llm: complete the Protoss rename on the wire — served ids frank-archon/dragoon/zealot

The 2026-10-08 rename moved the harness model ids and the homepage cards;
the served aliases on the wire stayed frank-primary/frank-large/
frank-secondary. This closes the gap: the alias each endpoint announces is
now the family name, while the services, units, scripts, env files and
runbooks keep the old names (container identity stays stable).

- scripts/frank-secondary.env ALIAS, scripts/frank-large.env
  HALOGEN_MODEL_ID, scripts/frank-primary.env FRANK_PRIMARY_SERVED_NAME
  (+ the two serve-script defaults/gate messages)
- seams re-pinned: frank_secondary/frank_large/frank_primary unit bats
- fleet harnesses retargeted: bench-probe, deep-probe, calib-push,
  fleet-probes-swift15, autoresearch(+measure), bench-threads-batch-http,
  bench-decode
- shared/homepage/docs.html: api-id annotations and the "switchover will
  rename the ids" footnote removed — the page's names are now the ids;
  opencode/Pi/curl examples send frank-zealot
- dankclaw/hermes/config.yaml.example: frank-large -> frank-dragoon and the
  live 262144 context (Hermes routes by served id; see Hermes.md)

Consumers with live state re-keyed out-of-band in the same window:
OpenWebUI (model row, access_grant, openai.api_configs model_ids) and the
Hermes config.yaml.

dankclaw/hermes/config.yaml.example

@@ -10,15 +10,15 @@ model:
   provider: dankclaw-large
   base_url: http://192.168.0.143:7770/v1
   api_key: not-needed
-  default: frank-large
+  default: frank-dragoon
 
 providers:
   dankclaw-large:
     api: http://192.168.0.143:7770/v1
     discover_models: false
     models:
-      frank-large:
-        context_length: 114688
+      frank-dragoon:
+        context_length: 262144
   dankserver-small:
     api: http://192.168.0.235:7770/v1
     discover_models: false
@@ -29,7 +29,7 @@ providers:
 # Auxiliary routing from the live configuration. Named providers route via
 # their `api:` URL; `custom` entries route by their explicit `base_url`.
 auxiliary:
-  vision: {provider: dankclaw-large, model: frank-large}
+  vision: {provider: dankclaw-large, model: frank-dragoon}
   web_extract: {provider: dankserver-small, model: frank-medium}
   compression: {provider: dankserver-small, model: frank-medium}
   skills_hub: {provider: dankserver-small, model: frank-medium}
@@ -50,8 +50,8 @@ auxiliary:
         effort: none
   memory_query_rewrite: {provider: custom, model: frank-medium, base_url: http://192.168.0.235:7770/v1}
   tts_audio_tags: {provider: custom, model: frank-medium, base_url: http://192.168.0.235:7770/v1}
-  triage_specifier: {provider: dankclaw-large, model: frank-large}
-  kanban_decomposer: {provider: dankclaw-large, model: frank-large}
+  triage_specifier: {provider: dankclaw-large, model: frank-dragoon}
+  kanban_decomposer: {provider: dankclaw-large, model: frank-dragoon}
   profile_describer: {provider: dankserver-small, model: frank-medium}
   curator: {provider: dankserver-small, model: frank-medium}
 

scripts/autoresearch-bench.py

@@ -104,7 +104,7 @@ def stream_completion(url: str, model: str, prompt: str):
 def main():
     ap = argparse.ArgumentParser()
     ap.add_argument("--url", default="http://127.0.0.1:7770")
-    ap.add_argument("--model", default="frank-large")
+    ap.add_argument("--model", default="frank-dragoon")
     args = ap.parse_args()
 
     with urllib.request.urlopen(args.url.rstrip("/") + "/v1/models",

scripts/autoresearch-frank-primary.sh

@@ -146,7 +146,7 @@ while n < TGT:
     n += len(seg) + 1
 prompt = " ".join(parts)
 json.dump(
-    {"model": "frank-primary", "prompt": prompt,
+    {"model": "frank-archon", "prompt": prompt,
      "max_tokens": 256, "temperature": 0.0, "stream": False,
      "stop": ["<|im_end|>"]},
     open(sys.argv[1], "w"),

scripts/autoresearch/frank-primary-measure.py

@@ -45,7 +45,7 @@ import urllib.error
 import urllib.request
 
 BASE = os.environ.get("AR_BASE", "http://127.0.0.1:7770")
-MODEL = os.environ.get("AR_MODEL", "frank-primary")
+MODEL = os.environ.get("AR_MODEL", "frank-archon")
 PROMPT_CEILING = int(os.environ.get("AR_PROMPT_CEILING", "100000"))
 DEPTHS = (115, 1056, 4096)
 WARM_TOKENS = 64

scripts/bench-decode.sh

@@ -57,7 +57,7 @@ run_bench() {
     # Warmup (small request)
     curl -s -m 60 http://127.0.0.1:$PORT/v1/chat/completions \
         -H "Content-Type: application/json" \
-        -d '{"model":"frank-large","messages":[{"role":"user","content":"Hi"}],"max_tokens":16,"stream":false}' > /dev/null 2>&1 || true
+        -d '{"model":"frank-dragoon","messages":[{"role":"user","content":"Hi"}],"max_tokens":16,"stream":false}' > /dev/null 2>&1 || true
     
     # Build 8K prompt
     local prompt

scripts/bench-probe.py

@@ -26,7 +26,7 @@ def build_prompt():
 def probe(salt):
     prompt = f"[probe {salt}]\n" + build_prompt()
     body = json.dumps({
-        "model": "frank-primary",
+        "model": "frank-archon",
         "prompt": prompt, "temperature": 0.0, "max_tokens": 512,
     }).encode()
     req = urllib.request.Request(URL, data=body,

scripts/bench-threads-batch-http.py

@@ -39,7 +39,7 @@ def send_prefill_request():
     with open(PROMPT_FILE, "r") as f:
         prompt = f.read()
     body = json.dumps({
-        "model": "frank-large",
+        "model": "frank-dragoon",
         "messages": [{"role": "user", "content": prompt}],
         "max_tokens": 1,
         "stream": False

scripts/calib-push.py

@@ -51,7 +51,7 @@ def tap_done(container):
 
 def push_one(url, prompt):
     body = json.dumps({
-        "model": "frank-primary",
+        "model": "frank-archon",
         "prompt": prompt,
         "max_tokens": 1,
         "temperature": 0,

scripts/deep-probe.py

@@ -18,7 +18,7 @@ def build():
 
 def main(salt):
     body = json.dumps({
-        "model": "frank-primary",
+        "model": "frank-archon",
         "messages": [{"role": "user", "content": f"[probe {salt}] Continue and summarize this material in English, 400 words.\n\n" + build()}],
         "temperature": 0.0, "max_tokens": 512,
         "stream": True, "stream_options": {"include_usage": True},

scripts/fleet-probes-swift15.sh

@@ -16,7 +16,7 @@ def png(color):
             + chunk(b"IHDR", struct.pack(">IIBBBBB", w, h, 8, 2, 0, 0, 0))
             + chunk(b"IDAT", zlib.compress(raw)) + chunk(b"IEND", b""))
 b64 = base64.b64encode(png((255, 0, 0))).decode()
-body = json.dumps({"model": "frank-primary", "max_tokens": 256, "temperature": 0,
+body = json.dumps({"model": "frank-archon", "max_tokens": 256, "temperature": 0,
     "messages": [{"role": "user", "content": [
         {"type": "image_url", "image_url": {"url": "data:image/png;base64," + b64}},
         {"type": "text", "text": "What color is this image? Answer with one word."}]}]}).encode()
@@ -30,7 +30,7 @@ PY
 
 echo "== tools (expect tool_calls)"
 curl -s -m 120 $B/chat/completions -H 'Content-Type: application/json' -d '{
- "model":"frank-primary","temperature":0,"max_tokens":128,
+ "model":"frank-archon","temperature":0,"max_tokens":128,
  "messages":[{"role":"user","content":"What is 23 times 47? Use the calculator tool."}],
  "tools":[{"type":"function","function":{"name":"calculator","description":"evaluate arithmetic",
  "parameters":{"type":"object","properties":{"expr":{"type":"string"}},"required":["expr"]}}}]}' \
@@ -40,17 +40,17 @@ echo "== reasoning_effort fold (xhigh/medium/low/high all 200 on froggeric v22.5
 for lvl in xhigh medium low high; do
   code=$(curl -s -o /dev/null -w "%{http_code}" -m 120 $B/chat/completions \
     -H 'Content-Type: application/json' \
-    -d "{\"model\":\"frank-primary\",\"max_tokens\":8,\"reasoning_effort\":\"$lvl\",\"messages\":[{\"role\":\"user\",\"content\":\"hi\"}]}")
+    -d "{\"model\":\"frank-archon\",\"max_tokens\":8,\"reasoning_effort\":\"$lvl\",\"messages\":[{\"role\":\"user\",\"content\":\"hi\"}]}")
   echo "  reasoning_effort=$lvl -> HTTP $code"
 done
 
 echo "== reasoning_content channel"
 curl -s -m 120 $B/chat/completions -H 'Content-Type: application/json' \
- -d '{"model":"frank-primary","max_tokens":64,"messages":[{"role":"user","content":"Is 97 prime? Think briefly."}]}' \
+ -d '{"model":"frank-archon","max_tokens":64,"messages":[{"role":"user","content":"Is 97 prime? Think briefly."}]}' \
  | python3 -c 'import json,sys; m=json.load(sys.stdin)["choices"][0]["message"]; print("has reasoning_content:", bool(m.get("reasoning_content")), "| content:", (m.get("content") or "")[:60].replace(chr(10)," "))'
 
 echo "== response_format json_object"
 curl -s -m 120 $B/chat/completions -H 'Content-Type: application/json' \
- -d '{"model":"frank-primary","max_tokens":64,"response_format":{"type":"json_object"},"messages":[{"role":"user","content":"Return JSON {\"ok\": true}"}]}' \
+ -d '{"model":"frank-archon","max_tokens":64,"response_format":{"type":"json_object"},"messages":[{"role":"user","content":"Return JSON {\"ok\": true}"}]}' \
  | python3 -c 'import json,sys; d=json.load(sys.stdin); print("JSON MODE:", (d["choices"][0]["message"].get("content") or "")[:60])'
 echo "PROBES_DONE"

scripts/frank-large.env

@@ -130,7 +130,10 @@ FRANK_LARGE_TOKENIZER_FILES="tokenizer.json chat_template.jinja tokenizer_config
 
 # --- engine flags (docs/FLAGS.md of the flash-server repo; anything unset
 # stays at the image default, which is what was qualified) ------------------
-HALOGEN_MODEL_ID=frank-large
+# Served model id — Protoss name (wire rename 2026-10-09); the service, unit,
+# scripts and this file keep the frank-large name. OpenWebUI api_configs
+# model_ids for the :7770 backend MUST name this value.
+HALOGEN_MODEL_ID=frank-dragoon
 HALOGEN_CTX=262144
 HALOGEN_KV_POOL_POSITIONS=524288
 HALOGEN_KV_SLOTS=2

scripts/frank-primary.env

@@ -86,7 +86,11 @@ FRANK_PRIMARY_STATE_DIR=/home/dank/radiance-state
 # the GPUs or the port.
 FRANK_PRIMARY_CONTAINER=frank-primary
 FRANK_PRIMARY_LEGACY_CONTAINERS="frank-primary-qwen frank-primary-r9v qwen-fp8 glm-probe"
-FRANK_PRIMARY_SERVED_NAME=frank-primary
+# Served model id — Protoss name (wire rename 2026-10-09). The container,
+# unit, scripts and this file keep the frank-primary name above; only the
+# alias on the wire moved. Radiance validates the requested model name, so
+# every client (harness, bench scripts, probes) MUST send this value.
+FRANK_PRIMARY_SERVED_NAME=frank-archon
 FRANK_PRIMARY_PORT=7770
 # Frank's chat-template call: froggeric's fixed Qwen3.8 template (the
 # repo's root chat_template.jinja, vendored here; the checkpoint's own

scripts/frank-secondary.env

@@ -35,7 +35,13 @@
 LLAMA_BIN=/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server
 MODEL_FILE=/home/dank/models/Qwen35-9B-HauhauCS-Q6K/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf
 MMPROJ_FILE=/home/dank/models/Qwen35-9B-HauhauCS-Q6K/mmproj-Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-BF16.gguf
-ALIAS=frank-secondary
+# Served model id — the harness/family name (Protoss rename completed to the
+# wire 2026-10-09: harness ids + homepage cards 2026-10-08, /v1/models aliases
+# this day). The SERVICE, unit, scripts and this env file keep the
+# frank-secondary name; only the alias on the wire changed. Consumers that
+# key on the served id: OpenWebUI (model row, access_grant, api_configs
+# model_ids) and the harness models.yml.
+ALIAS=frank-zealot
 BIND_ADDR=0.0.0.0
 LISTEN_PORT=7771
 # CTX_SIZE is the POOL llama.cpp divides across slots: 401,408 / 2 = 200,704

scripts/serve-frank-large.sh

@@ -51,7 +51,7 @@ set +a
 : "${FRANK_LARGE_VISION_TOWER:?FRANK_LARGE_VISION_TOWER must name the tower}"
 : "${FRANK_LARGE_VISION_BYTES:?FRANK_LARGE_VISION_BYTES must pin the tower size}"
 : "${FRANK_LARGE_TOKENIZER_FILES:?FRANK_LARGE_TOKENIZER_FILES must list the tokenizer dir contents}"
-: "${HALOGEN_MODEL_ID:?HALOGEN_MODEL_ID must be the served alias (frank-large)}"
+: "${HALOGEN_MODEL_ID:?HALOGEN_MODEL_ID must be the served alias (frank-dragoon)}"
 : "${HALOGEN_CTX:?HALOGEN_CTX must be set (per-slot window)}"
 : "${HALOGEN_KV_POOL_POSITIONS:?HALOGEN_KV_POOL_POSITIONS must be set}"
 : "${HALOGEN_KV_SLOTS:?HALOGEN_KV_SLOTS must be set}"

scripts/serve-frank-secondary.sh

@@ -39,7 +39,7 @@ fi
 # --- defaults (used when the env file does not set them) -------------------
 : "${LLAMA_BIN:=/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server}"
 : "${MODEL_FILE:=/home/dank/models/Qwen35-9B-HauhauCS-Q6K/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf}"
-: "${ALIAS:=frank-secondary}"
+: "${ALIAS:=frank-zealot}"
 : "${BIND_ADDR:=0.0.0.0}"
 : "${LISTEN_PORT:=7771}"
 # ctx-size is the POOL llama.cpp divides across slots: 401,408 / 2 = 200,704

shared/homepage/docs.html

@@ -70,8 +70,7 @@
   conversations are saved to your account, so history follows you between devices.</p>
   <img src="img/openwebui-chat.png" alt="Open WebUI chat screen with a question and the AI's answer">
   <p>Below the text box, the model box on the right chooses which model answers you.
-  Family accounts get <code>frank-zealot</code> — the fleet's fast all-rounder
-  (Open&nbsp;WebUI lists models by their API id; this one is <code>frank-secondary</code>),
+  Family accounts get <code>frank-zealot</code> — the fleet's fast all-rounder,
   which also sees images: drag a photo or screenshot straight into the chat box.
   Frank's account can additionally reach the bigger models.</p>
   <img src="img/openwebui-model-picker.png" alt="The Open WebUI welcome screen with the family model selected in the model box">
@@ -85,11 +84,11 @@
   The homepage "Model Information" panel shows whether each one is up right now —
   and plays the unit's voice if you click its quoted line.</p>
 
-  <p class="foot-note">Naming: the Open&nbsp;WebUI picker and the raw API show the
-  endpoint <em>api ids</em> in brackets below. The Protoss names are the family
-  names; a future switchover will rename the ids to match.</p>
+  <p class="foot-note">Naming: the Open&nbsp;WebUI picker and the raw API show
+  exactly the Protoss names used on this page (renamed 2026-10-09). The name you
+  read here is the name you type into a config file.</p>
 
-  <h2>frank-zealot — the fast utility model <em>(api id: frank-secondary)</em></h2>
+  <h2>frank-zealot — the fast utility model</h2>
   <ul>
     <li><strong>Model:</strong> <a href="https://huggingface.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive" target="_blank" rel="noopener">Qwen3.5-9B-Uncensored</a> (Q6_K) on the RTX&nbsp;3090 — roughly 95 tokens per second.</li>
     <li><strong>Equivalent:</strong> last year's frontier level (2025).</li>
@@ -101,7 +100,7 @@
     <li><strong>Warning:</strong> <details class="key-warn"><summary>&#9888; uncensored model</summary><div class="warn-body">Uncensored model: output can include adult content, content that describes harmful, hateful, or illegal acts, content concerning &ldquo;sensitive offensive cybersecurity topics&rdquo;, and other output that may carry severe legal risk. Take this warning seriously &mdash; don&rsquo;t ruin this server for everybody.</div></details></li>
   </ul>
 
-  <h2>frank-dragoon — deep reasoning <em>(api id: frank-large)</em></h2>
+  <h2>frank-dragoon — deep reasoning</h2>
   <ul>
     <li><strong>Model:</strong> <a href="https://huggingface.co/Quat3rnion/halogen-swift1.5-qwen3.8-flash-next-v2-abliterated" target="_blank" rel="noopener">Qwen3.8-Flash-Next v2 Swift1.5 abliterated</a> (halogen flash-server, ~62&nbsp;GiB) on the Strix Halo iGPU — an abliterated (censorship-removed) edition that thinks before answering.</li>
     <li><strong>Equivalent:</strong> Claude Sonnet 5 / OpenAI-Luna (Summer 2026 frontier intelligence).</li>
@@ -111,7 +110,7 @@
     <li><strong>Supervision:</strong> safe for autonomous, low-supervision use.</li>
     <li><strong>Warning:</strong> <details class="key-warn"><summary>&#9888; uncensored model</summary><div class="warn-body">Uncensored model: output can include adult content, content that describes harmful, hateful, or illegal acts, content concerning &ldquo;sensitive offensive cybersecurity topics&rdquo;, and other output that may carry severe legal risk. Take this warning seriously &mdash; don&rsquo;t ruin this server for everybody.</div></details></li>
 
-  <h2>frank-archon — the big one <em>(api id: frank-primary)</em></h2>
+  <h2>frank-archon — the big one</h2>
   <ul>
     <li><strong>Model:</strong> our own build — a GPTQ-w4 quant of <a href="https://huggingface.co/frank8465/Swift-1.5-Qwen3.8-Flash-Next-GPTQ-W4A8-Radiance-AMD-R9700" target="_blank" rel="noopener">Swift1.5-Qwen3.8-Flash-Next</a>, quantized and tuned in-house (radiance, ~114&nbsp;GiB) on twin AMD R9700s with more than 200&nbsp;GB of system RAM — the biggest brain on the network and the fastest runtime.</li>
     <li><strong>Equivalent:</strong> Claude Opus 4.8 / OpenAI-Terra (Summer 2026 frontier intelligence).</li>
@@ -123,9 +122,8 @@
   <p class="foot-note">Which one to pick? Small utility work, autocomplete, RAG,
   programming, and personal agents: <code>frank-dragoon</code>. Software
   engineering, sysadmin, and instruction tasks: <code>frank-archon</code> (ask
-  Frank first). The ids in brackets are what the Open&nbsp;WebUI picker and the
-  raw API show today; the Protoss names are the family names, and the switchover
-  will rename the ids to match.</p>
+  Frank first). Every name on this page is the id the Open&nbsp;WebUI picker and
+  the raw API answer to.</p>
 </section>
 
 <section id="api-access">
@@ -154,14 +152,14 @@
   <h2>Step 2 — the three details every tool asks for</h2>
   <ul>
     <li><strong>Base URL:</strong> <code>https://ai.franksdank.cloud/api/v1</code></li>
-    <li><strong>Model:</strong> <code>frank-secondary</code> — this is <code>frank-zealot</code>, the family utility model (the API uses the id, not the family name)</li>
+    <li><strong>Model:</strong> <code>frank-zealot</code> — the family utility model (this is the id the API expects)</li>
     <li><strong>API key:</strong> the <code>sk-…</code> from step 1 — sent as the header <code>Authorization: Bearer sk-…</code></li>
   </ul>
   <p>Proof that it works, from any terminal (replace the key):</p>
   <pre><code>curl https://ai.franksdank.cloud/api/v1/chat/completions \
   -H "Authorization: Bearer PASTE-YOUR-KEY" \
   -H "Content-Type: application/json" \
-  -d '{"model": "frank-secondary", "messages": [{"role": "user", "content": "Hello!"}]}'</code></pre>
+  -d '{"model": "frank-zealot", "messages": [{"role": "user", "content": "Hello!"}]}'</code></pre>
 
   <h2>Step 3a — Opencode</h2>
   <p>Install once (<code>npm install -g opencode-ai</code>), then create the file
@@ -177,13 +175,13 @@
         "apiKey": "PASTE-YOUR-KEY"
       },
       "models": {
-        "frank-secondary": { "name": "frank-secondary" }
+        "frank-zealot": { "name": "frank-zealot" }
       }
     }
   }
 }</code></pre>
   <p>Start <code>opencode</code> and pick the model with <code>/model</code> —
-  it appears as <code>frank/frank-secondary</code>.</p>
+  it appears as <code>frank/frank-zealot</code>.</p>
 
   <h2>Step 3b — Pi</h2>
   <p>Create the file <code>~/.pi/agent/models.json</code> with:</p>
@@ -194,12 +192,12 @@
       "api": "openai-completions",
       "apiKey": "PASTE-YOUR-KEY",
       "models": [
-        { "id": "frank-secondary" }
+        { "id": "frank-zealot" }
       ]
     }
   }
 }</code></pre>
-  <p>Then start Pi with <code>pi --model frank/frank-secondary</code>.</p>
+  <p>Then start Pi with <code>pi --model frank/frank-zealot</code>.</p>
 
   <p class="foot-note">The key works only for the family AI — it is not your
   Authentik password, and losing it costs nothing beyond asking Frank to rotate it.

tests/frank_large_unit.bats

@@ -79,7 +79,7 @@ good_env() {
         "FRANK_LARGE_VISION_TOWER=vision.hgn"
         "FRANK_LARGE_VISION_BYTES=0"
         "FRANK_LARGE_TOKENIZER_FILES=tok.json"
-        "HALOGEN_MODEL_ID=frank-large"
+        "HALOGEN_MODEL_ID=frank-dragoon"
         "HALOGEN_CTX=262144"
         "HALOGEN_KV_POOL_POSITIONS=524288"
         "HALOGEN_KV_SLOTS=2"
@@ -104,7 +104,7 @@ good_env() {
     grep -qE '^FRANK_LARGE_VISION_BYTES=[0-9]+$' "$ENV_FILE"
     grep -qE '^FRANK_LARGE_VISION_SHA256=[0-9a-f]{64}$' "$ENV_FILE"
     grep -qE '^FRANK_LARGE_TOKENIZER_FILES="tokenizer\.json( [a-z_.]+)+"$' "$ENV_FILE"
-    grep -qE '^HALOGEN_MODEL_ID=frank-large$' "$ENV_FILE"
+    grep -qE '^HALOGEN_MODEL_ID=frank-dragoon$' "$ENV_FILE"
     grep -qE '^HALOGEN_CTX=[0-9]+$' "$ENV_FILE"
 }
 
@@ -262,7 +262,7 @@ good_env() {
 $(cat "$TEST_TMP/serve.log")"
     [[ "$output" == *"--name frank-large-halogen"* ]]
     [[ "$output" == *"--publish 7770:8731"* ]]
-    [[ "$output" == *"-e HALOGEN_MODEL_ID=frank-large"* ]]
+    [[ "$output" == *"-e HALOGEN_MODEL_ID=frank-dragoon"* ]]
     [[ "$output" == *"-e HALOGEN_CTX=262144"* ]]
     [[ "$output" == *"-e HALOGEN_KV_POOL_POSITIONS=524288"* ]]
     [[ "$output" == *"-e HALOGEN_KV_SLOTS=2"* ]]

tests/frank_primary_unit.bats

@@ -186,7 +186,7 @@ TEMPLATE="$REPO_ROOT/scripts/qwen38-froggeric-v22.5.jinja"
     ! grep -q -- '--publish' "$SERVE"
     ! grep -q -- '-p 7770' "$SERVE"
     grep -q '^FRANK_PRIMARY_PORT=7770$' "$ENV_FILE"
-    grep -q '^FRANK_PRIMARY_SERVED_NAME=frank-primary$' "$ENV_FILE"
+    grep -q '^FRANK_PRIMARY_SERVED_NAME=frank-archon$' "$ENV_FILE"
     grep -q -- '--init' "$SERVE"
     grep -q -- '--security-opt seccomp=unconfined' "$SERVE"
     grep -q -- '--ulimit memlock=-1' "$SERVE"

tests/frank_secondary_unit.bats

@@ -50,7 +50,7 @@ serve_argv() {
 LLAMA_BIN=$RUNTIME_DIR/bin/llama-server
 MODEL_FILE=$MODEL_DIR/$MODEL_STUB
 MMPROJ_FILE=$MODEL_DIR/$MM_STUB
-ALIAS=frank-secondary
+ALIAS=frank-zealot
 BIND_ADDR=0.0.0.0
 LISTEN_PORT=7771
 CTX_SIZE=$(sed -nE 's/^CTX_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")
@@ -118,7 +118,7 @@ run_stage() {
 @test "two conversations share the pool at a 200704 window each" {
     serve_argv
     [ "$status" -eq 0 ]
-    [ "$(argv_value --alias)" = "frank-secondary" ]
+    [ "$(argv_value --alias)" = "frank-zealot" ]
     [ "$(argv_value --port)" = "7771" ]
     [ "$(argv_value --host)" = "0.0.0.0" ]
     [ "$(argv_value --model)" = "$MODEL_DIR/$MODEL_STUB" ]