configure anonymous SearXNG provider defaults

.githooks/pre-commit

@@ -0,0 +1,6 @@
+#!/usr/bin/env bash
+# Repository pre-commit hook: run only tests selected by staged paths.
+set -euo pipefail
+
+REPO_ROOT="$(git rev-parse --show-toplevel)"
+exec "$REPO_ROOT/scripts/test-changed.sh"

AGENTS.md

@@ -27,7 +27,7 @@ host.
 | Target | Runtime | Service | Model | Port |
 |--------|---------|---------|-------|------|
 | Dankserver | llama.cpp (upstream b10121) | frank-default-small | HauhauCS Qwen3.6-35B-A3B-Uncensored-Aggressive Q6_K_P + ngram-mod, 36 MoE experts on CPU | 7770 |
-| Dankclaw | charlie12345/ROCmFPX llama.cpp | frank-default-large | kingjones Qwen3.8-27B-ROCmFPX-Q8_0-AGENT Q8_0_ROCMFPX (standalone MTP draft head, Turbo4 V cache, 262K context / 1 slot), reasoning on | 7770 |
+| Dankclaw | charlie12345/ROCmFPX llama.cpp | frank-default-large | kingjones Qwen3.8 Uncensored Q6_0_ROCmFPX_AGENT (standalone MTP draft head, Turbo4 V cache, 262K context / 1 slot), reasoning on | 7770 |
 
 History: the 2026-08-17 redo retired the pipeline-parallel split and the
 FastFlowLM NPU endpoint. The 2026-08-18 swap retired the vLLM service on
@@ -35,8 +35,9 @@ Dankclaw. On 2026-08-21 a DFlash2 Vulkan deployment briefly replaced CIRU,
 then was reverted the same day for speed. On 2026-08-22 the service briefly
 swapped to the Kairic Edge IU4 runtime, then was reverted to v3 the same day
 (operator decision). On 2026-08-25 the service switched to the kingjones
-Qwen3.8-27B-ROCmFPX-Q8_0-AGENT model (standalone MTP draft, 262144 context,
+Qwen3.8-27B-Uncensored-Q6_0-ROCmFPX_AGENT model (standalone MTP draft,
-reasoning on); the previous Kairic Edge model was retired the same day. Runbooks:
+262144 context, reasoning on); the previous Q8_0 AGENT model was retired after
+its `set_rows` crash. Runbooks:
 [docs/LLM/index.md](docs/LLM/index.md).
 Retired scripts live in `old/` (reference only) and `.AGENTTRASH/`.
 
@@ -182,19 +183,22 @@ When you rename a service or move a model to a new host, update
 
 ## Runtime & Troubleshooting
 
-### kingjones Qwen3.8-27B-ROCmFPX-Q8_0-AGENT llama.cpp (Dankclaw, ACTIVE)
+### kingjones Qwen3.8 Uncensored Q6_0 ROCmFPX AGENT llama.cpp (Dankclaw, ACTIVE)
 
-The large service serves `kingjones/Qwen3.8-27B-ROCmFPX-Q8_0-AGENT`
+The large service serves `kingjones/Qwen3.8-Uncensored-ROCmFP4-STRIX-MTP`
-(public) from `/home/dank/models/kingjones-Qwen3.8-27B-ROCMFPX-Q8_0-AGENT/`
+(public) from `/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP/` with a
-with a charlie12345/ROCmFPX `llama-server` (build `build-kairic`). It runs a
+charlie12345/ROCmFPX `llama-server` (build `build-promptforge`). It runs a
 standalone MTP draft head on ROCm0, f16 K + TurboQuant V KV cache, a full
 262144 context / 1 slot, and reasoning on (Sharp template, budget -1,
 `--reasoning-format none`; chat kwargs keep `preserve_thinking` +
-`preserve_reasoning`). The payload (~28 GB main + 1.7 GB draft + 0.9 GB
+`preserve_reasoning`). The Q6_0 main model is 24.86 GB. Env
-mmproj, ~30 GB total) plus the 262k KV cache fit in the lifted 114 GiB TTM/GTT
+`scripts/frank-default-large.env`, serve `scripts/serve-frank-large.sh`, and
-budget (raised 2026-08-25). Env `scripts/frank-default-large.env`, serve
+runbook `docs/LLM/kingjones-q8agent-rocmfpx.md` define the deployment.
-`scripts/serve-frank-large.sh`, runbook
+
-[docs/LLM/kingjones-q8agent-rocmfpx.md](docs/LLM/kingjones-q8agent-rocmfpx.md).
+**Serving status (2026-09-01):** restored the previously deployed Q6_0 AGENT
+model. The Q8_0 AGENT experiment is documented in
+`docs/LLM/kingjones-q8agent-rocmfpx.md`; it was retired because it crashed in
+`ggml_compute_forward_set_rows` and did not provide a working service.
 
 ### charlie12345/ROCmFPX ROCmI4 W4A4 llama.cpp (Dankclaw, prior v3, 2026-08-18 to 2026-08-25)
 

dankclaw/hermes/config.yaml.example

@@ -0,0 +1,55 @@
+# Hermes configuration backup / non-secret baseline.
+#
+# Source on Dankclaw: /home/dank/hermes-data/config.yaml
+# This file is a sanitized Git backup, not a complete replacement for the
+# live Hermes state. Do not add dashboard password hashes, phone numbers,
+# OAuth credentials, API keys, sessions, memories, or generated state here.
+# The live directory is bind-mounted into the containers as /data.
+
+model:
+  provider: custom
+  base_url: http://192.168.0.143:52625/v1
+  api_key: not-needed
+  default: frank-default-large
+
+providers:
+  custom:
+    stale_timeout_seconds: 1800
+    request_timeout_seconds: 1800
+  dankserver-small:
+    api: http://192.168.0.235:7770/v1
+    discover_models: false
+    models:
+      frank-default-small:
+        context_length: 163840
+
+# Auxiliary routing from the live configuration. These use the existing
+# custom endpoint shape and are retained here as a settings backup.
+auxiliary:
+  vision: {provider: custom, model: frank-default-small, base_url: http://192.168.0.235:7770/v1}
+  web_extract: {provider: custom, model: frank-default-small, base_url: http://192.168.0.235:7770/v1}
+  compression: {provider: custom, model: frank-default-small, base_url: http://192.168.0.235:7770/v1}
+  skills_hub: {provider: custom, model: frank-default-small, base_url: http://192.168.0.235:7770/v1}
+  approval: {provider: custom, model: frank-default-small, base_url: http://192.168.0.235:7770/v1}
+  mcp: {provider: custom, model: frank-default-small, base_url: http://192.168.0.235:7770/v1}
+  title_generation: {provider: custom, model: frank-default-small, base_url: http://192.168.0.235:7770/v1}
+  memory_query_rewrite: {provider: custom, model: frank-default-small, base_url: http://192.168.0.235:7770/v1}
+  tts_audio_tags: {provider: custom, model: frank-default-small, base_url: http://192.168.0.235:7770/v1}
+  triage_specifier: {provider: custom, model: frank-default-small, base_url: http://192.168.0.235:7770/v1}
+  kanban_decomposer: {provider: custom, model: frank-default-small, base_url: http://192.168.0.235:7770/v1}
+  profile_describer: {provider: custom, model: frank-default-small, base_url: http://192.168.0.235:7770/v1}
+  curator: {provider: custom, model: frank-default-small, base_url: http://192.168.0.235:7770/v1}
+
+dashboard:
+  # basic_auth intentionally omitted; its password_hash remains live-only.
+  font: atkinson-hyperlegible
+skills:
+  disabled: []
+onboarding:
+  seen:
+    busy_input_prompt: true
+_config_version: 34
+platforms:
+  signal:
+    enabled: true
+    # extra.http_url and account intentionally omitted from the backup.

docs/Architecture/Testing Policy.md

@@ -13,6 +13,28 @@ This repository tests its configuration at defined seams. The tests run with `ba
 | Script syntax | `tests/scripts_syntax.bats` | `bash -n` clean, executable bits, shellcheck when available |
 | Deployment flow | `tests/deployment_flow.bats` | deploy.sh exists, targets known, SSH reachable (skips offline) |
 
+## Focused pre-commit testing
+
+For normal commits, use the focused wrapper:
+
+```bash
+./scripts/test-changed.sh
+```
+
+It reads staged paths with `git diff --cached` and runs only the mapped Bats
+files. The tracked `.githooks/pre-commit` hook invokes this wrapper. Enable the
+repository hook path once per checkout:
+
+```bash
+git config core.hooksPath .githooks
+```
+
+Use `--list` to inspect the selection without running tests, or `--paths FILE
+...` to preview a mapping. Shared test infrastructure and unmapped paths fail
+closed rather than silently skipping coverage. Run the full suite with
+`./tests/run.sh` when changing shared test helpers, the test runner, or when
+focused coverage is not sufficient.
+
 ## Red-Green
 
 Tests are written first. A failing test means the seam is not satisfied; the config change that makes it pass is the only acceptable fix. No `--no-verify`, no deleting tests without approval.

docs/Dankclaw/Hermes-Dashboard.md

@@ -22,7 +22,7 @@ The gateway container runs `hermes gateway run` (the Signal platform). That entr
 
 The dashboard refuses to bind to a non-loopback address without an auth provider. There is no unauthenticated public bind. This repo uses basic auth:
 
-- `dashboard.basic_auth.username` and `dashboard.basic_auth.password_hash` live in the git-ignored `/home/dank/hermes-data/config.yaml`.
+- `dashboard.basic_auth.username` and `dashboard.basic_auth.password_hash` live in the live `/home/dank/hermes-data/config.yaml`; the tracked backup at `dankclaw/hermes/config.yaml.example` intentionally omits the password hash.
 - The stored value is a one-way scrypt hash. The plaintext password is never written to a file or the repo.
 - The hash is generated with `plugins.dashboard_auth.basic.hash_password`.
 

docs/Dankclaw/Hermes.md

@@ -4,6 +4,10 @@ Hermes is the self-improving AI agent from Nous Research. It runs in a terminal,
 
 **Host:** Dankclaw — **Hostname:** `hermes.dankclaw.local` — **Docs:** https://hermes-agent.nousresearch.com/docs
 
+**Persistent state:** `/home/dank/hermes-data` on Dankclaw, mounted as `/data` in
+both containers. The tracked, sanitized configuration baseline is
+[`dankclaw/hermes/config.yaml.example`](../../dankclaw/hermes/config.yaml.example).
+
 ## Facts (from research, primary source)
 
 | Item | Value |
@@ -17,15 +21,20 @@ Hermes is the self-improving AI agent from Nous Research. It runs in a terminal,
 
 ## Configuration
 
-- Point Hermes at the local model endpoint (`http://localhost:7770/v1`) or an external provider through its provider config.
+- Point Hermes at the local model endpoint or an external provider through its provider config.
 - The gateway process exposes one port for chat integration; the exact port is set in the Hermes config (`8090` convention in this repo).
 - The data volume persists skills, memory, and session history.
+- The configured `dankserver-small` provider reaches `http://192.168.0.235:7770/v1`
+  and exposes the `frank-default-small` alias. It is a named provider, so it can
+  coexist with the existing `custom` provider for the large model.
+- The live `config.yaml` contains secrets and user state and is not committed;
+  the tracked example is the sanitized backup of its non-secret settings.
 
 ## Volumes
 
 | Container path | Host path (convention) |
 |----------------|------------------------|
-| `/data` | `/opt/hermes/data` |
+| `/data` | `/home/dank/hermes-data` |
 
 ## Gotchas
 

docs/Dankclaw/SearXNG Providers.md

@@ -15,6 +15,26 @@ engine for an hour to 15 days and silently drops it from results. That is the
 This page is the fixbook. Read [[SearXNG]] for the stack; the sub-pages below
 are the detail if you need it.
 
+## Provider policy
+
+The default aggregation should maximize **independent, anonymous coverage**
+without turning one user query into a request storm. Disabled engines remain
+installed and selectable on demand; `inactive` is reserved for engines that
+should disappear completely.
+
+| Category | Default baseline | On-demand / deferred |
+|----------|------------------|----------------------|
+| General/web | Bing, DuckDuckGo, Wikipedia | Google CSE, Brave, Startpage, Qwant, Mojeek, Wiby, MWMBL after retesting |
+| Technical | GitHub, MDN, Stack Overflow, Ask Ubuntu, Superuser, Docker Hub, PyPI | Other technical indexes as needed |
+| Science | arXiv, PubMed, Semantic Scholar, OpenAlex-compatible sources | Google Scholar until independently tested |
+| News | Reuters, Bing News, DuckDuckGo News, Wikinews | Google News, Brave News, Startpage News |
+| Images | Openverse, Wikimedia Commons, Bing Images, Unsplash | Google/Brave/Startpage image engines |
+| Videos | YouTube, Vimeo, Dailymotion, Bing Videos | Brave video engines |
+
+This policy uses no API credentials and does not identify the operator to a
+search provider. It is deliberately conservative: a bundled engine is not
+necessarily healthy, anonymous, or suitable for every default query.
+
 ## Root cause (one line)
 
 All SearXNG engine traffic shares **one ProtonVPN exit IP** with no rotation, so
@@ -51,6 +71,12 @@ Most "Google is broken on a VPN host" cases are a **mix of both**.
 
 ## Fix A — Engine config (settings.yml `engines:`)
 
+The current tracked policy enables Bing and DuckDuckGo for default general
+search, gives each weight 2, disables pagination, and allows 5 seconds for the
+VPN path. CAPTCHA/429-prone Google, Brave, and Startpage families are retained
+but disabled from default aggregation. This limits fan-out while preserving
+explicit/on-demand selection.
+
 Important: SearXNG's engines are configured in the **`engines:` list inside
 `settings.yml`**, not a separate `engines.yml` file. With
 `use_default_settings: true` (our setting) your `engines:` list is *merged* over
@@ -137,12 +163,12 @@ Tune the `outgoing` block and the suspend model to survive load:
 
 ```yaml
 outgoing:
-  request_timeout: 6.0             # raise from 2.0 so slow engines aren't dropped as unresponsive
+  request_timeout: 4.0             # current Dankclaw value; modest VPN-latency allowance
-  max_request_timeout: 15.0
+  max_request_timeout: 12.0
-  pool_connections: 200            # bigger pool = more concurrent connections per engine host
+  pool_connections: 100
-  pool_maxsize: 40                 # keep-alive connections per host
+  pool_maxsize: 20
-  enable_http2: true               # multiplexing = fewer distinct "new connection" events per engine
+  enable_http2: true
-  retries: 3                       # on 429/5xx, retry against a different proxy + source IP
+  retries: 1                       # avoid amplifying 429/CAPTCHA responses from one exit IP
   useragent_suffix: "ops@yourhomelab.example"   # so a per-engine blocker can reach you
 
 search:
@@ -159,8 +185,12 @@ Notes:
   that is a historical-searx concept. The functional equivalent is the suspend
   schedule above (widen to back off before blocking, narrow to recover faster).
 - `request_timeout` interacts with the suspend model: too tight → engines look
-  "unresponsive"; too loose → slow pages. Aim per-engine `timeout` at
+  "unresponsive"; too loose → slow pages. Dankclaw uses 4 seconds globally and
-  *proxy-add-on time + engine latency*, capped by `max_request_timeout`.
+  12 seconds as the cap; raise it only when measurements show real upstream
+  latency rather than 429/CAPTCHA responses.
+- Keep retries low: retrying a 429/CAPTCHA through the same VPN exit can make the
+  provider's rate limit worse. A retry count of 1 is a bounded compromise for a
+  transient network failure.
 - `safe_search: 0` when diagnosing — a too-strict global safe search can make an
   engine return zero rows and *look* blocked.
 
@@ -226,6 +256,39 @@ gateway.
 > containers/systemd/<unit>.container` `Environment` to inject names into the
 > tunnel's `/etc/hosts`.
 
+## Observed Dankclaw baseline (2026-08-25)
+
+The read-only audit found:
+
+- SearXNG image: `ghcr.io/searxng/searxng:latest`; embedded version `1.0.0`.
+- Gluetun uses `VPN_SERVICE_PROVIDER=custom` with a static WireGuard profile;
+  no `SERVER_COUNTRIES`, `SERVER_CITIES`, `SERVER_REGIONS`, or
+  `SERVER_HOSTNAMES` filters are configured.
+- The observed exit was `149.22.88.19` (Seattle, Washington, US).
+- Bing and DuckDuckGo returned results. Mojeek returned no results without an
+  upstream error.
+- `google cse` and Brave were suspended for too many requests; Startpage was
+  suspended for CAPTCHA; Qwant returned CAPTCHA. SearXNG logs also recorded
+  Google's "unusual traffic from your network" response.
+- `/healthz` returned `200 OK`; the SearXNG service and Gluetun service were
+  healthy. This isolates the primary failures to upstream provider handling,
+  not application availability.
+
+This deployment returns the legacy array form for `unresponsive_engines`:
+
+```json
+"unresponsive_engines": [
+  ["brave", "Suspended: too many requests"],
+  ["startpage", "Suspended: CAPTCHA"]
+]
+```
+
+Do not assume the newer object form (`engine`, `error_type`, `suspended`)
+until the live response has been checked. The direct published port is the
+useful diagnostic path because it exercises the ProtonVPN exit. The Caddy
+hostname resolved to the WAN address during the audit and timed out from the
+audit host, so it was not used as the baseline path.
+
 ## Fix D — Verify an engine is unblocked
 
 Three layers, cheapest first. All queries should hit the path production uses
@@ -242,11 +305,11 @@ curl -s "$BASE/search?q=test&engines=google&format=json" \
 
 Inspect:
 - `content[].engine` — which engine produced each result.
-- `unresponsive_engines[]` — `{engine, error_type, suspended}`. `error_type`
+- `unresponsive_engines[]` — inspect the live shape first. On Dankclaw it is
-  tells you *why* (`SearxEngineTooManyRequests`, `SearxEngineCaptcha`,
+  `[engine, message]`, for example `["google cse", "Suspended: too many requests"]`.
-  `timeout`, `SearxEngineAccessDenied`); `suspended: true` = auto-banned right
+  Newer builds may return objects containing `engine`, `error_type`, and
-  now.
+  `suspended`.
-- `timings[].engine` — per-engine latency.
+- `timings[].engine` — per-engine latency when the running build emits timings.
 
 Full status check (bash + jq):
 
@@ -285,16 +348,23 @@ misleading).
 
 ## Recommended path for Dankclaw (ranked)
 
-1. **Verify first** — `/json` + `?engines=google` and the searx-checker to see
+1. **Measure individual engines** — use `/json` + `?engines=<name>` and several
+   query classes before enabling a bundled engine in default aggregation.
+2. **Keep default fan-out small** — prefer independent anonymous providers and
+   disable pagination for rate-sensitive engines.
+3. **Promote by evidence** — raise `weight` only for engines that return useful
+   results consistently; weight is not a health check.
+4. **Avoid credentials** — do not add API-backed engines unless the provider is
+   genuinely free, anonymous, and compatible with our privacy requirements.
+5. **Verify first** — `/json` + `?engines=google` and the searx-checker to see
    exactly which engines are down and why. Confirm the running SearXNG version
    (check whether `parsers`/`rate_limit` exist in the pinned build).
-2. **Tighten Fix B** — raise `outgoing.request_timeout`, add `retry_on_http_error:
+6. **Use conservative request tuning** — Dankclaw now allows 5 seconds per
-   [403, 429]` on the Google engines, widen `suspended_times`. Cheapest, no new
+   upstream request, caps it at 15 seconds, and retries once. This addresses
-   infra.
+   modest VPN latency without multiplying 429/CAPTCHA traffic. Adjust only
-3. **Duplicate the Google engines** (Fix A) so a CAPTCHA ban on one leaves the
+   after measuring the resulting error and latency profile.
-   other returning results.
+7. **If Google still re-blocks** — Fix C Option 1: point the Google engines at
-4. **If Google still re-blocks** — Fix C Option 1: point the Google engines at a
+   a dedicated-IP proxy (Option 2 dedicated second Gluetun if reputation
-   dedicated-IP proxy (Option 2 dedicated second Gluetun if reputation
    isolation is needed). Avoid the same-netns-proxy trap.
 
 ---

docs/Dankclaw/SearXNG.md

@@ -61,9 +61,29 @@ valkey:
   url: "valkey://searxng-valkey:6379/0"
 
 outgoing:
-  request_timeout: 3.0
+  request_timeout: 5.0
-  max_request_timeout: 10.0
+  max_request_timeout: 15.0
-  retries: 3
+  retries: 1                     # avoid amplifying upstream 429/CAPTCHA responses
+
+# Anonymous, bounded default aggregation. Disabled engines remain configured
+# for explicit/on-demand selection; see SearXNG Providers for the policy.
+engines:
+  - name: bing
+    disabled: false
+    weight: 2
+    paging: false
+    timeout: 5.0
+  - name: duckduckgo
+    disabled: false
+    weight: 2
+    paging: false
+    timeout: 5.0
+  - name: google cse
+    disabled: true
+  - name: brave
+    disabled: true
+  - name: startpage
+    disabled: true
 ```
 
 ## Volumes
@@ -96,10 +116,16 @@ Reach SearXNG through Caddy (`search.dankclaw.local`) for browser use. A local s
 
 ## Unblocking Google & Search Providers
 
-SearXNG queries all ~50 upstream engines from one Gluetun VPN exit IP. The
+The current request policy allows a modest amount of VPN latency (`4.0s` per
-rate-sensitive engines (Google, DuckDuckGo) then answer with reCAPTCHA / 429,
+request, `12.0s` maximum) while limiting retries to one. This can recover slow
-and SearXNG **suspends** the offending engine for hours to days, which is what
+providers, but it cannot fix an upstream CAPTCHA or 429 caused by the shared
-shows up as "Google went unavailable". This is upstream, not local.
+VPN exit IP. SearXNG queries all ~50 upstream engines from one Gluetun VPN exit
+IP. The rate-sensitive engines (Google, DuckDuckGo) then answer with reCAPTCHA / 429.
+The default provider policy therefore favors anonymous Bing and DuckDuckGo,
+disables observed CAPTCHA/429 providers from normal aggregation, and disables
+pagination to reduce upstream request volume. SearXNG **suspends** offending
+engines for hours to days, which is what shows up as "Google went unavailable".
+This is upstream, not local.
 
 Fixes (cheapest first): tune the `outgoing` block (`request_timeout`,
 `retry_on_http_error`, `suspended_times`), duplicate the `google` engine under a

docs/Dankserver/Entropy Volume.md

@@ -0,0 +1,43 @@
+# Entropy Volume
+
+The Dankserver entropy volume is a RAID-backed LUKS filesystem mounted at
+`/mnt/entropy`. The command-line helper reuses the host's desktop-integrated
+`udisks2`, `crypttab`, and `fstab` configuration; it does not store or handle
+the passphrase itself.
+
+## Command-line mount
+
+```bash
+/home/dank/serverAppConfigs/scripts/mount-entropy.sh
+```
+
+Run it as the normal desktop user (`dank`), not from a root shell. `udisksctl`
+will securely prompt for the LUKS passphrase. `sudo mount /mnt/entropy` then
+uses the existing `/etc/fstab` entry, preserving its options:
+
+```text
+nosuid,nodev
+```
+
+The existing mountpoint is owned by `dank:dankserver` with mode `0755`; the
+helper deliberately does not run `chmod` or `chown`, so it cannot silently
+change those permissions.
+
+## Device path
+
+The current storage chain is:
+
+```text
+/dev/md0 -> LUKS UUID cd86c728-459e-4f3a-bcc2-41ecf84685ec
+         -> ext4 label entropy
+         -> /mnt/entropy
+```
+
+The helper checks that `/dev/md0` exists and exits successfully if the volume
+is already mounted. It is intentionally specific to this host and volume:
+that avoids accidentally unlocking or mounting a different disk.
+
+## Related
+
+- [[Storage Policy]]
+- [[Dankserver Stack]]

docs/LLM/deployment.md

@@ -18,7 +18,7 @@ repository to a running service.
 | Target | Host | Runtime | Service | Port |
 |--------|------|---------|---------|------|
 | Dankserver | dank@dankserver | upstream llama.cpp (Ornith-1.5-35B-A3B-CRACK Q6_K, native MTP draft, selected MoE experts offloaded via --override-tensor) | frank-default-small | 7770 |
-| Dankclaw | dank@dankclaw | charlie12345/ROCmFPX llama.cpp (caf-eemin Qwen3.8-27B ROCmI4 Q4_0, embedded MTP, ROCmI4 W4A4, 262K ctx / 1 slot) | frank-default-large | 7770 |
+| Dankclaw | dank@dankclaw | charlie12345/ROCmFPX llama.cpp (kingjones Qwen3.8 Uncensored Q6_0 ROCmFPX AGENT, standalone MTP, 262K ctx / 1 slot) | frank-default-large | 7770 |
 
 ## Workflow
 
@@ -138,21 +138,21 @@ from `peculiar-ragdoll/Qwen-Sharp-Chat-Templates`. See [[dealign-ornith-crack]].
 ### Dankclaw — frank-default-large
 
 The active service on Dankclaw uses the ROCmFPX llama.cpp runtime to serve
-[kingjones777/Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF](https://huggingface.co/kingjones777/Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF)
+[kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP-GGUF](https://huggingface.co/kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP-GGUF)
 under the alias `frank-default-large` on port 7770. The main model is
-`Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf`; the standalone MTP draft is
+`Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf`; the standalone MTP draft is
-`mtp-Qwen3.8-27B-Q4_0.gguf`, and the BF16 vision projector is loaded alongside
+`mtp-Qwen3.8-27B-Q4_0.gguf`, and the Q8_0 vision projector is loaded alongside
 it. The K-side KV cache remains `f16`; the V-side cache uses `turbo4`. The
-service keeps the existing 65536 context / 1-slot profile. The unit file is
+service uses the 262144 context / 1-slot profile. The unit file is
 `scripts/frank-default-large.service`; it launches through
 `scripts/serve-frank-large.sh`, which reads tunables from
 `scripts/frank-default-large.env`, applying the Qwen-Sharp chat template.
 
-> The kingjones ROCmFP4 STRIX MTP model served the slot from 2026-08-24; it
+> The Q8_0 AGENT experiment was retired on 2026-09-01 after repeated
-> was replaced by the caf-eemin ROCmI4 embedded-MTP model on 2026-08-25. The
+> `set_rows` crashes and device-local allocation failures. The former caf-eemin
-> v3 PromptForge payload and the CIRU ROCmFPX runtime are retired on this slot.
+> ROCmI4 embedded-MTP model and the v3 PromptForge payload are historical
-> The intermediate DFlash2 Vulkan deployment was retired the same day (2026-08-21).
+> deployments. The intermediate DFlash2 Vulkan deployment was retired on
-> See [[dflash2-large-vulkan]] for the archived runbook.
+> 2026-08-21. See [[kingjones-q8agent-rocmfpx]] and [[dflash2-large-vulkan]].
 
 ## Validation
 

docs/LLM/index.md

@@ -3,7 +3,7 @@
 Documentation for the LLM inference fleet on two local machines
 (2026-09-01): upstream llama.cpp on Dankserver (frank-default-small,
 Ornith-1.5-35B-A3B CRACK) and ROCmFPX llama.cpp on Dankclaw
-(frank-default-large, kingjones Qwen3.8-27B ROCmFPX Q8 AGENT). Both
+(frank-default-large, kingjones Qwen3.8 Uncensored Q6 AGENT). Both
 services run the Qwen-Sharp chat template.
 
 > 2026-08-22: the former `vllmScripts` repository is merged into the
@@ -26,9 +26,9 @@ ngram-mod, selected experts offloaded via override, 491520 ctx]
 
     subgraph Dankclaw[AMD Strix Halo - Ubuntu 26.04]
         D[gfx1151 iGPU 64 GiB unified memory]
-        E[CIRU ROCmFPX llama.cpp PromptForge v3
+        E[charlie12345/ROCmFPX build-kairic (v81)
 frank-default-large, port 7770]
-        F[Qwen3.8-27B ROCmFPX Q8_0 AGENT
+        F[Qwen3.8 Uncensored Q6 ROCmFPX AGENT
 MTP draft + Turbo4 V cache, 262K ctx / 1 slot]
         D --> E --> F
     end
@@ -48,14 +48,16 @@ MTP draft + Turbo4 V cache, 262K ctx / 1 slot]
 
 - [[deployment]] — deploy and update process for both servers
 - [[frank-redo-2026-08-17]] — the 2026-08-17 topology change
-- [kingjones Qwen3.8-27B ROCmFPX Q8 AGENT](https://huggingface.co/kingjones777/Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF) — active frank-default-large model on Dankclaw; standalone MTP and Turbo4 V cache
+- [kingjones Qwen3.8 Uncensored ROCmFP4 STRIX MTP](https://huggingface.co/kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP-GGUF) — active frank-default-large model on Dankclaw; Q6 AGENT main model with standalone MTP
-- [[kingjones-q8agent-rocmfpx]] — the Q8_0-AGENT runbook: serving profile, download, 262144 context, reasoning + preserve_thinking, 114 GiB TTM/GTT
+- [[kingjones-strix-mtp]] — the active Q6 AGENT runbook: serving profile, standalone MTP, reasoning + preserve_thinking, 114 GiB TTM/GTT
+- [[ubatch-benchmark-large]] — active-model ubatch sweep plan and results
+- [[kingjones-q8agent-rocmfpx]] — the retired Q8_0-AGENT investigation and `set_rows` failure
 - [[eemin-rocmi4-mtp]] — the former caf-eemin Qwen3.8-27B embedded-MTP model
   on Dankclaw (retired)
 - [[dealign-ornith-crack]] — the dealign Ornith-1.5-35B-A3B CRACK model on
   Dankserver (frank-default-small, active 2026-08-24)
-- [[kingjones-strix-mtp]] — the retired kingjones Qwen3.8-27B ROCmFP4 STRIX MTP
+- [[kingjones-strix-mtp]] — the active kingjones Qwen3.8-27B ROCmFP4 STRIX MTP
-  model on Dankclaw (superseded 2026-08-25 by the ROCmI4 embedded-MTP model)
+  model on Dankclaw (restored 2026-09-01 after the Q8_0 AGENT experiment)
 - [[dealign-ornith-crack]] — the dealign Ornith-1.5-35B-A3B CRACK model on
   Dankserver (frank-default-small, active 2026-08-24)
 - [[ciru-activefpx-promptforge]] — the RETIRED v3 CIRU PromptForge runtime

docs/LLM/kingjones-q8agent-rocmfpx.md

@@ -1,6 +1,9 @@
 # frank-default-large: kingjones Qwen3.8-27B-ROCmFPX-Q8_0-AGENT
 
-**Status:** ACTIVE on Dankclaw (since 2026-08-25).
+**Status:** Deployed on Dankclaw (since 2026-08-25). Serving is **BLOCKED by
+the `set_rows` build bug** — the model loads but crashes in
+`ggml_compute_forward_set_rows` before it can serve. All config goals are met;
+a build fix is required for the model to run.
 
 **Alias:** `frank-default-large`, port **7770**.
 
@@ -26,6 +29,53 @@ fit in the lifted **114 GiB TTM/GTT** budget (see the 114 GiB change in
 | Tunables | `scripts/frank-default-large.env` |
 | Serve script | `scripts/serve-frank-large.sh` |
 
+## Serving status: the `set_rows` build bug (blocks serving)
+
+As of 2026-08-25 the Q8_0 AGENT model will not serve on Dankclaw. It loads,
+reaches `initializing slots, n_slots = 1`, but never prints `start serving`.
+Health stays `503` until the process exits. The crash is in
+`ggml_compute_forward_set_rows` in `libggml-cpu.so.0`, a NULL function-pointer
+jump (address `0x00000000`).
+
+The backtrace (gdb). The main thread and one OpenMP worker crash in the same
+path:
+
+```mermaid
+graph TD
+    A[llama_context::graph_compute] --> B[ggml_backend_cpu_graph_compute]
+    B --> C[ggml_graph_compute]
+    C --> D[GOMP_parallel]
+    D --> E[ggml_compute_forward_set_rows]
+    E --> F[NULL dispatch -> address 0x0]
+    D --> G[Thread 23 worker: same path]
+```
+
+Test matrix. Five ROCmFPX builds and the all-CPU path were tested on a scratch
+port (`/tmp/g80bench/run.sh`), `gl=45`, `ctx=131072`. All crash in `set_rows`.
+
+| Build | Binary | Version | Result |
+| ----- | ------ | ------- | ------ |
+| build-kairic | `ciru-qwen38/ROCmFPX/build-kairic/bin/llama-server` | v81 (205a3e5f4) | segfault in set_rows |
+| build-promptforge | `ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server` | PromptForge/ActiveFPX lineage | segfault in set_rows |
+| build-rocmi4-w4a4 | `rocmi4-qwen38/ROCmFPX/build-rocmi4-w4a4/bin/llama-server` | v257 (c49ebdb) | segfault in set_rows |
+| build-strix-rocmfp4 | `GitPackages/ROCmFPX/build-strix-rocmfp4/bin/llama-server` | v209 (00d5452) | segfault in set_rows |
+| all-CPU | build-kairic, `-ngl 0` | v81 | segfault in set_rows |
+
+The crash is not GPU-specific (the all-CPU path fails too), not MTP-specific
+(`--spec-type none` fails), and not fixed by `LLAMA_SET_ROWS=0`. So it is a
+build bug: the Q8_0 AGENT GGUF graph needs a `set_rows` dispatch the ROCmFPX
+backends do not register. The older caf-eemin ROCmI4 and Kairic Edge models
+served fine on related ROCmFPX builds. The caf-eemin payload was about 14.4
+GiB; the separate
+PromptForge/ActiveFPX deployment used a much larger multi-file payload of about
+36.7 GiB. These are different deployments. The Q8_0 AGENT graph is the trigger
+for the `set_rows` failure.
+
+**Fix path:** rebuild charlie12345/ROCmFPX from source with a working
+`set_rows` for the ROCmFPX backend, or find a build where it is registered.
+This unblocks the model. See the context budget reality below once `set_rows`
+is fixed.
+
 ## Model files
 
 Three files, from the HF repo above:
@@ -93,9 +143,14 @@ Key choices:
 - **f16 K + TurboQuant V** cache. f16 K is the safe long-ctx default; TurboQuant
   halves the V cache at 262k while keeping quality (see the ubatch/threads-batch
   notes in [[qwen3.8-strix-optimizations]]).
-- **Full 262144 context, 1 slot.** The whole context KV cache plus the ~30 GB
+- **262144 context, 1 slot — the target.** The whole context KV cache plus the
-  payload (main + draft + mmproj) fit in the 114 GiB budget. Concurrent
+  ~30 GB payload (main + draft + mmproj) are meant to fit in the 114 GiB
-  requests queue; the server never preempts a running generation.
+  budget. Measured reality: `gl=999` (all layers on ROCm0) at 262144 **OOMs**
+  on device-local (`cudaMalloc failed`, the KV cache needs ~10-18 GiB that does
+  not fit once the payload is on the card). `gl=45` (partial offload) fits a
+  131072 context. The env ships `CTX_SIZE=262144`; the proven serving context
+  today is **131072 at `gl=45`** (before the `set_rows` fix). `deploy.sh` waits
+  up to 20 minutes (see `LLM_WAIT`).
 - **Reasoning on.** The Sharp template drives thinking (medium effort);
   `--reasoning-format none` lets the template project the reasoning content into
   `reasoning_content`. `--reasoning-budget -1` = no budget cap.
@@ -160,6 +215,11 @@ reads `--host/--port/--temp` as CLI flags, never as env vars.
 - **2026-08-25 (today):** switched the large service to the kingjones
   Q8_0-AGENT model with 262144 context and reasoning on. Downloaded the three
   payload files from the HF repo, raised the TTM/GTT to 114 GiB for the full
-  context, and persisted the env/serve script in this repo.
+  context, and persisted the env/serve script in this repo. Measured that the
+  model loads but crashes in `ggml_compute_forward_set_rows` on all five
+  available ROCmFPX builds; serving is BLOCKED pending a rebuild. The config
+  goals (GTT 114 GiB, reasoning on, preserve_thinking/preserve_reasoning on,
+  262144 env context) are in place. Proven serving context today is 131072 at
+  `gl=45`. See the `set_rows` build bug section above.
 - Preceding model: Kairic Edge Qwen3.8-27B IU4 (deployed 2026-08-25 ~05:42,
   retired the same day for the AGENT model). See [[kairic-edge]].

docs/LLM/kingjones-strix-mtp.md

@@ -15,13 +15,12 @@ timestamp: 2026-08-24
 
 # kingjones Qwen3.8-27B ROCmFP4 STRIX MTP on Dankclaw
 
-> **Retired 2026-08-25.** The kingjones ROCmFP4 STRIX MTP payload has been
+> **Active again 2026-09-01.** The kingjones ROCmFP4 STRIX MTP payload is
-> replaced by the caf-eemin Qwen3.8-27B ROCmI4 embedded-MTP model on the same
+> restored as `frank-default-large` after the Q8_0 AGENT experiment. The Q8_0
-> port and iGPU, under a new runtime (charlie12345/ROCmFPX ROCmI4 W4A4). See
+> model was retired because it crashed before serving. The Q6 AGENT model,
-> [[eemin-rocmi4-mtp]]. The old kingjones GGUF + standalone MTP Q4_0 draft are
+> standalone MTP draft, Q8 projector, and PromptForge runtime are now active.
-> retired on this slot. The CIRU ROCmFPX runtime/binary is also retired here.
 
-> _This page documents the retired model and its runbook for reference._
+> This page documents the active model and its runbook.
 
 `frank-default-large` (port 7770) serves
 `Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP` from `kingjones777` on Hugging
@@ -34,7 +33,7 @@ here; the head is loaded with `--model-draft`.
 
 The card ships six text files plus the vision projector. The service uses
 the Q6 AGENT file (requested for the fleet), the separate MTP draft head
-and the Q8 vision projector.
+and the Q8 vision projector (`mmproj-Qwen3.8-27B-Q8_0.gguf`).
 
 | File | Size |
 |------|------|

docs/LLM/ubatch-benchmark-large.md

@@ -0,0 +1,60 @@
+---
+type: benchmark plan
+title: frank-default-large ubatch sweep
+description: Standardized ubatch sweep for the active kingjones Qwen3.8 ROCmFPX deployment.
+tags:
+  - llama.cpp
+  - rocm
+  - benchmark
+  - ubatch
+timestamp: 2026-09-01
+---
+
+# frank-default-large ubatch sweep
+
+This benchmark sweeps the active `frank-default-large` model on Dankclaw using
+scratch ports and a 32K-context workload. The production service is stopped
+before the sweep and restarted by the benchmark's exit handler.
+
+## Sweep
+
+The default points are `256, 512, 768, 1024, 1280, 1536, 2048, 3072, 4096,
+5120, 6144`. This implements the requested 256-step range through 1536 and
+1024-step range from 2048 through 6144. Each point runs three 256-token decode
+requests by default.
+
+Run on Dankclaw from the repository checkout:
+
+```bash
+STOPSVC=1 ./scripts/bench-ubatch-rocmi4.sh
+```
+
+The script uses the active Q6 AGENT model, standalone MTP draft, a fixed
+32K batch, and the tracked Sharp
+template, and `--reasoning-format deepseek`. It reports server timing lines and
+per-run generation throughput. Run only when the production service can be
+interrupted; the GPU is shared with live workloads.
+
+## Results
+
+Record results below after the sweep, including failures or OOM points.
+
+| ubatch | prefill | generation | notes |
+| ---: | ---: | ---: | --- |
+| 256 | — | — | pending |
+| 512 | — | — | pending |
+| 768 | — | — | pending |
+| 1024 | — | — | pending |
+| 1280 | — | — | pending |
+| 1536 | — | — | pending |
+| 2048 | — | — | pending |
+| 3072 | — | — | pending |
+| 4096 | — | — | pending |
+| 5120 | — | — | pending |
+| 6144 | — | — | pending |
+
+## See also
+
+- [LLM fleet index](index.md)
+- [Deployment](deployment.md)
+- [Active kingjones runbook](kingjones-strix-mtp.md)

docs/index.md

@@ -30,6 +30,10 @@ covers both workloads).
 - [[Deployment Flow]] — git-based deploy, target map, health checks
 - [[Testing Policy]] — the test seams and how to run them
 
+## Dankserver Storage
+
+- [[Entropy Volume]] — command-line unlock and mount helper
+
 ## Dankserver Services
 
 - [[RomM]] — retro game manager
@@ -97,9 +101,9 @@ The LLM inference fleet on the two hosts. Full index:
 
 - [[deployment]] — unified deploy and update process for both servers
 - [[frank-redo-2026-08-17]] — the 2026-08-17 topology change
-- [[eemin-rocmi4-mtp]] — the caf-eemin Qwen3.8-27B ROCmI4 embedded-MTP model on Dankclaw (frank-default-large, active)
+- [[kingjones-strix-mtp]] — the active kingjones Qwen3.8-27B ROCmFP4 STRIX MTP model on Dankclaw (restored 2026-09-01)
-- [[kingjones-strix-mtp]] — the RETIRED kingjones Qwen3.8-27B ROCmFP4 STRIX MTP model on Dankclaw (superseded 2026-08-25)
+- [[kingjones-q8agent-rocmfpx]] — the retired Q8_0-AGENT investigation and `set_rows` failure
-- [[kingjones-q8agent-rocmfpx]] — the Q8_0-AGENT runbook for frank-default-large (active): serving, download, 262144 context, reasoning + preserve_thinking, 114 GiB TTM/GTT
+- [[eemin-rocmi4-mtp]] — the former caf-eemin Qwen3.8-27B ROCmI4 embedded-MTP model on Dankclaw
 - [[ciru-activefpx-promptforge]] — the RETIRED v3 CIRU PromptForge runtime on Dankclaw (superseded 2026-08-24)
 - [[kingjones-strix-mtp]] — the kingjones Qwen3.8-27B ROCmFP4 STRIX MTP model on Dankclaw (active)
 - [[dealign-ornith-crack]] — the dealign Ornith-1.5-35B-A3B CRACK model on Dankserver (active)
@@ -112,6 +116,7 @@ The LLM inference fleet on the two hosts. Full index:
 ### Benchmarks and Sizing
 
 - [[frank-default-large-benchmark]] — backend/spec benchmark behind the old head
+- [[ubatch-benchmark-large]] — active-model ubatch sweep plan and results
 - [[frank-default-small-benchmark]] — the small-model benchmark suite
 - [[Running Qwen3.6 35B A3B FP8 on Dankserver]] — Qwen3.6-35B-A3B hardware notes
 - [[Running Qwen3.6 27B FP8 on Dankclaw]] — Qwen3.6-27B sizing on the iGPU

scripts/bench-ubatch-rocmi4.sh

@@ -1,9 +1,9 @@
 #!/usr/bin/env bash
 # bench-ubatch-rocmi4.sh — sweep ubatch size at 8k context on the
-# frank-default-large ROCmI4 embedded-MTP stack (dankclaw, gfx1151).
+# frank-default-large ROCmFPX standalone-MTP stack (dankclaw, gfx1151).
 #
 # Boots one llama-server instance per ubatch on a scratch port with a fixed
-# -b and -c 8192, runs a standardized ~75%-of-ctx prose workload, and reads
+# -b and -c 32768, runs a standardized ~75%-of-ctx prose workload, and reads
 # authoritative prefill/generation tok/s from the server's own print_timing
 # lines. Steps from UBATCH_MIN to UBATCH_MAX inclusive by UBATCH_STEP.
 #
@@ -26,21 +26,23 @@ if [[ -f "$ENV_FILE" ]]; then
 fi
 
 # --- sweep parameters -------------------------------------------------------
-: "${UBATCH_MIN:=512}"
+: "${UBATCH_MIN:=256}"
-: "${UBATCH_MAX:=4096}"
+: "${UBATCH_MAX:=6144}"
-: "${UBATCH_STEP:=512}"
+: "${UBATCH_STEP:=256}"
-: "${CTX:=8192}"                 # 8k contexts
+: "${UBATCH_VALUES:=256 512 768 1024 1280 1536 2048 3072 4096 5120 6144}"
-: "${BENCH_BATCH:=$CTX}"         # fixed batch = ctx, so the full 8k prompt fits
+: "${CTX:=32768}"                # 32k contexts
+: "${BENCH_BATCH:=32768}"         # batch is fixed to the 32k context size
 : "${OUT_TOKENS:=256}"
 : "${RUNS:=3}"                   # decode runs per ubatch
 : "${PORT_BASE:=7894}"           # scratch ports 7894..
-: "${STOPSVC:=0}"                # stop/restart the live unit for a clean GPU
+: "${STOPSVC:=1}"                # stop/restart the live unit for a clean GPU
 
 # --- resolved paths (fall back to serve-script defaults) --------------------
-: "${LLAMA_BIN:=/home/dank/rocmi4-qwen38/ROCmFPX/build-rocmi4-w4a4/bin/llama-server}"
+: "${LLAMA_BIN:=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server}"
-: "${MODEL_DIR:=/home/dank/models/eemin-Qwen3.8-27B-ROCMI4-MTP}"
+: "${MODEL_DIR:=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP}"
-: "${MODEL_FILE:=Qwen3.8-27B-Q4_0_ROCMI4.gguf}"
+: "${MODEL_FILE:=Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf}"
-: "${MMPROJ_FILE:=mmproj-BF16.gguf}"
+: "${MTP_DRAFT_FILE:=$MODEL_DIR/mtp-Qwen3.8-27B-Q4_0.gguf}"
+: "${MMPROJ_FILE:=mmproj-Qwen3.8-27B-Q8_0.gguf}"
 : "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
 : "${ALIAS:=frank-default-large}"
 : "${HSA_OVERRIDE_GFX_VERSION:=11.5.1}"
@@ -68,7 +70,14 @@ if [[ -f "$MMPROJ" ]]; then
 fi
 
 STopped=0
+SCRATCH_PID=""
 cleanup() {
+    if [[ -n "$SCRATCH_PID" ]] && kill -0 "$SCRATCH_PID" 2>/dev/null; then
+        echo "=== stopping scratch llama-server (pid $SCRATCH_PID) ==="
+        kill "$SCRATCH_PID" 2>/dev/null || true
+        wait "$SCRATCH_PID" 2>/dev/null || true
+        SCRATCH_PID=""
+    fi
     if [ "$STopped" = 1 ]; then
         echo "=== restarting frank-default-large ==="
         sudo systemctl restart frank-default-large || true
@@ -109,12 +118,12 @@ run_one() {
     local log="/tmp/ubatch-${ubatch}-p${port}.log"
     : > "$log"
 
-    echo "=== ubatch=${ubatch} ctx=${CTX} port=${port} runs=${runs} ==="
+    echo "=== ubatch=${ubatch} ctx=${CTX} batch=${BENCH_BATCH} port=${port} runs=${runs} ==="
     "$LLAMA_BIN" \
         --model "$MODEL" \
         "${MMPROJ_ARGS[@]}" \
         --chat-template-file "$CHAT_TEMPLATE_FILE" \
-        --chat-template-kwargs '{"enable_thinking":true,"preserve_thinking":true}' \
+        --chat-template-kwargs '{"enable_thinking":true,"preserve_thinking":true,"preserve_reasoning":true}' \
         --alias bench-ubatch \
         --host 127.0.0.1 --port "$port" \
         -dev ROCm0 -ngl 999 -np 1 \
@@ -122,25 +131,32 @@ run_one() {
         -c "$CTX" -b "$BENCH_BATCH" -ub "$ubatch" \
         -fa on -ctk f16 -ctv f16 -ctxcp 16 \
         --cache-ram 8192 --cache-prompt --metrics --no-mmap \
-        --spec-type draft-mtp --spec-mtp-strict-qwen \
+        --spec-type draft-mtp --model-draft "$MTP_DRAFT_FILE" \
-        --spec-draft-device ROCm0 --spec-draft-ngl all \
+        --spec-draft-device ROCm0 --spec-draft-ngl 999 \
         --spec-draft-type-k f16 --spec-draft-type-v f16 \
         --spec-draft-n-max "$MTP_N_MAX" --spec-draft-n-min 0 \
         --spec-draft-p-min "$MTP_P_MIN" \
         --spec-draft-backend-sampling \
         --temp 0.7 --top-p 0.95 \
-        --reasoning on --reasoning-format deepseek --reasoning-budget -1 \
+        --reasoning "$REASONING" --reasoning-format "$REASONING_FORMAT" --reasoning-budget -1 \
         -lv 4 >>"$log" 2>&1 &
     local pid=$!
-    wait_health "$pid" "$port" || { tail -30 "$log"; return 2; }
+    SCRATCH_PID="$pid"
+    if ! wait_health "$pid" "$port"; then
+        tail -30 "$log"
+        kill "$pid" 2>/dev/null || true
+        wait "$pid" 2>/dev/null || true
+        SCRATCH_PID=""
+        return 2
+    fi
 
     # one python pass per run; reuse the same boot across runs
     local r
     for r in $(seq 1 "$runs"); do
         echo "--- run ${r}/${runs} ---"
-        python3 - "$ubatch" "$port" "$out_tokens" "$CTX" "$log" <<'PY'
+        if ! python3 - "$ubatch" "$port" "$out_tokens" "$CTX" "$log" "$r" <<'PY'
 import sys, time, json, urllib.request
-ubatch, port, out_tokens, ctx, log = sys.argv[1], sys.argv[2], int(sys.argv[3]), int(sys.argv[4]), sys.argv[5]
+ubatch, port, out_tokens, ctx, log, run_number = sys.argv[1], sys.argv[2], int(sys.argv[3]), int(sys.argv[4]), sys.argv[5], sys.argv[6]
 
 # Flowing prose at ~75% of ctx so MTP acceptance is realistic.
 VAR = (
@@ -175,8 +191,12 @@ body = json.dumps({
 req = urllib.request.Request(f"http://127.0.0.1:{port}/v1/completions",
                              data=body, headers={"Content-Type": "application/json"})
 t0 = time.time()
-with urllib.request.urlopen(req, timeout=7200) as resp:
+try:
-    out = json.load(resp)
+    with urllib.request.urlopen(req, timeout=7200) as resp:
+        out = json.load(resp)
+except Exception:
+    print("request failed; preserving benchmark cleanup", file=sys.stderr)
+    raise
 dt = time.time() - t0
 pt = out.get("usage", {}).get("prompt_tokens", 0)
 ct = out.get("usage", {}).get("completion_tokens", 0)
@@ -190,24 +210,33 @@ def grab(arr):
 
 g_tps = ""
 if evals and ct:
-    # eval time line: "eval time = .. ms for N tokens"
+    # eval timing line: "eval time = .. ms / N tokens (... tokens per second)"
-    ev = evals[-1].split("= ")[-1]
+    import re
-    ms = float(ev.split(" for")[0].strip())
+    match = re.search(r"eval time =\s*([0-9.]+) ms", evals[-1])
-    g_tps = f"{ct / (ms / 1000):.2f}"
+    if match:
-print(f"== RESULT ubatch={ubatch} run={r} "
+        ms = float(match.group(1))
+        g_tps = f"{ct / (ms / 1000):.2f}"
+print(f"== RESULT ubatch={ubatch} run={run_number} "
       f"PREFILL={grab(prefill)} GEN_TPS={g_tps} "
       f"pt={pt} ct={ct} wall={dt:.1f}s")
 PY
+        then
+            kill "$pid" 2>/dev/null || true
+            wait "$pid" 2>/dev/null || true
+            SCRATCH_PID=""
+            return 2
+        fi
     done
     kill "$pid" 2>/dev/null || true
     wait "$pid" 2>/dev/null || true
+    SCRATCH_PID=""
 }
 
 main() {
     stop_live_service
     local idx=0 ubatch port
     printf "%-10s %-14s %-10s\n" "UBATCH" "PREFILL" "GEN_TPS"
-    for ubatch in $(seq "$UBATCH_MIN" "$UBATCH_STEP" "$UBATCH_MAX"); do
+    for ubatch in $UBATCH_VALUES; do
         port=$((PORT_BASE + idx))
         run_one "$ubatch" "$port" "$OUT_TOKENS" "$RUNS"
         idx=$((idx + 1))

scripts/deploy.sh

@@ -154,11 +154,11 @@ fi
 if [ '${COPY_SHARED[$TARGET]}' = '1' ]; then
   echo '[3/5] Copying shared configs into place...'
   mkdir -p /opt/searxng/config /opt/prometheus/config /opt/loki/config /opt/alloy/config
-  cp shared/searxng/settings.yml /opt/searxng/config/settings.yml
+  ${SUDO} cp shared/searxng/settings.yml /opt/searxng/config/settings.yml
-  cp shared/searxng/limiter.toml /opt/searxng/config/limiter.toml
+  ${SUDO} cp shared/searxng/limiter.toml /opt/searxng/config/limiter.toml
-  cp shared/prometheus/prometheus.yml /opt/prometheus/config/prometheus.yml
+  ${SUDO} cp shared/prometheus/prometheus.yml /opt/prometheus/config/prometheus.yml
-  cp shared/loki/loki-config.yaml /opt/loki/config/loki-config.yaml
+  ${SUDO} cp shared/loki/loki-config.yaml /opt/loki/config/loki-config.yaml
-  cp shared/alloy/config.alloy /opt/alloy/config/config.alloy
+  ${SUDO} cp shared/alloy/config.alloy /opt/alloy/config/config.alloy
 
   echo '  Rendering Caddyfile (basicauth hash from .env)...'
   # Extract the hash with grep/cut rather than sourcing .env: sourcing a
@@ -213,7 +213,9 @@ if [ '${COMPOSE_UP[$TARGET]}' = '1' ]; then
       podman build --no-cache --label cfhash=\$cfhash -t \$img:latest -f dankclaw/\$dir/Containerfile .
     fi
   done
-  podman-compose -f '${COMPOSE[$TARGET]}' up -d
+  if ! podman-compose -f '${COMPOSE[$TARGET]}' up -d; then
+    echo '  WARN: compose restart failed; continuing with LLM deployment.' >&2
+  fi
 
   # A Caddyfile render is a bind-mount content change, not a container
   # config change: the caddy container often survives 'up -d' and keeps
@@ -233,7 +235,7 @@ if [ '${COMPOSE_UP[$TARGET]}' = '1' ]; then
   done
   if [ \"\$caddy_reloaded\" -ne 1 ]; then
     echo \"  Caddy reload failed; restarting the container to load the file.\"
-    podman restart caddy
+    podman restart caddy || true
   fi
 else
   echo '[4/5] Skipping compose restart (stack runs as bare containers on this host)'

scripts/frank-default-large.env

@@ -1,4 +1,4 @@
-# Tunables for frank-default-large (kingjones Qwen3.8-27B ROCmFPX Q8 AGENT,
+# Tunables for frank-default-large (kingjones Qwen3.8 Uncensored Q6 AGENT,
 # dankclaw, Strix Halo gfx1151).
 #
 # Runtime: ROCmFPX llama.cpp with TurboQuant support. Serves the kingjones
@@ -9,18 +9,22 @@
 # HIP runtime reads those bare env vars (see the 2026-08-13 TEMP incident).
 # llama.cpp reads --host/--port/--temp as CLI flags, never as env vars.
 
-# ROCmFPX build with TurboQuant KV-cache support.
+# PromptForge ROCmFPX build and its historical ROCm 7.15 SDK environment.
-LLAMA_BIN=/home/dank/ciru-qwen38/ROCmFPX/build-kairic/bin/llama-server
+LLAMA_BIN=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server
+ROCM_DEVEL=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_devel
+ROCM_LIB=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_libraries
+ROCM_CORE=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_core
 
-# Model files from https://huggingface.co/kingjones777/Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF.
+# Model files from https://huggingface.co/kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP-GGUF.
-MODEL_DIR=/home/dank/models/kingjones-Qwen3.8-27B-ROCMFPX-Q8_0-AGENT
+MODEL_DIR=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP
-MODEL_FILE=Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf
+MODEL_FILE=Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf
 MTP_DRAFT_FILE=$MODEL_DIR/mtp-Qwen3.8-27B-Q4_0.gguf
-MMPROJ_FILE=mmproj-Qwen3.8-27B-BF16.gguf
+MMPROJ_FILE=mmproj-Qwen3.8-27B-Q8_0.gguf
 
 # Qwen-Sharp chat template (tracked in the repo, staged on the host). The Sharp
-# template drives thinking on by default (medium effort) and produces the
+# template drives thinking on by default (medium effort); the server emits
-# peg-native + deepseek chat/reasoning shape the Pi agent expects.
+# reasoning in DeepSeek format so clients receive reasoning_content separately
+# instead of literal <think> tags in content.
 CHAT_TEMPLATE_FILE=/home/dank/serverAppConfigs/scripts/chat-template.jinja
 CHAT_TEMPLATE_KWARGS='{"enable_thinking":true,"preserve_thinking":true,"preserve_reasoning":true}'
 
@@ -37,13 +41,13 @@ LISTEN_PORT=7770
 CTX_SIZE=262144
 PARALLEL=1
 # Batch/ubatch follow the existing qualified Dankclaw profile.
-BATCH_SIZE=512
+BATCH_SIZE=4096
-UBATCH_SIZE=512
+UBATCH_SIZE=4096
 NUM_THREADS=16
 THREAD_BATCH=32
 CACHE_TYPE_K=f16
-CACHE_TYPE_V=turbo4
+CACHE_TYPE_V=f16
-CTX_CHECKPOINTS=32
+CTX_CHECKPOINTS=16
 CACHE_RAM=8192
 
 # Standalone MTP draft head, loaded from MTP_DRAFT_FILE by the serve script.
@@ -60,10 +64,10 @@ MIN_P=0.0
 PRESENCE_PENALTY=1.5
 
 # Reasoning on (Sharp template drives it; preserve_thinking + preserve_reasoning
-# keep the reasoning trail in the conversation). reasoning-format none lets the
+# keep the reasoning trail in the conversation). DeepSeek format projects the
-# template project the reasoning content into reasoning_content.
+# reasoning into the API's reasoning_content field instead of content tags.
 REASONING=on
-REASONING_FORMAT=none
+REASONING_FORMAT=deepseek
 
 # Strix Halo unified memory + native gfx1151 detection for this ROCmFPX build.
 HSA_OVERRIDE_GFX_VERSION=11.5.1

scripts/mount-entropy.sh

@@ -0,0 +1,32 @@
+#!/usr/bin/env bash
+# Unlock and mount Dankserver's encrypted entropy volume.
+#
+# The desktop flow uses the system's crypttab and fstab entries.  Reuse those
+# entries here instead of embedding a passphrase, mount options, or ownership
+# changes in this helper.  udisksctl reads the passphrase through its secure
+# desktop/terminal authentication path.
+set -euo pipefail
+
+MOUNTPOINT='/mnt/entropy'
+MAPPER='/dev/mapper/luks-cd86c728-459e-4f3a-bcc2-41ecf84685ec'
+
+if mountpoint -q "$MOUNTPOINT"; then
+    printf '%s is already mounted.\n' "$MOUNTPOINT"
+    exit 0
+fi
+
+if [ ! -e /dev/md0 ]; then
+    printf 'ERROR: RAID device /dev/md0 is not available.\n' >&2
+    exit 1
+fi
+
+if [ ! -e "$MAPPER" ]; then
+    udisksctl unlock --block-device /dev/md0
+fi
+
+# udisks2 may mount automatically as part of unlocking.  Do not attempt a
+# second mount in that case.
+if ! mountpoint -q "$MOUNTPOINT"; then
+    sudo mount "$MOUNTPOINT"
+fi
+printf 'Mounted %s.\n' "$MOUNTPOINT"

scripts/serve-frank-large.sh

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
-# Serve the kingjones Qwen3.8-27B ROCmFPX Q8 AGENT model as frank-default-large.
+# Serve the kingjones Qwen3.8 Uncensored Q6 AGENT model as frank-default-large.
-# The deployment uses a standalone MTP draft head and Turbo4 V-side KV cache.
+# The deployment uses a standalone MTP draft head and f16 KV cache.
 set -euo pipefail
 
 SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
@@ -12,23 +12,23 @@ if [[ -f "$ENV_FILE" ]]; then
     set +a
 fi
 
-: "${LLAMA_BIN:=/home/dank/ciru-qwen38/ROCmFPX/build-kairic/bin/llama-server}"
+: "${LLAMA_BIN:=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server}"
-: "${MODEL_DIR:=/home/dank/models/kingjones-Qwen3.8-27B-ROCMFPX-Q8_0-AGENT}"
+: "${MODEL_DIR:=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP}"
-: "${MODEL_FILE:=Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf}"
+: "${MODEL_FILE:=Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf}"
 : "${MTP_DRAFT_FILE:=$MODEL_DIR/mtp-Qwen3.8-27B-Q4_0.gguf}"
-: "${MMPROJ_FILE:=mmproj-Qwen3.8-27B-BF16.gguf}"
+: "${MMPROJ_FILE:=mmproj-Qwen3.8-27B-Q8_0.gguf}"
 : "${ALIAS:=frank-default-large}"
 : "${BIND_ADDR:=0.0.0.0}"
 : "${LISTEN_PORT:=7770}"
 : "${CTX_SIZE:=262144}"
 : "${PARALLEL:=1}"
-: "${BATCH_SIZE:=2048}"
+: "${BATCH_SIZE:=4096}"
-: "${UBATCH_SIZE:=512}"
+: "${UBATCH_SIZE:=4096}"
 : "${NUM_THREADS:=16}"
 : "${THREAD_BATCH:=32}"
 : "${CACHE_TYPE_K:=f16}"
-: "${CACHE_TYPE_V:=turbo4}"
+: "${CACHE_TYPE_V:=f16}"
-: "${CTX_CHECKPOINTS:=32}"
+: "${CTX_CHECKPOINTS:=16}"
 : "${CACHE_RAM:=8192}"
 : "${MTP_N_MAX:=4}"
 : "${MTP_N_MIN:=0}"
@@ -55,14 +55,18 @@ if [[ ! -x "$LLAMA_BIN" ]]; then
     exit 1
 fi
 SERVER_DIR="$(cd -- "$(dirname -- "$LLAMA_BIN")" && pwd)"
-ROCM_PATH="${ROCM_PATH:-/opt/rocm}"
+ROCM_PATH="${ROCM_DEVEL:-${ROCM_PATH:-/opt/rocm}}"
-LIBRARY_PATH="$SERVER_DIR:$ROCM_PATH/lib:$ROCM_PATH/lib/rocm_sysdeps/lib:$ROCM_PATH/lib/llvm/lib:$ROCM_PATH/llvm/lib${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"
+if [[ -n "${ROCM_LIB:-}" && -n "${ROCM_CORE:-}" ]]; then
+    LIBRARY_PATH="$ROCM_LIB/lib:$ROCM_CORE/lib:$ROCM_DEVEL/lib/llvm/lib:$SERVER_DIR:${LD_LIBRARY_PATH:-}"
+else
+    LIBRARY_PATH="$SERVER_DIR:$ROCM_PATH/lib:$ROCM_PATH/lib/rocm_sysdeps/lib:$ROCM_PATH/lib/llvm/lib:$ROCM_PATH/llvm/lib${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"
+fi
 
 exec /usr/bin/env \
     ROCM_PATH="$ROCM_PATH" \
     HIP_VISIBLE_DEVICES=0 \
-    HSA_OVERRIDE_GFX_VERSION="$HSA_OVERRIDE_GFX_VERSION" \
     LD_LIBRARY_PATH="$LIBRARY_PATH" \
+    HSA_OVERRIDE_GFX_VERSION="$HSA_OVERRIDE_GFX_VERSION" \
     GGML_CUDA_GRAPH_OPT=0 \
     LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0 \
     LLAMA_MTP_CPU_ARGMAX_FASTPATH=1 \

scripts/test-changed.sh

@@ -0,0 +1,148 @@
+#!/usr/bin/env bash
+# Run only the Bats tests affected by the staged paths.
+#
+# Usage:
+#   scripts/test-changed.sh              # inspect the staged commit
+#   scripts/test-changed.sh --list       # print selected test files
+#   scripts/test-changed.sh --paths FILE ...
+#
+# --paths is intended for tests and local experimentation. The normal mode is
+# deliberately staged-only so a pre-commit hook cannot accidentally validate
+# an unrelated dirty working-tree file.
+set -euo pipefail
+
+REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+LIST_ONLY=0
+USE_PATHS=0
+declare -a CHANGED=()
+
+die() {
+    printf 'ERROR: %s\n' "$*" >&2
+    exit 2
+}
+
+while [ "$#" -gt 0 ]; do
+    case "$1" in
+        --list)
+            LIST_ONLY=1
+            shift
+            ;;
+        --paths)
+            USE_PATHS=1
+            shift
+            while [ "$#" -gt 0 ] && [[ "$1" != --* ]]; do
+                CHANGED+=("$1")
+                shift
+            done
+            ;;
+        --)
+            shift
+            CHANGED+=("$@")
+            break
+            ;;
+        *)
+            die "unknown option '$1' (use --list or --paths FILE ...)"
+            ;;
+    esac
+done
+
+cd "$REPO_ROOT"
+if [ "$USE_PATHS" -eq 0 ]; then
+    while IFS= read -r -d '' path; do
+        CHANGED+=("$path")
+    done < <(git diff --cached --name-only -z --diff-filter=ACMRTUXB)
+fi
+
+[ "${#CHANGED[@]}" -gt 0 ] || {
+    printf 'No staged paths; no focused tests to run.\n'
+    exit 0
+}
+
+declare -a TESTS=()
+add_test() {
+    local test="$1"
+    local existing
+    for existing in "${TESTS[@]:-}"; do
+        [ "$existing" != "$test" ] || return 0
+    done
+    TESTS+=("$test")
+}
+
+for path in "${CHANGED[@]}"; do
+    case "$path" in
+        tests/*.bats)
+            add_test "$path"
+            ;;
+        tests/helpers.bash|tests/run.sh)
+            die "$path is shared test infrastructure; run ./tests/run.sh explicitly"
+            ;;
+        .githooks/*)
+            add_test tests/changed_tests.bats
+            ;;
+        dankserver/compose.yaml|dankclaw/compose.yaml)
+            add_test tests/compose_validity.bats
+            add_test tests/env_consistency.bats
+            ;;
+        dankserver/Caddyfile|dankclaw/Caddyfile)
+            add_test tests/caddyfile.bats
+            ;;
+        dankserver/.env.example|dankclaw/.env.example)
+            add_test tests/env_consistency.bats
+            ;;
+        shared/homepage/*)
+            add_test tests/homepage_caddy.bats
+            add_test tests/homepage_config.bats
+            add_test tests/homepage_deploy.bats
+            add_test tests/homepage_pages.bats
+            add_test tests/homepage_checker.bats
+            ;;
+        shared/searxng/*)
+            add_test tests/searxng_limiter.bats
+            add_test tests/searxng_quadlet.bats
+            ;;
+        dankclaw/*.container|dankclaw/*.network)
+            add_test tests/open_webui_quadlet.bats
+            add_test tests/pihole.bats
+            add_test tests/searxng_quadlet.bats
+            ;;
+        scripts/mount-entropy.sh)
+            add_test tests/mount_entropy.bats
+            ;;
+        scripts/frank-default-large.env|scripts/serve-frank-large.sh)
+            add_test tests/frank_large_config.bats
+            add_test tests/llm_secrets.bats
+            add_test tests/scripts_syntax.bats
+            ;;
+        scripts/frank-default-small.env|scripts/serve-frank-small.sh)
+            add_test tests/frank_small_config.bats
+            add_test tests/llm_secrets.bats
+            add_test tests/scripts_syntax.bats
+            ;;
+        scripts/*.service)
+            add_test tests/llm_units.bats
+            add_test tests/scripts_syntax.bats
+            ;;
+        scripts/*)
+            add_test tests/scripts_syntax.bats
+            ;;
+        docs/*)
+            add_test tests/docs_completeness.bats
+            ;;
+        dankclaw/hermes/*)
+            add_test tests/docs_completeness.bats
+            ;;
+        *)
+            die "no focused-test mapping for '$path'; add one before committing"
+            ;;
+    esac
+done
+
+if [ "$LIST_ONLY" -eq 1 ]; then
+    printf '%s\n' "${TESTS[@]}"
+    exit 0
+fi
+
+command -v bats >/dev/null 2>&1 || die 'bats is not installed'
+printf 'Running focused tests for %d changed path(s):\n' "${#CHANGED[@]}"
+printf '  %s\n' "${TESTS[@]}"
+bats --print-output-on-failure "${TESTS[@]}"

scripts/tmux-resurrect.sh

@@ -0,0 +1,234 @@
+#!/usr/bin/env bash
+#
+# tmux-resurrect.sh — snapshot and restore the exact layout of a tmux session
+# on Dankclaw, including each pane's start directory and foreground command.
+#
+# Use it after a reboot (or when the display session is gone) to reopen the
+# same windows/panes on the Dankclaw console:
+#
+#   scripts/tmux-resurrect.sh snapshot      # record the live session to JSON
+#   scripts/tmux-resurrect.sh restore       # rebuild it, then attach
+#
+# Data file: ~/.tmux-resurrect/<session>.json (set TMUX_RES_DIR to relocate).
+# Re-run snapshot as the session changes so the restore stays faithful.
+#
+# How each pane's command is captured: a tmux pane runs one main shell
+# (#{pane_pid}). The foreground command is that shell's direct child — chosen
+# as the child that launched its own child (ssh, sudo ...) or the first child
+# when none did (btop sitting at the top of a pane). An idle shell yields no
+# command and is left at its prompt on restore.
+set -euo pipefail
+
+TMUX_RES_DIR="${TMUX_RES_DIR:-$HOME/.tmux-resurrect}"
+DEFAULT_SESSION="0"
+
+die() { printf 'tmux-resurrect: %s\n' "$*" >&2; exit 1; }
+b64() { base64 -w0; }
+b64d() { base64 -d; }
+
+# fg_command <shell_pid>: print the foreground command of a tmux pane, or the
+# empty string when the shell is idle.
+fg_command() {
+    local pid="$1" kids=() kid cmd_pid=""
+    mapfile -t kids < <(pgrep -P "$pid" 2>/dev/null || true)
+    if [ "${#kids[@]}" -eq 0 ]; then return 0; fi
+    # Prefer a child that launched its own child (a launcher such as ssh or
+    # sudo); fall back to the first direct child (e.g. btop at the top).
+    for kid in "${kids[@]}"; do
+        if pgrep -P "$kid" >/dev/null 2>&1; then
+            cmd_pid="$kid"; break
+        fi
+    done
+    if [ -z "$cmd_pid" ]; then cmd_pid="${kids[0]}"; fi
+    tr '\0' ' ' < "/proc/$cmd_pid/cmdline" 2>/dev/null | sed -E 's/[[:space:]]+$//'
+}
+
+# snapshot <session> [dest.json]
+snapshot() {
+    local session="${1:-$DEFAULT_SESSION}" dest="${2:-}"
+    local exists
+    exists=$(tmux list-sessions -F '#{session_name}' 2>/dev/null | grep -Fxq "$session" && echo 1 || echo 0)
+    [ "$exists" = 1 ] || die "no tmux session named '$session'"
+    mkdir -p "$TMUX_RES_DIR"
+    [ -z "$dest" ] && dest="$TMUX_RES_DIR/$session.json"
+    python3 - "$dest" "$session" 3< <(
+    {
+        while IFS=$'\t' read -r widx wname wlayout; do
+            printf 'W\t%s\t%s\t%s\n' "$widx" "$(printf '%s' "$wname" | b64)" "$(printf '%s' "$wlayout" | b64)"
+            while IFS=$'\t' read -r pidx ppid pdir; do
+                pcmd=$(fg_command "$ppid")
+                printf 'P\t%s\t%s\t%s\t%s\n' "$widx" "$pidx" \
+                    "$(printf '%s' "$pdir" | b64)" "$(printf '%s' "$pcmd" | b64)"
+            done < <(tmux list-panes -t "$session:$widx" \
+                        -F $'#{pane_index}\t#{pane_pid}\t#{pane_current_path}' | sort -n -k1,1)
+        done < <(tmux list-windows -t "$session" \
+                    -F $'#{window_index}\t#{window_name}\t#{window_layout}' | sort -n -k1,1)
+    }
+    ) > /dev/null <<'PY'
+import sys, json, base64, os
+dest, session = sys.argv[1], sys.argv[2]
+wmap, panes = {}, {}
+for line in os.fdopen(3).read().splitlines():
+    if not line:
+        continue
+    p = line.split('\t')
+    if p[0] == 'W':
+        wmap[int(p[1])] = {"name": base64.b64decode(p[2]).decode(),
+                           "layout": base64.b64decode(p[3]).decode()}
+    elif p[0] == 'P':
+        widx = int(p[1])
+        panes.setdefault(widx, []).append({
+            "index": int(p[2]),
+            "dir": base64.b64decode(p[3]).decode(),
+            "cmd": base64.b64decode(p[4]).decode(),
+        })
+windows = []
+for widx in sorted(wmap):
+    windows.append({
+        "index": widx,
+        "name": wmap[widx]["name"],
+        "layout": wmap[widx]["layout"],
+        "panes": sorted(panes.get(widx, []), key=lambda x: x["index"]),
+    })
+with open(dest, "w") as f:
+    json.dump({"session": session, "windows": windows}, f, indent=2, ensure_ascii=False)
+    f.write("\n")
+PY
+    printf 'snapshot: wrote %s (session %s)\n' "$dest" "$session"
+}
+
+# emit_plan <src.json> [session]: python reads the JSON and prints a base64
+# TSV plan (W/P records) for the bash orchestrator to consume.
+emit_plan() {
+    python3 - "$1" "$2" <<'PY'
+import sys, json, base64
+src, session = sys.argv[1], sys.argv[2]
+with open(src) as f:
+    data = json.load(f)
+wins = data.get("windows", [])
+if session:
+    wins = [w for w in wins if str(w.get("index")) == "0"]
+def b64(s): return base64.b64encode(s.encode()).decode()
+for w in wins:
+    print('W\t%s\t%s\t%s' % (w["index"], b64(w["name"]), b64(w["layout"])))
+    for pan in w["panes"]:
+        print('P\t%s\t%s\t%s\t%s' % (w["index"], pan["index"],
+                                      b64(pan["dir"]), b64(pan["cmd"])))
+PY
+}
+
+# restore [session] [--no-attach] [--dry-run]
+restore() {
+    local session="${1:-$DEFAULT_SESSION}"
+    shift || true
+    local keep=0 noattach=0 dryrun=0 a
+    for a in "$@"; do
+        case "$a" in
+            --keep) keep=1 ;;
+            --no-attach) noattach=1 ;;
+            --dry-run) dryrun=1 ;;
+            *) die "unknown restore option: $a" ;;
+        esac
+    done
+    local dest="$TMUX_RES_DIR/$session.json"
+    [ -f "$dest" ] || die "no snapshot at $dest (run snapshot first)"
+
+    # Restore wrapper: run tmux, or print the command under --dry-run.
+    tmuxr() {
+        if [ "$dryrun" = 1 ]; then printf '  tmux %s\n' "$*"; else tmux "$@"; fi
+    }
+
+    local target_exists
+    target_exists=$(tmux list-sessions -F '#{session_name}' 2>/dev/null | grep -Fxq "$session" && echo 1 || echo 0)
+    if [ "$target_exists" = 1 ]; then
+        if [ "$keep" = 1 ]; then
+            die "session '$session' already exists; rebuild without --keep or save a copy"
+        fi
+        if [ "$dryrun" = 1 ]; then printf '  # kill existing session %s\n' "$session"
+        else tmux kill-session --force "$session"; fi
+    fi
+
+    # Parse the plan into flat, window-major lists.
+    local -a WNAME=() WLAY=() WSTART=() PD=() PC=()
+    local tag idx nameb layoutb dirb cmdb
+    while IFS=$'\t' read -r tag idx nameb layoutb dirb cmdb; do
+        case "$tag" in
+            W) WNAME+=("$(printf '%s' "$nameb" | b64d)"); WLAY+=("$(printf '%s' "$layoutb" | b64d)"); WSTART+=("${#PD[@]}") ;;
+            P) PD+=("$(printf '%s' "$dirb" | b64d)"); PC+=("$(printf '%s' "$cmdb" | b64d)") ;;
+        esac
+    done < <(emit_plan "$dest" "")
+
+    local n=${#WNAME[@]} w first last npanes i curwin wname wlayout dir cmd
+    for ((w = 0; w < n; w++)); do
+        first=${WSTART[w]}
+        if (( w + 1 < n )); then last=${WSTART[w + 1]}; else last=${#PD[@]}; fi
+        npanes=$(( last - first ))
+        wname="${WNAME[w]}"; wlayout="${WLAY[w]}"
+        if [ "$dryrun" = 1 ]; then
+            if (( w == 0 )); then
+                tmuxr new-session -d -s "$session" -n "$wname" -c "${PD[first]}"
+            else
+                tmuxr new-window -d -t "$session" -n "$wname" -c "${PD[first]}"
+            fi
+            curwin="$session:$wname"
+        elif (( w == 0 )); then
+            curwin=$(tmux new-session -d -P -F '#{window_id}' \
+                -s "$session" -n "$wname" -c "${PD[first]}")
+        else
+            curwin=$(tmux new-window -d -P -F '#{window_id}' \
+                -t "$session" -n "$wname" -c "${PD[first]}")
+        fi
+        # Create the remaining panes in recorded order (index == creation order).
+        for ((i = first + 1; i < last; i++)); do
+            tmuxr split-window -t "$curwin" -c "${PD[i]}"
+        done
+        # Restore the exact geometry for this window.
+        tmuxr select-layout -t "$curwin" "$wlayout"
+        # Launch each pane's recorded command, matched to panes by ascending
+        # pane index (so this is correct regardless of base-index).
+        local -a ordered=()
+        mapfile -t ordered < <(tmux list-panes -t "$curwin" \
+            -F $'#{pane_id}\t#{pane_target}' | sort -n -k1,1)
+        local k=0 tgt
+        for tgt in "${ordered[@]}"; do
+            cmd="${PC[first + k]}"
+            if [ -n "$cmd" ]; then tmuxr send-keys -t "$tgt" "$cmd" Enter; fi
+            k=$((k + 1))
+        done
+    done
+
+    if [ "$noattach" = 1 ]; then
+        return 0
+    elif [ -t 0 ]; then
+        tmuxr attach -t "$session"
+    elif [ "$dryrun" = 0 ]; then
+        echo "session '$session' rebuilt; attach with: tmux attach -t $session"
+    fi
+}
+
+usage() {
+    cat <<'USAGE'
+tmux-resurrect.sh — snapshot & restore a tmux session on Dankclaw.
+
+Usage:
+  tmux-resurrect.sh snapshot [session] [dest.json]   record the live session
+  tmux-resurrect.sh restore  [session] [options]      rebuild the session
+    options:
+      --keep        skip if the session already exists (default: rebuild)
+      --no-attach   rebuild without attaching to this terminal
+      --dry-run     print the commands instead of running them
+USAGE
+}
+
+main() {
+    local cmd="${1:-snapshot}"
+    shift || true
+    case "$cmd" in
+        snapshot) snapshot "$@" ;;
+        restore)  restore "$@" ;;
+        -h|--help|help) usage ;;
+        *) die "unknown command: $cmd (use snapshot|restore)" ;;
+    esac
+}
+
+main "$@"

shared/searxng/settings.yml

@@ -21,13 +21,93 @@ valkey:
   url: "valkey://searxng-valkey:6379/0"
 
 outgoing:
-  request_timeout: 3.0
+  request_timeout: 5.0
-  max_request_timeout: 10.0
+  max_request_timeout: 15.0
   pool_connections: 100
   pool_maxsize: 20
   enable_http2: true
   keepalive_expiry: 5.0
-  retries: 3
+  retries: 1
+
+# Keep default aggregation anonymous and bounded. Disabled engines remain
+# available for explicit selection/on-demand use; inactive engines are removed.
+# Provider-specific overrides below also reduce pagination fan-out.
+engines:
+  - name: bing
+    disabled: false
+    weight: 2
+    paging: false
+    timeout: 5.0
+  - name: bing images
+    paging: false
+    timeout: 5.0
+  - name: bing news
+    paging: false
+    timeout: 5.0
+  - name: bing videos
+    paging: false
+    timeout: 5.0
+  - name: duckduckgo
+    disabled: false
+    weight: 2
+    paging: false
+    timeout: 5.0
+  - name: duckduckgo images
+    paging: false
+    timeout: 5.0
+  - name: duckduckgo news
+    paging: false
+    timeout: 5.0
+  - name: duckduckgo videos
+    paging: false
+    timeout: 5.0
+  - name: wikipedia
+    weight: 1
+    timeout: 5.0
+  - name: google cse
+    disabled: true
+    paging: false
+    timeout: 5.0
+  - name: google cse images
+    disabled: true
+    paging: false
+    timeout: 5.0
+  - name: google news
+    disabled: true
+    paging: false
+    timeout: 5.0
+  - name: google scholar
+    disabled: true
+    paging: false
+    timeout: 5.0
+  - name: brave
+    disabled: true
+    paging: false
+    timeout: 5.0
+  - name: brave.images
+    disabled: true
+    paging: false
+    timeout: 5.0
+  - name: brave.news
+    disabled: true
+    paging: false
+    timeout: 5.0
+  - name: brave.videos
+    disabled: true
+    paging: false
+    timeout: 5.0
+  - name: startpage
+    disabled: true
+    paging: false
+    timeout: 5.0
+  - name: startpage images
+    disabled: true
+    paging: false
+    timeout: 5.0
+  - name: startpage news
+    disabled: true
+    paging: false
+    timeout: 5.0
 
 plugins:
   searx.plugins.unit_converter.SXNGPlugin:

tests/changed_tests.bats

@@ -0,0 +1,30 @@
+#!/usr/bin/env bats
+# Seam: the changed-test wrapper selects only the tests associated with
+# staged paths and refuses to silently run the entire suite.
+
+load helpers
+
+@test "changed-test wrapper is executable and uses staged diff by default" {
+    [ -x "$REPO_ROOT/scripts/test-changed.sh" ]
+    [ -x "$REPO_ROOT/.githooks/pre-commit" ]
+    run grep -F 'scripts/test-changed.sh' "$REPO_ROOT/.githooks/pre-commit"
+    [ "$status" -eq 0 ]
+    run grep -F 'git diff --cached' "$REPO_ROOT/scripts/test-changed.sh"
+    [ "$status" -eq 0 ]
+}
+
+@test "changed-test wrapper maps a compose change to compose and environment tests" {
+    run bash "$REPO_ROOT/scripts/test-changed.sh" --list --paths dankserver/compose.yaml
+    [ "$status" -eq 0 ]
+    [[ "$output" == *"tests/compose_validity.bats"* ]]
+    [[ "$output" == *"tests/env_consistency.bats"* ]]
+    [[ "$output" != *"tests/homepage_pages.bats"* ]]
+}
+
+@test "changed-test wrapper maps a service script to its focused config tests" {
+    run bash "$REPO_ROOT/scripts/test-changed.sh" --list --paths scripts/serve-frank-small.sh
+    [ "$status" -eq 0 ]
+    [[ "$output" == *"tests/scripts_syntax.bats"* ]]
+    [[ "$output" == *"tests/frank_small_config.bats"* ]]
+    [[ "$output" != *"tests/frank_large_config.bats"* ]]
+}

tests/frank_large_config.bats

@@ -11,14 +11,15 @@ UNIT_FILE="$REPO_ROOT/scripts/frank-default-large.service"
 TEMPLATE_FILE="$REPO_ROOT/scripts/chat-template.jinja"
 
 @test "frank-default-large serves the kingjones AGENT model" {
-    grep -q '^MODEL_FILE=Qwen3\.8-27B-Q8_0_ROCMFPX_AGENT\.gguf$' "$ENV_FILE"
+    grep -q '^MODEL_FILE=Qwen3\.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT\.gguf$' "$ENV_FILE"
     grep -q '^MTP_DRAFT_FILE=' "$ENV_FILE"
+    grep -q '^MMPROJ_FILE=mmproj-Qwen3\.8-27B-Q8_0\.gguf$' "$ENV_FILE"
     ! grep -q -- '--kairic-edge' "$SERVE_FILE"
 }
 
 @test "frank-default-large uses the ROCmFPX runtime" {
     grep -q 'ROCmFPX/.*/bin/llama-server' "$ENV_FILE"
-    grep -q 'build-kairic/bin/llama-server' "$ENV_FILE"
+    grep -q 'build-promptforge/bin/llama-server' "$ENV_FILE"
 }
 
 @test "frank-default-large runs standalone MTP" {
@@ -38,6 +39,11 @@ TEMPLATE_FILE="$REPO_ROOT/scripts/chat-template.jinja"
     grep -q ': "${CTX_SIZE:=262144}"' "$SERVE_FILE"
 }
 
+@test "frank-default-large uses DeepSeek reasoning output" {
+    grep -q '^REASONING_FORMAT=deepseek$' "$ENV_FILE"
+    grep -q -- '--reasoning-format "$REASONING_FORMAT"' "$SERVE_FILE"
+}
+
 @test "frank-default-large has reasoning and preserved reasoning/thinking enabled" {
     grep -q '^REASONING=on$' "$ENV_FILE"
     grep -q 'enable_thinking":true' "$ENV_FILE"
@@ -45,18 +51,37 @@ TEMPLATE_FILE="$REPO_ROOT/scripts/chat-template.jinja"
     grep -q 'preserve_reasoning":true' "$ENV_FILE"
 }
 
-@test "frank-default-large uses Turbo4 only for the V cache" {
+@test "frank-default-large uses f16 for both KV cache sides" {
     grep -q '^CACHE_TYPE_K=f16$' "$ENV_FILE"
-    grep -q '^CACHE_TYPE_V=turbo4$' "$ENV_FILE"
+    grep -q '^CACHE_TYPE_V=f16$' "$ENV_FILE"
     grep -qF -- '-ctk "$CACHE_TYPE_K" -ctv "$CACHE_TYPE_V"' "$SERVE_FILE"
 }
 
 @test "frank-default-large exposes a swappable ubatch" {
-    grep -q '^UBATCH_SIZE=512$' "$ENV_FILE"
+    grep -q '^UBATCH_SIZE=4096$' "$ENV_FILE"
-    grep -q ': "${UBATCH_SIZE:=512}"' "$SERVE_FILE"
+    grep -q ': "${UBATCH_SIZE:=4096}"' "$SERVE_FILE"
     grep -q -- '-ub "$UBATCH_SIZE"' "$SERVE_FILE"
 }
 
+@test "large ubatch bench defaults to the active model and requested sweep" {
+    local bench="$REPO_ROOT/scripts/bench-ubatch-rocmi4.sh"
+    grep -q ': "${UBATCH_MIN:=256}"' "$bench"
+    grep -q ': "${UBATCH_MAX:=6144}"' "$bench"
+    grep -q 'UBATCH_VALUES.*256 512 768 1024 1280 1536 2048 3072 4096 5120 6144' "$bench"
+    grep -q ': "${STOPSVC:=1}"' "$bench"
+    grep -q ': "${CTX:=32768}"' "$bench"
+    grep -q ': "${BENCH_BATCH:=32768}"' "$bench"
+    grep -q 'MODEL_FILE' "$bench"
+    grep -q 'REASONING_FORMAT' "$bench"
+}
+
+@test "large ubatch bench cleans up scratch server on request failure" {
+    local bench="$REPO_ROOT/scripts/bench-ubatch-rocmi4.sh"
+    grep -q 'SCRATCH_PID=' "$bench"
+    grep -q 'kill.*SCRATCH_PID' "$bench"
+    grep -qF 'eval time =\s' "$bench"
+}
+
 @test "frank-default-large uses the tracked Qwen-Sharp template on :7770" {
     grep -q '^CHAT_TEMPLATE_FILE=' "$ENV_FILE"
     grep -q -- '--jinja' "$SERVE_FILE"

tests/mount_entropy.bats

@@ -0,0 +1,25 @@
+#!/usr/bin/env bats
+# Seam: the entropy helper unlocks the known LUKS-on-md device and mounts via
+# the host's fstab entry, preserving the existing mount options and directory
+# ownership rather than inventing a second mount configuration.
+
+load helpers
+
+@test "entropy helper is executable and has the expected safe shell shape" {
+    run bash -c "test -x '$REPO_ROOT/scripts/mount-entropy.sh'"
+    [ "$status" -eq 0 ]
+
+    run grep -E '^set -euo pipefail$' "$REPO_ROOT/scripts/mount-entropy.sh"
+    [ "$status" -eq 0 ]
+
+    run grep -F 'udisksctl unlock --block-device /dev/md0' "$REPO_ROOT/scripts/mount-entropy.sh"
+    [ "$status" -eq 0 ]
+
+    run grep -F 'sudo mount "$MOUNTPOINT"' "$REPO_ROOT/scripts/mount-entropy.sh"
+    [ "$status" -eq 0 ]
+}
+
+@test "entropy helper does not embed a secret or alter mount ownership" {
+    run grep -Eiq 'password|secret|chmod|chown' "$REPO_ROOT/scripts/mount-entropy.sh"
+    [ "$status" -eq 1 ]
+}

tests/searxng_limiter.bats

@@ -57,6 +57,38 @@ assert not missing, f"pass_ip missing {missing}; got {pass_ip}"
 PYEOF
 }
 
+@test "SearXNG outgoing policy allows modest VPN latency without retry amplification" {
+    python3 - "$REPO_ROOT/shared/searxng/settings.yml" <<'PYEOF'
+import sys, yaml
+with open(sys.argv[1]) as fh:
+    data = yaml.safe_load(fh)
+outgoing = data.get("outgoing", {})
+assert outgoing.get("request_timeout") == 5.0, outgoing
+assert outgoing.get("max_request_timeout") == 15.0, outgoing
+assert outgoing.get("retries") == 1, outgoing
+assert outgoing["request_timeout"] < outgoing["max_request_timeout"], outgoing
+PYEOF
+}
+
+@test "SearXNG default provider policy favors anonymous healthy engines" {
+    python3 - "$REPO_ROOT/shared/searxng/settings.yml" <<'PYEOF'
+import sys, yaml
+with open(sys.argv[1]) as fh:
+    data = yaml.safe_load(fh)
+engines = {entry["name"]: entry for entry in data.get("engines", [])}
+assert engines["bing"]["disabled"] is False, engines.get("bing")
+assert engines["bing"]["weight"] > 1, engines["bing"]
+assert engines["bing"]["paging"] is False, engines["bing"]
+assert engines["duckduckgo"]["disabled"] is False, engines["duckduckgo"]
+assert engines["duckduckgo"]["paging"] is False, engines["duckduckgo"]
+for name in ("google cse", "startpage", "brave"):
+    assert engines[name]["disabled"] is True, engines.get(name)
+    assert engines[name].get("inactive", False) is False, engines[name]
+for name in ("bing", "duckduckgo", "wikipedia"):
+    assert engines[name]["timeout"] == 5.0, engines[name]
+PYEOF
+}
+
 @test "deploy.sh copies limiter.toml into /opt/searxng/config" {
     grep -q "shared/searxng/limiter.toml" "$REPO_ROOT/scripts/deploy.sh" \
         || { echo "deploy.sh does not copy shared/searxng/limiter.toml"; return 1; }