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.
This commit is contained in:
Frank
@@ -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",
|
||||
|
||||
@@ -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"),
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -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},
|
||||
|
||||
@@ -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"
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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}"
|
||||
: "${HALOGEN_KV_SLOTS:?HALOGEN_KV_SLOTS must be set}"
|
||||
|
||||
@@ -39,7 +39,7 @@ fi
|
||||
# --- defaults (used when the env file does not set them) -------------------
|
||||
: "${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
|
||||
|
||||
Reference in New Issue
Block a user