feat(model-server): source Hugging Face (-hf) + options structurées llama.cpp + migration store V2

Backend du support natif d'une source modèle Hugging Face en alternative au
chemin .gguf local pour le serveur llama.cpp intégré, et refonte des options.

- domaine : ModelSource {LocalPath|HuggingFace} + HfModelRef,
  LlamaCppOptions {host,gpu_layers,context_size,jinja}, invariant auto_start
  exigeant une source, validate_free_args (rejet des flags réservés).
- infra : build_argv partagé avec build_spawn_spec, émission -hf vs --model,
  ordre argv figé ; migration model-servers.json V1 -> V2.
- app-tauri : DTO V2 (modelSource, compat modelPath, conflit = INVALID),
  commande preview_model_server_command.

QA : cargo test ciblés verts (domain 7, application 8, infra model_server 4,
app-tauri dto 5). Échecs des suites complètes infra/app-tauri environnementaux
(sandbox bind/socket), hors périmètre.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
2026-07-12 14:31:54 +02:00
parent bc96285fa5
commit 38aecf2cac
11 changed files with 820 additions and 102 deletions

View File

@ -116,6 +116,81 @@ impl ModelPath {
}
}
/// Explicit source of the served model.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "camelCase", tag = "type")]
pub enum ModelSource {
/// Local `.gguf` file path.
LocalPath {
/// Absolute local path.
path: ModelPath,
},
/// Hugging Face llama.cpp `-hf` reference.
HuggingFace {
/// `namespace/repo` or `namespace/repo:quant`.
repo: HfModelRef,
},
}
/// Hugging Face model reference accepted by `llama-server -hf`.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
#[serde(transparent)]
pub struct HfModelRef(pub String);
impl HfModelRef {
/// Builds a validated Hugging Face model reference.
///
/// # Errors
/// Returns [`DomainError`] if the reference is blank, URL-like, contains
/// spaces, or does not match `namespace/repo[:quant]`.
pub fn new(repo: impl Into<String>) -> Result<Self, DomainError> {
let repo = repo.into();
crate::validation::non_empty(&repo, "modelServer.model.source.repo")?;
if repo.chars().any(char::is_whitespace) {
return Err(DomainError::Invariant(
"modelServer.model.source.repo must not contain spaces".to_owned(),
));
}
if repo.starts_with("http://") || repo.starts_with("https://") {
return Err(DomainError::Invariant(
"modelServer.model.source.repo must not be an URL in V1".to_owned(),
));
}
if repo.matches(':').count() > 1 {
return Err(DomainError::Invariant(
"modelServer.model.source.repo must contain at most one ':'".to_owned(),
));
}
let (base, quant) = repo
.split_once(':')
.map_or((repo.as_str(), None), |(base, quant)| (base, Some(quant)));
let Some((namespace, name)) = base.split_once('/') else {
return Err(DomainError::Invariant(
"modelServer.model.source.repo must be namespace/repo or namespace/repo:quant"
.to_owned(),
));
};
if namespace.is_empty() || name.is_empty() || base.matches('/').count() != 1 {
return Err(DomainError::Invariant(
"modelServer.model.source.repo must be namespace/repo or namespace/repo:quant"
.to_owned(),
));
}
if quant.is_some_and(str::is_empty) {
return Err(DomainError::Invariant(
"modelServer.model.source.repo quant must not be empty".to_owned(),
));
}
Ok(Self(repo))
}
/// Returns the reference as a string slice.
#[must_use]
pub fn as_str(&self) -> &str {
&self.0
}
}
/// Absolute local path to an executable.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
#[serde(transparent)]
@ -159,9 +234,9 @@ pub struct LocalModelRef {
pub id: String,
/// Human display label.
pub label: String,
/// Explicit absolute `.gguf` path. Required for auto-start.
/// Explicit source. Required for auto-start.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub path: Option<ModelPath>,
pub source: Option<ModelSource>,
/// Name exposed by the server and used in `OpenCodeConfig.model`.
pub served_name: String,
}
@ -174,7 +249,7 @@ impl LocalModelRef {
pub fn new(
id: impl Into<String>,
label: impl Into<String>,
path: Option<ModelPath>,
source: Option<ModelSource>,
served_name: impl Into<String>,
) -> Result<Self, DomainError> {
let id = id.into();
@ -186,12 +261,121 @@ impl LocalModelRef {
Ok(Self {
id,
label,
path,
source,
served_name,
})
}
}
/// Structured llama.cpp server options owned by IdeA.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
pub struct LlamaCppOptions {
/// Host passed to `--host`.
pub host: String,
/// GPU layers passed to `-ngl`.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub gpu_layers: Option<u32>,
/// Context size passed to `-c`.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub context_size: Option<u32>,
/// Enables llama.cpp Jinja templates.
pub jinja: bool,
}
impl Default for LlamaCppOptions {
fn default() -> Self {
Self {
host: "127.0.0.1".to_owned(),
gpu_layers: None,
context_size: None,
jinja: false,
}
}
}
impl LlamaCppOptions {
/// Builds validated llama.cpp options.
///
/// # Errors
/// Returns [`DomainError`] if host is blank/contains spaces or numeric
/// options are zero.
pub fn new(
host: impl Into<String>,
gpu_layers: Option<u32>,
context_size: Option<u32>,
jinja: bool,
) -> Result<Self, DomainError> {
let options = Self {
host: host.into(),
gpu_layers,
context_size,
jinja,
};
options.validate()?;
Ok(options)
}
/// Validates option invariants.
///
/// # Errors
/// Returns [`DomainError`] on invalid options.
pub fn validate(&self) -> Result<(), DomainError> {
crate::validation::non_empty(&self.host, "modelServer.options.host")?;
if self.host.chars().any(char::is_whitespace) {
return Err(DomainError::Invariant(
"modelServer.options.host must not contain spaces".to_owned(),
));
}
if self.gpu_layers == Some(0) {
return Err(DomainError::Invariant(
"modelServer.options.gpuLayers must be > 0".to_owned(),
));
}
if self.context_size == Some(0) {
return Err(DomainError::Invariant(
"modelServer.options.contextSize must be > 0".to_owned(),
));
}
Ok(())
}
}
/// Validates free-form runtime arguments do not duplicate structured options.
///
/// # Errors
/// Returns [`DomainError`] if an argument is a reserved exact flag or
/// `--flag=value` form.
pub fn validate_free_args(args: &[String]) -> Result<(), DomainError> {
const RESERVED: &[&str] = &[
"--model",
"-m",
"-hf",
"--port",
"--host",
"-ngl",
"--gpu-layers",
"-c",
"--ctx-size",
"--jinja",
];
for arg in args {
if RESERVED.contains(&arg.as_str()) {
return Err(DomainError::Invariant(format!(
"modelServer.args contains reserved flag {arg}"
)));
}
if let Some((flag, _)) = arg.split_once('=') {
if RESERVED.contains(&flag) {
return Err(DomainError::Invariant(format!(
"modelServer.args contains reserved flag {flag}"
)));
}
}
}
Ok(())
}
/// Stop policy for a managed local model server.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
@ -221,6 +405,8 @@ pub struct LocalModelServerConfig {
/// Optional executable path or bare command name.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub binary: Option<ExecutablePath>,
/// Structured llama.cpp options.
pub options: LlamaCppOptions,
/// Extra argv passed to the runtime.
#[serde(default)]
pub args: Vec<String>,
@ -249,21 +435,24 @@ impl LocalModelServerConfig {
endpoint: ModelServerEndpoint,
model: LocalModelRef,
binary: Option<ExecutablePath>,
options: LlamaCppOptions,
args: Vec<String>,
auto_start: bool,
stop_policy: StopPolicy,
) -> Result<Self, DomainError> {
let name = name.into();
crate::validation::non_empty(&name, "modelServer.name")?;
options.validate()?;
validate_free_args(&args)?;
if auto_start {
if kind != LocalModelServerKind::LlamaCpp {
return Err(DomainError::Invariant(
"modelServer.autoStart requires kind=LlamaCpp".to_owned(),
));
}
if model.path.is_none() {
if model.source.is_none() {
return Err(DomainError::Invariant(
"modelServer.autoStart requires model.path".to_owned(),
"modelServer.autoStart requires model.source".to_owned(),
));
}
}
@ -274,6 +463,7 @@ impl LocalModelServerConfig {
endpoint,
model,
binary,
options,
args,
auto_start,
stop_policy,
@ -342,13 +532,12 @@ mod tests {
fn endpoint_rejects_remote_host() {
let err = ModelServerEndpoint::new("http://example.com:8080", 8080).unwrap_err();
assert!(err.to_string().contains("localhost"));
let err =
ModelServerEndpoint::new("http://127.0.0.1.evil.com:8080", 8080).unwrap_err();
let err = ModelServerEndpoint::new("http://127.0.0.1.evil.com:8080", 8080).unwrap_err();
assert!(err.to_string().contains("localhost"));
}
#[test]
fn auto_start_requires_model_path() {
fn auto_start_requires_model_source() {
let endpoint = ModelServerEndpoint::new("http://localhost:8080/v1", 8080).unwrap();
let model = LocalModelRef::new("qwen", "Qwen", None, "qwen").unwrap();
let err = LocalModelServerConfig::new(
@ -358,11 +547,47 @@ mod tests {
endpoint,
model,
None,
LlamaCppOptions::default(),
Vec::new(),
true,
StopPolicy::StopOnAppExit,
)
.unwrap_err();
assert!(err.to_string().contains("model.path"));
assert!(err.to_string().contains("model.source"));
}
#[test]
fn hf_model_ref_accepts_repo_and_optional_quant() {
assert_eq!(
HfModelRef::new("Qwen/Qwen3-Coder:Q4_K_M").unwrap().as_str(),
"Qwen/Qwen3-Coder:Q4_K_M"
);
assert!(HfModelRef::new("Qwen/Qwen3 Coder").is_err());
assert!(HfModelRef::new("https://huggingface.co/Qwen/Qwen3").is_err());
assert!(HfModelRef::new("Qwen").is_err());
assert!(HfModelRef::new("a/b:c:d").is_err());
}
#[test]
fn validate_free_args_rejects_reserved_flags_token_and_equals() {
for flag in [
"--model",
"-m",
"-hf",
"--port",
"--host",
"-ngl",
"--gpu-layers",
"-c",
"--ctx-size",
"--jinja",
] {
assert!(validate_free_args(&[flag.to_owned()]).is_err(), "{flag}");
assert!(
validate_free_args(&[format!("{flag}=value")]).is_err(),
"{flag}=value"
);
}
validate_free_args(&["--threads".to_owned(), "8".to_owned()]).unwrap();
}
}