','T','W','T','F','S','S'])) h += `<div class="cal-year-wd">${wd}</div>`;
     const first = new Date(y, m, 1);
-    const dow = (first.getDay() + 6) % 7;
+    const dow = _weekStartSun ? first.getDay() : (first.getDay() + 6) % 7;
     const daysInMonth = new Date(y, m + 1, 0).getDate();
     for (let p = 0; p < dow; p++) h += '<div class="cal-year-cell"></div>';
     for (let d = 1; d <= daysInMonth; d++) {
@@ -1966,10 +1968,10 @@ function _wireAll(body) {
             const ad = document.getElementById('cal-f-allday');
             if (ad && !ad.checked) { ad.checked = true; ad.dispatchEvent(new Event('change')); }
           } else {
-            const t1 = (ev.dtstart || '').match(/T(\d{2}:\d{2})/);
+            const t1 = _fmtTime(ev.dtstart);
-            const t2 = (ev.dtend || '').match(/T(\d{2}:\d{2})/);
+            const t2 = _fmtTime(ev.dtend);
-            if (t1) set('cal-f-start', t1[1]);
+            if (t1) set('cal-f-start', t1);
-            if (t2) set('cal-f-end', t2[1]);
+            if (t2) set('cal-f-end', t2);
             document.getElementById('cal-f-start')?.dispatchEvent(new Event('input'));
           }
           // Make sure the details panel is open so the user can verify time.
@@ -2474,6 +2476,13 @@ async function _showCalSettings() {
           </div>
           <div style="font-size:10px;opacity:0.4;margin-top:4px;">Download a calendar as .ics for backup or to import into another app.</div>
         </div>
+        <div style="border-top:1px solid var(--border);padding-top:12px;">
+          <div style="font-size:11px;opacity:0.5;margin-bottom:6px;">Week starts on</div>
+          <div style="display:flex;gap:6px;">
+            <button id="cal-wstart-mon" type="button" style="font-size:12px;padding:3px 10px;border-radius:4px;border:1px solid var(--border);background:${!_weekStartSun ? 'color-mix(in srgb, var(--accent,var(--red)) 18%, var(--panel))' : 'var(--panel)'};color:var(--fg);cursor:pointer;transition:background 0.1s,border-color 0.1s;outline:none;">Monday</button>
+            <button id="cal-wstart-sun" type="button" style="font-size:12px;padding:3px 10px;border-radius:4px;border:1px solid var(--border);background:${_weekStartSun ? 'color-mix(in srgb, var(--accent,var(--red)) 18%, var(--panel))' : 'var(--panel)'};color:var(--fg);cursor:pointer;transition:background 0.1s,border-color 0.1s;outline:none;">Sunday</button>
+          </div>
+        </div>
         <div style="border-top:1px solid var(--border);padding-top:12px;">
           <div style="font-size:11px;opacity:0.5;margin-bottom:6px;">Sync</div>
           <div style="display:flex;gap:8px;align-items:center;flex-wrap:wrap;">
@@ -2494,6 +2503,28 @@ async function _showCalSettings() {
   overlay.querySelector('#cal-settings-close').addEventListener('click', cleanup);
   overlay.addEventListener('click', (e) => { if (e.target === overlay) cleanup(); });
 
+  // Week-start toggle: save to localStorage, update module state, re-render.
+  const _monBtn = overlay.querySelector('#cal-wstart-mon');
+  const _sunBtn = overlay.querySelector('#cal-wstart-sun');
+  const _activeStyle  = 'color-mix(in srgb, var(--accent,var(--red)) 18%, var(--panel))';
+  const _inactiveStyle = 'var(--panel)';
+  const _applyWeekStartActive = () => {
+    if (_monBtn) _monBtn.style.background = _weekStartSun ? _inactiveStyle : _activeStyle;
+    if (_sunBtn) _sunBtn.style.background = _weekStartSun ? _activeStyle : _inactiveStyle;
+  };
+  _monBtn?.addEventListener('click', () => {
+    _weekStartSun = false;
+    localStorage.setItem('cal-week-start', 'mon');
+    _applyWeekStartActive();
+    if (_open) _render();
+  });
+  _sunBtn?.addEventListener('click', () => {
+    _weekStartSun = true;
+    localStorage.setItem('cal-week-start', 'sun');
+    _applyWeekStartActive();
+    if (_open) _render();
+  });
+
   // Create a new (local) calendar. Defaults the name + next palette color, then
   // reopens the panel so the user can rename it inline and pick a color.
   overlay.querySelector('#cal-settings-add')?.addEventListener('click', async (e) => {
@@ -2918,35 +2949,68 @@ function _showEventForm(existing, defaultDate, defaultEndDate) {
     const startEl = document.getElementById('cal-f-start');
     const endEl = document.getElementById('cal-f-end');
     if (!startEl || !endEl) return;
+
     const _toMin = (v) => {
       if (!v || !/^\d{2}:\d{2}$/.test(v)) return null;
       const [h, m] = v.split(':').map(n => parseInt(n, 10));
       return h * 60 + m;
     };
+
     const _toHHMM = (mins) => {
       let m = ((mins % 1440) + 1440) % 1440;
       const hh = String(Math.floor(m / 60)).padStart(2, '0');
       const mm = String(m % 60).padStart(2, '0');
       return `${hh}:${mm}`;
     };
+
+    const _autoAdvanceEndDate = () => {
+      const isAD = document.getElementById('cal-f-allday')?.checked;
+      if (isAD) return;
+
+      const dv = document.getElementById('cal-f-date')?.value;
+      const dvEndEl = document.getElementById('cal-f-date-end');
+      if (!dv || !dvEndEl || dvEndEl.value !== dv) return;
+
+      const sVal = startEl.value;
+      const eVal = endEl.value;
+
+      if (sVal && eVal && eVal <= sVal) {
+        const d = new Date(`${dv}T00:00:00`);
+        d.setDate(d.getDate() + 1);
+
+        dvEndEl.value = _ds(d);
+      }
+    };
+
     let prevStartMin = _toMin(startEl.value);
-    endEl.addEventListener('input', () => { endEl.dataset.userEdited = '1'; });
+
+    endEl.addEventListener('input', () => {
+      endEl.dataset.userEdited = '1';
+    });
+
+    endEl.addEventListener('change', _autoAdvanceEndDate);
+
     startEl.addEventListener('change', () => {
       const newStartMin = _toMin(startEl.value);
       const endMin = _toMin(endEl.value);
-      if (newStartMin == null) { prevStartMin = newStartMin; return; }
+
-      // Compute the duration before the change. Use the user's existing
+      if (newStartMin == null) {
-      // start→end gap, fallback to 1 hour.
-      let durationMin = 60;
-      if (prevStartMin != null && endMin != null && endMin > prevStartMin) {
-        durationMin = endMin - prevStartMin;
-      } else if (endMin != null && newStartMin != null && endMin > newStartMin && endEl.dataset.userEdited === '1') {
-        // User already set a custom end before changing start — leave it.
         prevStartMin = newStartMin;
         return;
       }
+
+      let durationMin = 60;
+
+      if (prevStartMin != null && endMin != null && endMin > prevStartMin) {
+        durationMin = endMin - prevStartMin;
+      } else if (endMin != null && newStartMin != null && endMin > newStartMin && endEl.dataset.userEdited === '1') {
+        prevStartMin = newStartMin;
+        return;
+      }
+
       endEl.value = _toHHMM(newStartMin + durationMin);
       prevStartMin = newStartMin;
+      _autoAdvanceEndDate();
     });
   })();
   // Custom reminder picker
@@ -3007,6 +3071,20 @@ function _showEventForm(existing, defaultDate, defaultEndDate) {
     // proper UTC instants (is_utc=True). Without this, naive "10:00" gets
     // re-interpreted as local elsewhere — the timezone-misfire bug.
     const _tz = _tzOffset();
+    
+    if (!isAD) {
+      const startVal = document.getElementById('cal-f-start').value;
+      const endVal = document.getElementById('cal-f-end').value;
+
+      const startDt = new Date(`${dv}T${startVal}:00`);
+      const endDt = new Date(`${dvEnd}T${endVal}:00`);
+
+      if (endDt <= startDt) {
+        uiModule.showToast('End time must be after start time');
+        return;
+      }
+    }
+
     const payload = {
       summary,
       dtstart: isAD ? dv : `${dv}T${document.getElementById('cal-f-start').value}:00${_tz}`,
@@ -3215,6 +3293,37 @@ function _fmtTime(s) {
   }
   return s.slice(11, 16);
 }
+
+function _timeToMin(iso) {
+  const hm = _fmtTime(iso);
+  if (!hm) return null;
+  const m = hm.match(/^(\d{1,2}):(\d{2})$/);
+  if (!m) return null;
+  const h = parseInt(m[1], 10);
+  const min = parseInt(m[2], 10);
+  if (h < 0 || h > 23 || min < 0 || min > 59) return null;
+  return h * 60 + min;
+}
+
+function _tzOffsetForDate(d) {
+  const off = -d.getTimezoneOffset();
+  const sign = off >= 0 ? '+' : '-';
+  const abs = Math.abs(off);
+  const hh = String(Math.floor(abs / 60)).padStart(2, '0');
+  const mm = String(abs % 60).padStart(2, '0');
+  return `${sign}${hh}:${mm}`;
+}
+
+function _addMinutesToLocalIso(baseIso, addMinutes) {
+  const d = new Date(new Date(baseIso).getTime() + addMinutes * 60000);
+  const y = d.getFullYear();
+  const mo = String(d.getMonth() + 1).padStart(2, '0');
+  const da = String(d.getDate()).padStart(2, '0');
+  const h = String(d.getHours()).padStart(2, '0');
+  const m = String(d.getMinutes()).padStart(2, '0');
+  return `${y}-${mo}-${da}T${h}:${m}:00${_tzOffsetForDate(d)}`;
+}
+
 function _e(s) { return uiModule.esc ? uiModule.esc(s || '') : (s || '').replace(/</g, '&lt;').replace(/>/g, '&gt;').replace(/"/g, '&quot;'); }
 
 // Linkify a location string: URLs become clickable, plain addresses get a Maps link.

static/js/calendar/utils.js

@@ -4,6 +4,8 @@
 // No DOM, no fetch, no global mutable state — safe to import anywhere.
 
 export const WEEKDAYS     = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'];
+export const WEEKDAYS_SUN = ['Sun', 'Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat'];
+
 
 export const MONTHS = ['January', 'February', 'March', 'April', 'May', 'June',
   'July', 'August', 'September', 'October', 'November', 'December'];

static/js/chat.js

@@ -1564,9 +1564,12 @@ import { wireArrowUpRecall, getLastUserMessageFromChatHistory } from './composer
                       .replace(/<channel\|>/gi, '');
                     thinkText = thinkText.replace(/^\s*Thinking(?:\s+Process)?:\s*/i, '');
                     _liveThinkInner.innerHTML = markdownModule.mdToHtml(thinkText);
-                    // Keep thinking box scrolled to bottom
+                    // Keep thinking box scrolled to bottom, but let user scroll up
                     var thinkBox = _liveThinkInner.closest('.thinking-content');
-                    if (thinkBox) thinkBox.scrollTop = thinkBox.scrollHeight;
+                    if (thinkBox) {
+                      var nearBottom = thinkBox.scrollHeight - thinkBox.clientHeight - thinkBox.scrollTop < 80;
+                      if (nearBottom) thinkBox.scrollTop = thinkBox.scrollHeight;
+                    }
                   }
                   uiModule.scrollHistory();
                   continue;
@@ -3865,7 +3868,9 @@ import { wireArrowUpRecall, getLastUserMessageFromChatHistory } from './composer
 
     // Also submit on Enter (without shift)
     editor.addEventListener('keydown', (e) => {
-      if (e.key === 'Enter' && !e.shiftKey && !e.isComposing) {
+      const isMobile = window.innerWidth <= 768
+
+      if (e.key === 'Enter' && !e.shiftKey && !e.isComposing && !isMobile) {
         e.preventDefault();
         saveBtn.click();
       }
@@ -3873,9 +3878,11 @@ import { wireArrowUpRecall, getLastUserMessageFromChatHistory } from './composer
   }
 
   /**
-   * Resend a user message — truncates history to that point and resubmits.
+   * Resend a user message. Normal resend appends a fresh copy at the end of
+   * the current thread; regenerate flows can opt into replacing from here.
    */
-  export async function resendUserMessage(userMsgElement) {
+  export async function resendUserMessage(userMsgElement, opts = {}) {
+    const replaceFromHere = Boolean(opts && opts.replaceFromHere);
     const box = document.getElementById('chat-history');
     const allMsgs = Array.from(box.querySelectorAll('.msg'));
     const msgIndex = allMsgs.indexOf(userMsgElement);
@@ -3921,9 +3928,11 @@ import { wireArrowUpRecall, getLastUserMessageFromChatHistory } from './composer
     const sessionId = sessionModule.getCurrentSessionId();
     if (!sessionId) return;
 
-    // Truncate backend to keep everything before this user message
-    const keepCount = msgIndex;
     try {
+      if (replaceFromHere) {
+        // Regenerate flows intentionally trim history to this point before
+        // resubmitting. The plain "Resend message" action must not do this.
+        const keepCount = msgIndex;
         await fetch(`${API_BASE}/api/session/${sessionId}/truncate`, {
           method: 'POST',
           headers: { 'Content-Type': 'application/json' },
@@ -3940,6 +3949,7 @@ import { wireArrowUpRecall, getLastUserMessageFromChatHistory } from './composer
           sibling = next;
         }
         _hideUserBubble = true;
+      }
       _pendingRegenAttachments = _ids;
 
       // Resubmit
@@ -4473,6 +4483,15 @@ import { wireArrowUpRecall, getLastUserMessageFromChatHistory } from './composer
    * Delete an AI message and its preceding user message from the conversation.
    */
   export async function deleteMessage(msgElement) {
+    if (uiModule && uiModule.styledConfirm) {
+      const ok = await uiModule.styledConfirm('Delete this message?', {
+        confirmText: 'Delete',
+        cancelText: 'Cancel',
+        danger: true,
+      });
+      if (!ok) return;
+    }
+
     const box = document.getElementById('chat-history');
     const allMsgs = Array.from(box.querySelectorAll('.msg'));
     const clickedIndex = allMsgs.indexOf(msgElement);

static/js/chatRenderer.js

@@ -362,7 +362,7 @@ function _openVisionEditor(att, userMsgEl) {
       await _saveVisionText();
       _closeVisionEditor();
       if (userMsgEl && window.chatModule?.resendUserMessage) {
-        window.chatModule.resendUserMessage(userMsgEl);
+        window.chatModule.resendUserMessage(userMsgEl, { replaceFromHere: true });
       } else if (uiModule?.showToast) {
         uiModule.showToast('Saved');
       }

static/js/compare/icons.js

@@ -40,7 +40,7 @@ export const EVAL_PROMPTS = {
   chat: [
     // ── ★ Featured — prompts that have actually broken frontier models ──
     { sub: '★ Featured', label: 'Sum digits 2^100', answer: '115', prompt: 'Compute the sum of the decimal digits of 2^100. Do NOT use code execution — work it out by reasoning about the number. Show every step, then end with the final number on its own line.' },
-    { sub: '★ Featured', label: 'Three jugs',       answer: '4 pours: 7→5, 5→3, 3→7, 5→3', prompt: 'You have three jugs of capacities 7, 5, and 3 liters. The 7-liter jug starts full; the others empty. Using only pouring (no markings), produce the shortest sequence of pours that leaves exactly 2 liters in the 3-liter jug. Output each step as `pour A → B` on its own line. Then state the total number of pours on a final line.' },
+    { sub: '★ Featured', label: 'Three jugs',       answer: '2 pours: 7→5, 7→3', prompt: 'You have three jugs of capacities 7, 5, and 3 liters. The 7-liter jug starts full; the others empty. Using only pouring (no markings), produce the shortest sequence of pours that leaves exactly 2 liters in the 3-liter jug. Output each step as `pour A → B` on its own line. Then state the total number of pours on a final line.' },
 
     { sub: 'Visual',         label: 'Draw SVG',         prompt: 'Output a complete self-contained HTML file (```html block, no explanation, no other text) that centers a single SVG illustration on a simple background. The SVG must use only inline shapes — no <img>, no external assets, no JavaScript. Make it expressive and detailed. The SVG should depict: a friendly robot' },
     { sub: 'Visual explain', label: 'Black hole HTML',  prompt: 'Output a complete HTML file (```html block, no explanation outside the code) that visually explains how a black hole forms. Use four labeled "frames" laid out left-to-right (or stacked on small screens) showing: 1) a glowing massive star, 2) the star going supernova with shockwave rings, 3) collapse into a singularity, 4) the final black hole with a curved accretion disk and bent light around it. Use only vanilla HTML, CSS, and inline SVG — no JavaScript, no images. Each frame should have a one-sentence caption.' },

static/js/cookbook-diagnosis.js

@@ -320,6 +320,15 @@ export const ERROR_PATTERNS = [
       }},
     ],
   },
+  {
+    pattern: /sgl_kernel[\s\S]*(Python\.h|libnuma\.so\.1|common_ops)|(Python\.h|libnuma\.so\.1|common_ops)[\s\S]*sgl_kernel|Please ensure sgl_kernel is properly installed/i,
+    message: 'SGLang native dependencies are missing on this server.',
+    fixes: [
+      { label: 'Copy OS package command', action: () => _copyText('sudo apt-get install -y libnuma-dev python3.12-dev build-essential') },
+      { label: 'Copy kernel upgrade', action: () => _copyText('python3 -m pip install --upgrade sglang-kernel') },
+      { label: 'Open Dependencies', action: () => _openCookbookDependencies('sglang') },
+    ],
+  },
   {
     pattern: /sglang.*command not found|No module named sglang|SGLang is not installed/i,
     message: 'SGLang is not installed or not in PATH.',

static/js/cookbook-hwfit.js

@@ -750,6 +750,80 @@ export async function _hwfitFetch(fresh = false) {
   }
 }
 
+// Renders a non-blocking hardware visibility warning when Cookbook is using
+// container-visible hardware that may not match the user's actual host machine.
+function _renderHwVisibilityWarning(sys) {
+  const row = document.getElementById('hwfit-hw-row');
+  if (!row) return;
+
+  let box = document.getElementById('hwfit-hw-visibility-warning');
+
+  // Manual hardware is an explicit user override, so avoid showing stale
+  // container-detection warnings once the user has chosen a simulated profile.
+  const warning = sys?.manual_hardware ? null : sys?.hardware_visibility_warning;
+
+  if (!warning) {
+    if (box) box.remove();
+    return;
+  }
+
+  if (!box) {
+    box = document.createElement('div');
+    box.id = 'hwfit-hw-visibility-warning';
+    box.className = 'hwfit-loading hwfit-hw-visibility-warning';
+    row.insertAdjacentElement('afterend', box);
+  }
+
+  box.innerHTML = `
+    <div class="hwfit-hw-visibility-warning-title">${esc(warning.title || 'Hardware visibility note')}</div>
+    <div class="hwfit-hw-visibility-warning-body">${esc(warning.message || '')}</div>
+    <div class="hwfit-hw-visibility-warning-actions">
+      <button type="button" class="hwfit-gpu-btn" data-hw-action="manual">Edit manual hardware</button>
+      <button type="button" class="hwfit-gpu-btn" data-hw-action="rescan">Rescan</button>
+      <button type="button" class="hwfit-gpu-btn" data-hw-action="copy">Copy diagnostics</button>
+    </div>
+  `;
+
+  box.querySelector('[data-hw-action="manual"]')?.addEventListener('click', () => {
+    const panel = document.getElementById('hwfit-manual-panel');
+    if (panel) panel.classList.remove('hidden');
+    document.getElementById('hwfit-hw-manual-btn')?.scrollIntoView?.({
+      behavior: 'smooth',
+      block: 'center',
+    });
+  });
+
+  box.querySelector('[data-hw-action="rescan"]')?.addEventListener('click', () => {
+    _resetGpuToggleState();
+    _hwfitCache = null;
+    _hwfitFetch(true);
+  });
+
+  box.querySelector('[data-hw-action="copy"]')?.addEventListener('click', () => {
+    // Keep diagnostics copy/paste friendly for GitHub issues and Docker support.
+    const text = [
+      'Odysseus Cookbook hardware diagnostics',
+      `probe_scope=${sys?.probe_scope || ''}`,
+      `containerized=${sys?.containerized === true}`,
+      `backend=${sys?.backend || ''}`,
+      `has_gpu=${sys?.has_gpu === true}`,
+      `gpu_name=${sys?.gpu_name || ''}`,
+      `gpu_count=${sys?.gpu_count || 0}`,
+      `gpu_vram_gb=${sys?.gpu_vram_gb || ''}`,
+      `ram=${sys?.available_ram_gb || '?'} / ${sys?.total_ram_gb || '?'} GB`,
+      `cpu_cores=${sys?.cpu_cores || ''}`,
+      `cpu_name=${sys?.cpu_name || ''}`,
+      '',
+      'Useful checks:',
+      'docker compose exec odysseus nvidia-smi -L',
+      'docker compose exec odysseus cat /proc/meminfo | head',
+      'docker compose exec odysseus python -c "from services.hwfit.hardware import detect_system; import json; print(json.dumps(detect_system(fresh=True), indent=2))"',
+    ].join('\n');
+
+    _copyText(text);
+  });
+}
+
 export function _hwfitRenderHw(el, sys) {
   if (!el || !sys) return;
   // Cache system info globally so other modules can read VRAM without refetching
@@ -838,6 +912,7 @@ export function _hwfitRenderHw(el, sys) {
     + chip('cores', cores)
     + chip('backend', esc(sys.backend || ''))
     + manualChip;
+  _renderHwVisibilityWarning(sys);
   // Body click → toggle "off" (dimmed, still visible). Membership of
   // _dismissedHwChips is what the ranker reads, so both add+remove
   // here also flips the model list. The manual chip is excluded —

static/js/cookbook.js

@@ -597,7 +597,8 @@ export function _buildServeCmd(f, modelName, backend) {
   } else if (backend === 'diffusers') {
     const gpuStr = f.gpus?.trim();
     if (gpuStr) cmd += `CUDA_VISIBLE_DEVICES=${gpuStr} `;
-    cmd += `python3 scripts/diffusion_server.py --model ${modelName} --port ${f.port || '8100'}`;
+    const diffusersPy = _isWindows() ? 'python' : _py3Bin;
+    cmd += `${diffusersPy} scripts/diffusion_server.py --model ${modelName} --port ${f.port || '8100'}`;
     if (f.diff_dtype && f.diff_dtype !== 'bfloat16') cmd += ` --dtype ${f.diff_dtype}`;
     if (f.diff_device_map && f.diff_device_map !== 'balanced') cmd += ` --device-map ${f.diff_device_map}`;
     if (f.diff_steps) cmd += ` --steps ${f.diff_steps}`;
@@ -718,7 +719,7 @@ async function _fetchDependencies() {
     const data = await resp.json();
     const pkgs = data.packages || [];
     if (!pkgs.length) { list.innerHTML = '<div class="hwfit-loading">No packages found</div>'; return; }
-    const _winUnsupported = new Set(['diffusers', 'hf_transfer', 'vllm', 'rembg', 'gfpgan']);
+    const _winUnsupported = new Set(['hf_transfer', 'vllm', 'rembg', 'gfpgan']);
 
     const _statusTag = (pkg, isLocal, isSystemDep, winBlocked) => {
       if (winBlocked) return `<span class="cookbook-dep-tag cookbook-dep-na">N/A</span>`;

static/js/cookbookRunning.js

@@ -793,9 +793,10 @@ function _winSessionCmd(task, tmuxArgs) {
     return host ? `ssh ${pf}${host} "powershell -Command \\"${ps}\\""` : `powershell -Command "${ps}"`;
   }
   if (tmuxArgs.includes('kill-session')) {
+    const stopTree = `function Stop-Tree([int]$Id) { Get-CimInstance Win32_Process -Filter "ParentProcessId = $Id" -ErrorAction SilentlyContinue | ForEach-Object { Stop-Tree ([int]$_.ProcessId) }; Stop-Process -Id $Id -Force -ErrorAction SilentlyContinue }`;
     const ps = host
-      ? `$p = Get-Content '${sd}\\${sid}.pid' -ErrorAction SilentlyContinue; if ($p) { Stop-Process -Id $p -Force -ErrorAction SilentlyContinue }; Remove-Item '${sd}\\${sid}.*' -Force -ErrorAction SilentlyContinue`
+      ? `${stopTree}; $p = Get-Content '${sd}\\${sid}.pid' -ErrorAction SilentlyContinue; if ($p -match '^\\d+$') { Stop-Tree ([int]$p) }; Remove-Item '${sd}\\${sid}.*' -Force -ErrorAction SilentlyContinue`
-      : `$p = Get-Content (Join-Path $env:TEMP 'odysseus-tmux\\${sid}.pid') -ErrorAction SilentlyContinue; if ($p) { Stop-Process -Id $p -Force -ErrorAction SilentlyContinue }; Remove-Item (Join-Path $env:TEMP 'odysseus-tmux\\${sid}.*') -Force -ErrorAction SilentlyContinue`;
+      : `${stopTree}; $p = Get-Content (Join-Path $env:TEMP 'odysseus-tmux\\${sid}.pid') -ErrorAction SilentlyContinue; if ($p -match '^\\d+$') { Stop-Tree ([int]$p) }; Remove-Item (Join-Path $env:TEMP 'odysseus-tmux\\${sid}.*') -Force -ErrorAction SilentlyContinue`;
     return host ? `ssh ${pf}${host} "powershell -Command \\"${ps}\\""` : `powershell -Command "${ps}"`;
   }
   if (tmuxArgs.includes('send-keys') && tmuxArgs.includes('C-c')) {
@@ -3532,12 +3533,22 @@ async function _pollBackgroundStatus() {
         // dead-session check inspects). Recover "done" from the retained output's
         // exit-0 sentinel so a clean install isn't downgraded to crashed.
         const depDone = !!task.payload?._dep && _depInstallSucceeded(task.output);
+        // A finished model download whose tmux pane is gone is also reported
+        // "stopped" (the dead-session check can miss the landed snapshot).
+        // Recover "done" from the terminal `DOWNLOAD_OK` sentinel — emitted
+        // only after the runner exits 0 — so a completed download isn't
+        // downgraded to crashed. This background poll runs blind (no live
+        // stream to debounce against), so unlike the reconnect loop it keys
+        // off the conclusive exit sentinel only, never the `/snapshots/` path,
+        // which can be printed mid-stream for multi-file downloads.
+        const downloadDone = task.type === 'download'
+          && String(task.output || '').includes('DOWNLOAD_OK');
         const nextStatus = live.status === 'completed'
           ? 'done'
           : (live.status === 'error'
             ? 'error'
             : (live.status === 'stopped'
-                ? (depDone ? 'done' : (task.type === 'download' ? 'crashed' : 'stopped'))
+                ? ((depDone || downloadDone) ? 'done' : (task.type === 'download' ? 'crashed' : 'stopped'))
                 : null));
         if (nextStatus && task.status !== nextStatus) {
           updates.status = nextStatus;

static/js/cookbookServe.js

@@ -530,7 +530,7 @@ function _rerenderCachedModels() {
         : (_lastUsed || (_isLegacyFlat ? _allSs : {}));
       const detectedBackend = _detectBackend(m).backend;
       const _allowedBackends = new Set(_isWindows()
-        ? ['llamacpp']
+        ? ['llamacpp', 'diffusers']
         : (_isMetal() ? ['llamacpp', 'ollama'] : ['vllm', 'sglang', 'llamacpp', 'ollama', 'diffusers']));
       const defaultBackend = (ss._forceBackend && ss.backend && _allowedBackends.has(ss.backend))
         ? ss.backend
@@ -590,7 +590,7 @@ function _rerenderCachedModels() {
       // Row 1: Backend + Server + Env
       panelHtml += `<div class="hwfit-serve-row">`;
       const _backendChoices = _isWindows()
-        ? [['llamacpp','llama.cpp']]
+        ? [['llamacpp','llama.cpp'],['diffusers','Diffusers']]
         : _isMetal()
         // Diffusers (diffusion_server.py) is CUDA-only — omit it on Metal.
         ? [['llamacpp','llama.cpp'],['ollama','Ollama']]

static/js/modalSnap.js

@@ -994,7 +994,7 @@ export function makeEdgeDockController(modal, side = 'right', dockClass) {
   stripe.style.bottom = '0';
   stripe.style.width = '10px';
   stripe.style.cursor = 'col-resize';
-  stripe.style.zIndex = '9999';
+  stripe.style.zIndex = '261';
   stripe.style.background = 'linear-gradient(to right, transparent 0 3px, color-mix(in srgb, var(--accent, var(--red)) 35%, transparent) 3px 7px, transparent 7px 10px)';
   stripe.style.pointerEvents = 'auto';
   stripe.style.touchAction = 'none';

static/js/notes.js

@@ -1099,6 +1099,9 @@ export function openPanel() {
   if (_open) return;
   _open = true;
   _editingId = null;
+  // Reset the search filter — the rebuilt pane's search input renders empty, so a
+  // stale _searchQuery would silently hide non-matching notes after a reopen.
+  _searchQuery = '';
   _clearViewedReminderGlows();
   _firedDotDismissedAt = Date.now();
   try { localStorage.setItem(REMINDER_DISMISSED_AT_KEY, String(_firedDotDismissedAt)); } catch {}

static/js/research/panel.js

@@ -354,7 +354,7 @@ function _buildPanelHTML() {
           <span>Multi-step web research with an LLM-in-the-loop agent</span>
         </p>
         <div id="research-no-past-hint" class="memory-desc doclib-desc" style="display:none;margin-top:-2px;font-size:11px;opacity:0.7;">All past research found in <button type="button" class="research-library-link">Library, Research</button></div>
-        <textarea id="research-query" class="research-query" placeholder="e.g. Trace Odysseus's ten-year journey home from Troy — every island, monster, and detour, and why each one cost him" rows="4"></textarea>
+        <textarea id="research-query" class="research-query" placeholder="e.g. Trace Odysseus's ten-year journey home from Troy — every island, monster, and detour, and what each one cost him." rows="4"></textarea>
         <div class="research-category-row" id="research-category-row">
           <button class="research-cat active" data-cat="" title="LLM auto-detects the best format">Auto</button>
           <button class="research-cat" data-cat="product">Product</button>

static/js/settings.js

@@ -3644,7 +3644,11 @@ async function initUnifiedIntegrations() {
     el('uf-api-cancel').addEventListener('click', () => { formEl.style.display = 'none'; });
     el('uf-api-save').addEventListener('click', async () => {
       const presetKey = preset.value || undefined;
-      const body = { name: name.value, base_url: url.value, auth_type: auth.value, auth_header: header.value, preset: presetKey };
+      const nameValue = name.value.trim();
+      const urlValue = url.value.trim();
+      if (!nameValue) { el('uf-api-msg').textContent = 'Name required'; el('uf-api-msg').style.color = 'var(--red)'; return; }
+      if (!urlValue) { el('uf-api-msg').textContent = 'Base URL required'; el('uf-api-msg').style.color = 'var(--red)'; return; }
+      const body = { name: nameValue, base_url: urlValue, auth_type: auth.value, auth_header: header.value, preset: presetKey };
       if (key.value) body.api_key = key.value;
       try {
         const u = _editId ? `/api/auth/integrations/${_editId}` : '/api/auth/integrations';

static/js/skills.js

@@ -514,6 +514,8 @@ function _buildBuiltinCards() {
 
     card.addEventListener('click', (e) => {
       if (e.target.closest('button, input, textarea')) return;
+      // Editing in progress → don't collapse on an outside-the-textarea click.
+      if (card.querySelector('.skill-md-editor')) return;
       _expandBuiltinCard(card, b.name);
     });
     return card;
@@ -786,6 +788,10 @@ function renderSkillsList() {
     card.addEventListener('click', (e) => {
       if (card._suppressNextClick) { card._suppressNextClick = false; return; }
       if (e.target.closest('button, input, textarea')) return;
+      // While editing, a click on the card body (outside the textarea) must
+      // NOT collapse the card — that silently discards unsaved edits. Only
+      // Save/Cancel exit edit mode.
+      if (card.querySelector('.skill-md-editor')) return;
       if (_selectMode) {
         const cb = card.querySelector('.skill-select-cb');
         if (cb) { cb.checked = !cb.checked; cb.dispatchEvent(new Event('change')); }

static/js/slashCommands.js

@@ -339,10 +339,13 @@ function _submitComposedMessage(text) {
   const msgInput = document.getElementById('message');
   const form = document.getElementById('chat-form');
   if (!msgInput || !form) return false;
+  // The slash handler and app-level form debounce must both release before
+  // sending the pinned prompt, otherwise the follow-up submit is dropped.
+  setTimeout(() => {
     msgInput.value = text;
     msgInput.dispatchEvent(new Event('input', { bubbles: true }));
-  if (typeof form.requestSubmit === 'function') form.requestSubmit();
+    form.dispatchEvent(new Event('submit', { cancelable: true, bubbles: true }));
-  else form.dispatchEvent(new Event('submit', { cancelable: true, bubbles: true }));
+  }, 350);
   return true;
 }