feat(opencode): remplace le profil Ollama HTTP par OpenCode

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

frontend/src/domain/index.ts

@@ -631,12 +631,12 @@ export type InjectionStrategy = ContextInjection["strategy"];
  * `StructuredAdapter`, camelCase wire format). Absent (`structuredAdapter`
  * omitted) ⇒ the profile is a plain TUI/PTY agent (historical behaviour);
  * present ⇒ the profile is selectable as a structured AI agent:
- * - `claude` / `codex`: driven by a spawned CLI binary,
+ * - `claude` / `codex` / `openCode`: driven by a spawned CLI binary,
  * - `openAiCompatible`: driven by IdeA's native HTTP adapter against an
  *   OpenAI-compatible chat server (Ollama, llama.cpp, a LAN runtime) — see
  *   {@link HttpChatConfig}.
  */
-export type StructuredAdapter = "claude" | "codex" | "openAiCompatible";
+export type StructuredAdapter = "claude" | "codex" | "openCode" | "openAiCompatible";
 
 /**
  * HTTP configuration of an OpenAI-compatible chat server (mirror of the backend
@@ -662,6 +662,12 @@ export interface HttpChatConfig {
   maxToolIterations?: number;
 }
 
+/** Configuration for an OpenCode process-backed profile. */
+export interface OpenCodeConfig {
+  /** Full OpenCode model id, for example `ollama/qwen3-coder:30b`. */
+  model?: string;
+}
+
 /**
  * A declarative AI-CLI profile (mirror of the backend `AgentProfile`). `id` is a
  * UUID string; `detect` is the optional detection command line.
@@ -690,6 +696,8 @@ export interface AgentProfile {
    * every historical profile and every non-HTTP adapter.
    */
   chatHttp?: HttpChatConfig;
+  /** OpenCode process-backed config. Present for `structuredAdapter: "openCode"`. */
+  opencode?: OpenCodeConfig;
 }
 
 /** Availability of a candidate profile after detection (mirror of the DTO). */