valknar/llmx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add "View Image" tool (#2723)

Browse Source 
Adds a "View Image" tool so Codex can find and see images by itself:

<img width="1772" height="420" alt="Screenshot 2025-08-26 at 10 40
04 AM"
src="https://github.com/user-attachments/assets/7a459c7b-0b86-4125-82d9-05fbb35ade03"
/>
This commit is contained in:
dedrisian-oai
2025-08-27 17:41:23 -07:00
committed by GitHub
parent 3e309805ae
commit 4e9ad23864
8 changed files with 126 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
codex-rs/core/src/config.rs
View File

@@ -178,6 +178,9 @@ pub struct Config {
pub preferred_auth_method: AuthMode,
pub use_experimental_streamable_shell_tool: bool,
/// Include the `view_image` tool that lets the agent attach a local image path to context.
pub include_view_image_tool: bool,
}
impl Config {
@@ -497,6 +500,10 @@ pub struct ToolsToml {
// Renamed from `web_search_request`; keep alias for backwards compatibility.
#[serde(default, alias = "web_search_request")]
pub web_search: Option<bool>,
/// Enable the `view_image` tool that lets the agent attach local images.
#[serde(default)]
pub view_image: Option<bool>,
}
impl ConfigToml {
@@ -586,6 +593,7 @@ pub struct ConfigOverrides {
pub base_instructions: Option<String>,
pub include_plan_tool: Option<bool>,
pub include_apply_patch_tool: Option<bool>,
pub include_view_image_tool: Option<bool>,
pub disable_response_storage: Option<bool>,
pub show_raw_agent_reasoning: Option<bool>,
pub tools_web_search_request: Option<bool>,
@@ -613,6 +621,7 @@ impl Config {
base_instructions,
include_plan_tool,
include_apply_patch_tool,
include_view_image_tool,
disable_response_storage,
show_raw_agent_reasoning,
tools_web_search_request: override_tools_web_search_request,
@@ -681,6 +690,10 @@ impl Config {
.or(cfg.tools.as_ref().and_then(|t| t.web_search))
.unwrap_or(false);
let include_view_image_tool = include_view_image_tool
.or(cfg.tools.as_ref().and_then(|t| t.view_image))
.unwrap_or(true);
let model = model
.or(config_profile.model)
.or(cfg.model)
@@ -784,6 +797,7 @@ impl Config {
use_experimental_streamable_shell_tool: cfg
.experimental_use_exec_command_tool
.unwrap_or(false),
include_view_image_tool,
};
Ok(config)
}
@@ -1152,6 +1166,7 @@ disable_response_storage = true
responses_originator_header: "codex_cli_rs".to_string(),
preferred_auth_method: AuthMode::ChatGPT,
use_experimental_streamable_shell_tool: false,
include_view_image_tool: true,
},
o3_profile_config
);
@@ -1208,6 +1223,7 @@ disable_response_storage = true
responses_originator_header: "codex_cli_rs".to_string(),
preferred_auth_method: AuthMode::ChatGPT,
use_experimental_streamable_shell_tool: false,
include_view_image_tool: true,
};
assert_eq!(expected_gpt3_profile_config, gpt3_profile_config);
@@ -1279,6 +1295,7 @@ disable_response_storage = true
responses_originator_header: "codex_cli_rs".to_string(),
preferred_auth_method: AuthMode::ChatGPT,
use_experimental_streamable_shell_tool: false,
include_view_image_tool: true,
};
assert_eq!(expected_zdr_profile_config, zdr_profile_config);