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:
1 parent
65dec6a80e
commit
7c77326c33
19 files changed
+58
-47
No files matched your search
@@ -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"* ]]
|
||||
[[ "$output" == *"-e HALOGEN_KV_SLOTS=2"* ]]
|
||||
|
||||
@@ -186,7 +186,7 @@ TEMPLATE="$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' "$SERVE"
|
||||
|
||||
@@ -50,7 +50,7 @@ serve_argv() {
|
||||
LLAMA_BIN=$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" ]
|
||||
|
||||
Reference in new issue
Block a user