admin/CC-Switch
1
0
Fork 0
mirror of https://github.com/farion1231/cc-switch.git synced 2026-07-28 08:44:41 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(codex): infer image capability for generated catalogs and resync takeover live on save

Browse Source 
Mapped GPT models were rejected by Codex clients with "model does not
support image inputs". Two root causes:

- Catalog entries for native-Responses/Anthropic providers cloned a
  template whose input_modalities defaulted to ["text"], so every mapped
  model was advertised text-only. model_catalog_json replaces Codex's
  built-in model table wholesale, and both the TUI and the IDE extension
  block images pre-send when the current model is found without "image".
- Editing the current Codex provider during proxy takeover only refreshed
  the DB backup, so removing the mapping left a stale model_catalog_json
  pointer (and its text-only catalog file) active in live config.

Changes:

- New shared model_capabilities module: explicit row declaration first,
  then a confirmed text-only registry (exact tail match only — prefix
  matching removed, variants enumerated so future -vl/-vision models fail
  open), everything else unknown.
- Catalog generation writes input_modalities from that inference for all
  tool profiles: unknown models fail open to ["text","image"]; only
  confirmed text-only models are advertised as ["text"], giving users a
  clear client-side prompt instead of silent image stripping.
- Live catalog reverse-import collapses modalities that match current
  inference, so registry corrections are not frozen into hidden row
  overrides and the rectifier's heuristic opt-out keeps working.
- Saving the current Codex provider while takeover owns live now
  re-projects the live config (mirrors the hot-switch path), so mapping
  edits and removals take effect immediately.
- Media rectifier delegates to the shared module; its preflight toggle is
  documented (4 locales) as proxy-request-only, never affecting catalog
  capability declarations.
This commit is contained in:
Jason
2026-07-13 16:27:51 +08:00
parent 618723b42f
commit ac52c851bf
14 changed files with 627 additions and 193 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src-tauri/src/proxy/media_sanitizer.rs
+20 -147
View File
@@ -1,3 +1,6 @@
#[cfg(test)]
use crate::model_capabilities::is_confirmed_text_only_model as confirmed_text_only_model;
use crate::model_capabilities::{image_input_capability_from_settings, ImageInputCapability};
use crate::provider::Provider;
use crate::proxy::error::ProxyError;
use serde_json::{json, Value};
@@ -9,9 +12,9 @@ pub const UNSUPPORTED_IMAGE_MARKER: &str = "[Unsupported Image]";
/// Two paths, both reached only when the caller's media-fallback switch is on:
/// - explicit capability from the provider config (modelCatalog / modalities) is
/// always trusted — it is declaration-driven, never a guess;
/// - the curated `known_text_only_model` list is a heuristic *prediction* and only
/// runs when `allow_heuristic` is true, so a mislabeled multimodal model cannot
/// have its images silently stripped when the user opts out.
/// - the confirmed text-only registry is used for proactive replacement only
/// when `allow_heuristic` is true. This switch controls silent request-body
/// mutation, not the capability truth advertised by the Codex model catalog.
pub fn replace_images_for_text_only_model(
body: &mut Value,
provider: &Provider,
@@ -27,13 +30,9 @@ pub fn replace_images_for_text_only_model(
.map(str::trim)
.unwrap_or("");
match explicit_model_image_support(provider, model) {
Some(true) => return 0,
Some(false) => return replace_images_in_body(body),
None => {}
}
if !allow_heuristic || !known_text_only_model(model) {
if image_input_capability_from_settings(&provider.settings_config, model, allow_heuristic)
!= ImageInputCapability::Unsupported
{
return 0;
}
@@ -237,95 +236,6 @@ fn replace_image_block_with_text_marker(block: &mut Value, text_type: &str) {
}
}
fn explicit_model_image_support(provider: &Provider, model: &str) -> Option<bool> {
let settings = &provider.settings_config;
[
settings
.get("modelCatalog")
.and_then(|catalog| catalog.get("models")),
settings.get("modelCatalog"),
settings.get("models"),
]
.into_iter()
.flatten()
.find_map(|value| explicit_model_image_support_in_value(value, model))
}
fn known_text_only_model(model: &str) -> bool {
let normalized = normalize_model_id(model);
let tail = normalized.rsplit('/').next().unwrap_or(normalized.as_str());
const EXACT_TAILS: &[&str] = &[
"ark-code-latest",
"deepseek-chat",
"deepseek-reasoner",
"deepseek-v4-flash",
"deepseek-v4-pro",
"glm-5.1",
// 精确匹配而非 TAIL_PREFIXES：智谱视觉版沿用 4v/5v 命名（glm-5.2v），
// 前缀匹配会误剥未来多模态变体的图片。
"glm-5.2",
"kat-coder",
"kat-coder-pro",
"kat-coder-pro v1",
"kat-coder-pro v2",
"kat-coder-pro-v1",
"kat-coder-pro-v2",
"ling-2.5-1t",
"longcat-2.0",
"longcat-flash-chat",
"mimo-v2.5-pro",
"us.deepseek.r1-v1",
];
const TAIL_PREFIXES: &[&str] = &["minimax-m2.7", "qwen3-coder", "step-3.5-flash"];
EXACT_TAILS.contains(&tail) || TAIL_PREFIXES.iter().any(|prefix| tail.starts_with(prefix))
}
fn explicit_model_image_support_in_value(value: &Value, model: &str) -> Option<bool> {
if let Some(models) = value.as_array() {
return models.iter().find_map(|entry| {
model_entry_matches(entry, None, model).then(|| explicit_image_support(entry))?
});
}
let object = value.as_object()?;
object.iter().find_map(|(key, entry)| {
model_entry_matches(entry, Some(key), model).then(|| explicit_image_support(entry))?
})
}
fn explicit_image_support(entry: &Value) -> Option<bool> {
if let Some(value) = entry
.get("supportsImage")
.or_else(|| entry.get("supports_image"))
.or_else(|| entry.get("vision"))
.and_then(Value::as_bool)
{
return Some(value);
}
[
entry.get("input"),
entry.pointer("/modalities/input"),
entry.get("input_modalities"),
entry.get("inputModalities"),
]
.into_iter()
.flatten()
.find_map(input_modalities_support_image)
}
fn input_modalities_support_image(value: &Value) -> Option<bool> {
let modalities = value.as_array()?;
Some(modalities.iter().any(|item| {
item.as_str()
.map(str::trim)
.is_some_and(|item| item.eq_ignore_ascii_case("image"))
}))
}
fn extract_error_text(body: &str) -> String {
if let Ok(value) = serde_json::from_str::<Value>(body) {
let candidates = [
@@ -350,43 +260,6 @@ fn extract_error_text(body: &str) -> String {
body.to_string()
}
fn model_entry_matches(entry: &Value, key: Option<&str>, model: &str) -> bool {
key.is_some_and(|key| model_ids_match(key, model))
|| ["model", "id", "name"]
.into_iter()
.filter_map(|field| entry.get(field).and_then(Value::as_str))
.any(|candidate| model_ids_match(candidate, model))
}
fn model_ids_match(candidate: &str, model: &str) -> bool {
let candidate = normalize_model_id(candidate);
let model = normalize_model_id(model);
if candidate.is_empty() || model.is_empty() {
return false;
}
if candidate == model {
return true;
}
let candidate_tail = candidate.rsplit('/').next().unwrap_or(candidate.as_str());
let model_tail = model.rsplit('/').next().unwrap_or(model.as_str());
candidate_tail == model_tail || candidate == model_tail || candidate_tail == model
}
fn normalize_model_id(value: &str) -> String {
let mut normalized = value
.trim()
.trim_start_matches("models/")
.trim()
.to_ascii_lowercase();
if let Some(stripped) =
normalized.strip_suffix(crate::claude_desktop_config::ONE_M_CONTEXT_MARKER)
{
normalized = stripped.trim().to_string();
}
normalized
}
#[cfg(test)]
mod tests {
use super::*;
@@ -431,7 +304,7 @@ mod tests {
}
#[test]
fn known_text_only_models_replace_images_before_send() {
fn confirmed_text_only_models_replace_images_before_send() {
let provider = provider(json!({}));
let mut body = json!({
"model": "deepseek/deepseek-v4-pro",
@@ -453,7 +326,7 @@ mod tests {
}
#[test]
fn known_text_only_models_replace_chat_image_url_before_send() {
fn confirmed_text_only_models_replace_chat_image_url_before_send() {
let provider = provider(json!({}));
let mut body = json!({
"model": "deepseek-v4-flash",
@@ -477,7 +350,7 @@ mod tests {
}
#[test]
fn known_text_only_models_replace_codex_input_image_before_send() {
fn confirmed_text_only_models_replace_codex_input_image_before_send() {
let provider = provider(json!({}));
let mut body = json!({
"model": "deepseek-v4-flash",
@@ -504,9 +377,9 @@ mod tests {
fn longcat_models_are_classified_text_only() {
// LongCat-2.0 (like the retired Flash Chat) is a text-only model; the
// preset ships it in mixed case, so the classifier must normalize first.
assert!(known_text_only_model("LongCat-2.0"));
assert!(known_text_only_model("longcat/LongCat-2.0"));
assert!(known_text_only_model("LongCat-Flash-Chat"));
assert!(confirmed_text_only_model("LongCat-2.0"));
assert!(confirmed_text_only_model("longcat/LongCat-2.0"));
assert!(confirmed_text_only_model("LongCat-Flash-Chat"));
}
#[test]
@@ -662,7 +535,7 @@ mod tests {
}
#[test]
fn known_text_only_prefixes_replace_images_before_send() {
fn confirmed_text_only_variant_replaces_images_before_send() {
let provider = provider(json!({}));
let mut body = json!({
"model": "therouter/qwen/qwen3-coder-480b",
@@ -761,11 +634,11 @@ mod tests {
fn glm_52_is_classified_text_only() {
// issue #5025：火山 Coding Plan 的 GLM 5.2 是纯文本端点，
// 映射链 glm-5.2[1M] 归一化后尾部为 glm-5.2。
assert!(known_text_only_model("glm-5.2"));
assert!(known_text_only_model("GLM-5.2[1M]"));
assert!(known_text_only_model("zai-org/GLM-5.2"));
assert!(confirmed_text_only_model("glm-5.2"));
assert!(confirmed_text_only_model("GLM-5.2[1M]"));
assert!(confirmed_text_only_model("zai-org/GLM-5.2"));
// 未来视觉版（智谱 4v/5v 命名惯例）不能被误判为纯文本。
assert!(!known_text_only_model("glm-5.2v"));
assert!(!confirmed_text_only_model("glm-5.2v"));
}
#[test]
src-tauri/src/proxy/types.rs
+4 -4
View File
@@ -219,11 +219,11 @@ pub struct RectifierConfig {
/// 让对话不中断。总开关，管辖「显式声明 text-only」与「上游报错后兜底」两条事实驱动路径。
#[serde(default = "default_true")]
pub request_media_fallback: bool,
/// 请求整流：启发式 text-only 模型名匹配（默认开启）
/// 请求整流：确认纯文本注册表的发送前降级（默认开启）
///
/// 在模型未声明能力时，按内置模型名列表预测性地剥离图片（发送前）。
/// 受 request_media_fallback 管辖；单独关闭后仅保留「显式声明」与「上游兜底」，
/// 避免内置列表把多模态模型误判成 text-only 而静默剥图。
/// 在模型未声明能力时，按内置的确认纯文本注册表预先剥离图片。
/// 受 request_media_fallback 管辖；单独关闭只停用代理的注册表预判，
/// 仍保留「显式声明」与「上游兜底」，且不改变 Codex 模型目录声明。
#[serde(default = "default_true")]
pub request_media_heuristic: bool,
}