Enable local image prompts without breaking text-only CLI flows

The Rust CLI now recognizes explicit local image references in prompt text,
encodes supported image files as base64, and serializes mixed text/image
content blocks for the API. The request conversion path was kept narrow so
existing runtime/session structures remain stable while prompt mode and user
text conversion gain multimodal support.

Constraint: Must support PNG, JPG/JPEG, GIF, and WebP without adding broad runtime abstractions
Constraint: Existing text-only prompt behavior and API tool flows must keep working unchanged
Rejected: Add only explicit --image CLI flags | does not satisfy auto-detect image refs in prompt text
Rejected: Persist native image blocks in runtime session model | broader refactor than needed for prompt support
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: Keep image parsing scoped to outbound user prompt adaptation unless session persistence truly needs multimodal history
Tested: cargo fmt --all; cargo clippy --workspace --all-targets -- -D warnings; cargo test --workspace
Not-tested: Live remote multimodal request against Anthropic API
This commit is contained in:
Yeachan-Heo
2026-04-01 00:59:16 +00:00
parent d6341d54c1
commit 5b046836b9
5 changed files with 377 additions and 42 deletions

View File

@@ -408,7 +408,7 @@ mod tests {
.sum::<i32>();
Ok(total.to_string())
});
let permission_policy = PermissionPolicy::new(PermissionMode::Prompt);
let permission_policy = PermissionPolicy::new(PermissionMode::WorkspaceWrite);
let system_prompt = SystemPromptBuilder::new()
.with_project_context(ProjectContext {
cwd: PathBuf::from("/tmp/project"),
@@ -487,7 +487,7 @@ mod tests {
Session::new(),
SingleCallApiClient,
StaticToolExecutor::new(),
PermissionPolicy::new(PermissionMode::Prompt),
PermissionPolicy::new(PermissionMode::WorkspaceWrite),
vec!["system".to_string()],
);
@@ -536,7 +536,7 @@ mod tests {
session,
SimpleApi,
StaticToolExecutor::new(),
PermissionPolicy::new(PermissionMode::Allow),
PermissionPolicy::new(PermissionMode::DangerFullAccess),
vec!["system".to_string()],
);
@@ -563,7 +563,7 @@ mod tests {
Session::new(),
SimpleApi,
StaticToolExecutor::new(),
PermissionPolicy::new(PermissionMode::Allow),
PermissionPolicy::new(PermissionMode::DangerFullAccess),
vec!["system".to_string()],
);
runtime.run_turn("a", None).expect("turn a");