helm/ulysses
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Detect llama.cpp server readiness for auto-endpoint registration
Some checks are pending
CI / Focused test guidance (report-only) (push) Waiting to run
Details
CI / Python syntax (compileall) (push) Waiting to run
Details
CI / JS syntax (node --check) (push) Waiting to run
Details
CI / Python tests (pytest) (push) Waiting to run
Details
Container scan / hadolint (Dockerfile lint) (push) Waiting to run
Details
Container scan (Trivy) / Trivy (image scan, advisory) (push) Waiting to run
Details
Container scan (Trivy) / Trivy (image scan + SARIF upload) (push) Waiting to run
Details
Dependency review / dependency-review (PR gate) (push) Waiting to run
Details
Dependency review / pip-audit (advisory) (push) Waiting to run
Details
ci / docker publish / build (amd64) (push) Waiting to run
Details
ci / docker publish / build (arm64) (push) Waiting to run
Details
ci / docker publish / merge manifest + tag (push) Blocked by required conditions
Details
Secret scan / gitleaks (push) Waiting to run
Details
Workflow security / actionlint (push) Waiting to run
Details
Workflow security / zizmor (Actions SAST) (push) Waiting to run
Details

Browse source 
_parseServePhase only recognized vLLM, FastAPI, and Ollama ready states.
llama-server's output ('server is listening on http://...') didn't match
any pattern, so _serveReady was never set and auto-registration never fired.
Added regex matching llamacpp-style listening messages.
This commit is contained in:
Lukas Parsons 2026-07-07 00:26:47 -04:00
parent 6918d9417f
commit 80f38c9443
1 changed files with 4 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
static/js/cookbookRunning.js
View file

@ -408,6 +408,10 @@ export function _parseServePhase(snapshot) {
if (/Ollama API ready on port\s+\d+/i.test(flat)) { if (/Ollama API ready on port\s+\d+/i.test(flat)) {
return { phase: 'ready', status: 'ready' }; return { phase: 'ready', status: 'ready' };
} }
// llama.cpp server (llama-server / llama-cli) — "server is listening" variants
if (/(?:server is listening|HTTP server listening|listening on (?:http|port))/i.test(flat)) {
return { phase: 'ready', status: 'ready' };
}
const llamaBuildMatches = [...flat.matchAll(/\[\s*(\d{1,3})%\]\s*(?:Building|Linking)/gi)]; const llamaBuildMatches = [...flat.matchAll(/\[\s*(\d{1,3})%\]\s*(?:Building|Linking)/gi)];
if (llamaBuildMatches.length) { if (llamaBuildMatches.length) {
const pct = Math.min(100, parseInt(llamaBuildMatches[llamaBuildMatches.length - 1][1], 10)); const pct = Math.min(100, parseInt(llamaBuildMatches[llamaBuildMatches.length - 1][1], 10));