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

@ -26,12 +26,14 @@ use application::{
UnassignSkillFromAgentInput, UpdateAgentContextInput, UpdateAgentPermissionsInput,
UpdateMemoryInput, UpdateProjectContextInput, UpdateProjectPermissionsInput, UpdateSkillInput,
};
use domain::ports::ModelServerRuntime;
use domain::ports::PtyHandle;
use crate::dto::{
parse_agent_id, parse_close_terminal, parse_delete_profile, parse_layout_id, parse_memory_slug,
parse_node_id, parse_profile_id, parse_project_id, parse_session_id, parse_skill_id,
parse_task_id, parse_template_id, parse_ticket_id, AgentDriftListDto, AgentDto, AgentListDto,
model_server_config_domain, parse_agent_id, parse_close_terminal, parse_delete_profile,
parse_layout_id, parse_memory_slug, parse_model_server_id, parse_node_id, parse_profile_id,
parse_project_id, parse_session_id, parse_skill_id, parse_task_id, parse_template_id,
parse_ticket_id, save_model_server_input, AgentDriftListDto, AgentDto, AgentListDto,
AssignSkillRequestDto, AttachLiveAgentRequestDto, AttachLiveAgentResponseDto,
BackgroundTaskDto, ChangeAgentProfileDto, ChangeAgentProfileRequestDto,
CloneOpenCodeProfileFromSeedRequestDto, ConfigureProfilesRequestDto, ConversationDetailsDto,
@ -45,19 +47,19 @@ use crate::dto::{
GraphCommitListDto, HealthRequestDto, HealthResponseDto, InspectConversationRequestDto,
InterruptAgentRequestDto, LaunchAgentRequestDto, LayoutDto, LayoutOperationDto, ListLayoutsDto,
LiveAgentListDto, MemoryDto, MemoryIndexDto, MemoryLinksDto, MemoryListDto,
ModelServerConfigDto, ModelServerConfigListDto, OpenTerminalRequestDto, ProfileDto,
ProfileListDto, ProjectDto, ProjectListDto, ProjectPermissionsDto, ProjectWorkStateDto,
ReadAgentContextResponseDto, ReadConversationPageRequestDto, ReattachChatDto,
ReattachResultDto, RecallMemoryRequestDto, RenameLayoutRequestDto, ReplyChunk,
ResizeTerminalRequestDto, ResolveAgentPermissionsRequestDto, ResumableAgentListDto,
SaveEmbedderProfileRequestDto, SaveModelServerRequestDto, SaveProfileRequestDto,
SetActiveLayoutRequestDto, SetActiveLayoutResultDto, SkillDto, SkillListDto,
StopLiveAgentRequestDto, StopLiveAgentResponseDto, SyncAgentWithTemplateRequestDto,
SyncResultDto, TemplateDto, TemplateListDto, TerminalClosedDto, TerminalSessionDto,
TurnPageDto, UnassignSkillRequestDto, UpdateAgentContextRequestDto,
UpdateAgentPermissionsRequestDto, UpdateMemoryRequestDto, UpdateProjectContextRequestDto,
UpdateProjectPermissionsRequestDto, UpdateSkillRequestDto, UpdateTemplateRequestDto,
WriteTerminalRequestDto, parse_model_server_id, save_model_server_input,
ModelServerConfigDto, ModelServerConfigListDto, OpenTerminalRequestDto,
PreviewModelServerCommandDto, ProfileDto, ProfileListDto, ProjectDto, ProjectListDto,
ProjectPermissionsDto, ProjectWorkStateDto, ReadAgentContextResponseDto,
ReadConversationPageRequestDto, ReattachChatDto, ReattachResultDto, RecallMemoryRequestDto,
RenameLayoutRequestDto, ReplyChunk, ResizeTerminalRequestDto,
ResolveAgentPermissionsRequestDto, ResumableAgentListDto, SaveEmbedderProfileRequestDto,
SaveModelServerRequestDto, SaveProfileRequestDto, SetActiveLayoutRequestDto,
SetActiveLayoutResultDto, SkillDto, SkillListDto, StopLiveAgentRequestDto,
StopLiveAgentResponseDto, SyncAgentWithTemplateRequestDto, SyncResultDto, TemplateDto,
TemplateListDto, TerminalClosedDto, TerminalSessionDto, TurnPageDto, UnassignSkillRequestDto,
UpdateAgentContextRequestDto, UpdateAgentPermissionsRequestDto, UpdateMemoryRequestDto,
UpdateProjectContextRequestDto, UpdateProjectPermissionsRequestDto, UpdateSkillRequestDto,
UpdateTemplateRequestDto, WriteTerminalRequestDto,
};
use crate::pty::{PtyBridge, PtyChunk};
use crate::state::AppState;
@ -900,6 +902,28 @@ pub async fn save_model_server(
.map_err(ErrorDto::from)
}
/// `preview_model_server_command` — build the llama.cpp argv without persisting.
///
/// # Errors
/// Returns an [`ErrorDto`] when the DTO or runtime invocation is invalid.
#[tauri::command]
pub fn preview_model_server_command(
config: ModelServerConfigDto,
) -> Result<PreviewModelServerCommandDto, ErrorDto> {
let config = model_server_config_domain(config, None)?;
let argv = infrastructure::LlamaCppRuntime::new()
.build_argv(&config)
.map_err(|err| ErrorDto {
code: "INVALID".to_owned(),
message: err.to_string(),
})?;
Ok(PreviewModelServerCommandDto {
display: display_command(&argv.command, &argv.args),
command: argv.command,
args: argv.args,
})
}
/// `delete_model_server` — delete a local model server config when unused.
///
/// # Errors
@ -924,6 +948,27 @@ fn model_server_command_error(err: AppError) -> ErrorDto {
}
}
fn display_command(command: &str, args: &[String]) -> String {
std::iter::once(command)
.chain(args.iter().map(String::as_str))
.map(shell_escape)
.collect::<Vec<_>>()
.join(" ")
}
fn shell_escape(value: &str) -> String {
if value.is_empty() {
return "''".to_owned();
}
if value
.chars()
.all(|ch| ch.is_ascii_alphanumeric() || matches!(ch, '/' | '.' | '_' | '-' | ':' | '='))
{
return value.to_owned();
}
format!("'{}'", value.replace('\'', "'\\''"))
}
// ---------------------------------------------------------------------------
// Embedder profiles & engines (LOT C2 — §14.5.3)
// ---------------------------------------------------------------------------