From 73dbd4cef714a2de8976f7ff44e8a8e6fd57d0d4 Mon Sep 17 00:00:00 2001 From: H-Chris233 Date: Mon, 4 May 2026 20:16:59 +0800 Subject: [PATCH] Harden ASR validation path against endpoint and response regressions Follow-up fixes from dual review keep the new end-to-end ASR check while removing compatibility and robustness regressions: normalize transcription endpoint URL, enforce HTTPS except localhost, cap response size, and switch to stable backend error codes mapped in i18n. Constraint: Preserve issue #242 full-chain validation behavior with minimal surface change Rejected: Revert to model-list-only validation | no longer verifies real transcription route Confidence: high Scope-risk: narrow Directive: Keep providerHttpStatus:* and stable error-code contract synchronized with Settings error mapping Tested: npm run build; cargo check -q Not-tested: Manual validation against all third-party ASR endpoints --- openless-all/app/src-tauri/src/commands.rs | 60 +++++++++++++++++----- openless-all/app/src/i18n/en.ts | 6 ++- openless-all/app/src/i18n/zh-CN.ts | 6 ++- openless-all/app/src/pages/Settings.tsx | 12 +++-- 4 files changed, 65 insertions(+), 19 deletions(-) diff --git a/openless-all/app/src-tauri/src/commands.rs b/openless-all/app/src-tauri/src/commands.rs index 05222f19..fd2ce834 100644 --- a/openless-all/app/src-tauri/src/commands.rs +++ b/openless-all/app/src-tauri/src/commands.rs @@ -239,7 +239,8 @@ async fn validate_asr_provider() -> Result<(), String> { } async fn validate_asr_transcription(config: &ProviderConfig, model: &str) -> Result<(), String> { - let url = format!("{}/audio/transcriptions", config.base_url.trim_end_matches('/')); + const MAX_ASR_VALIDATE_BODY_BYTES: usize = 1024 * 1024; + let url = asr_transcriptions_url(&config.base_url)?; let wav = encode_wav_16k_mono_silence(250); let wav_part = reqwest::multipart::Part::bytes(wav) .file_name("openless-asr-check.wav") @@ -251,7 +252,7 @@ async fn validate_asr_transcription(config: &ProviderConfig, model: &str) -> Res let client = reqwest::Client::builder() .timeout(Duration::from_secs(20)) .build() - .map_err(|e| format!("HTTP client 初始化失败: {e}"))?; + .map_err(|_| "providerClientInitFailed".to_string())?; let response = client .post(&url) .header("Authorization", format!("Bearer {}", config.api_key)) @@ -260,27 +261,48 @@ async fn validate_asr_transcription(config: &ProviderConfig, model: &str) -> Res .await .map_err(|e| { if e.is_timeout() { - "请求超时".to_string() + "providerRequestTimeout".to_string() } else { - format!("网络错误: {e}") + "providerNetworkError".to_string() } })?; let status = response.status(); - let body = response - .text() - .await - .map_err(|e| format!("读取响应失败: {e}"))?; if !status.is_success() { return Err(format!("providerHttpStatus:{}", status.as_u16())); } - let json: Value = - serde_json::from_str(&body).map_err(|e| format!("转写响应不是有效 JSON: {e}"))?; + if let Some(len) = response.content_length() { + if len as usize > MAX_ASR_VALIDATE_BODY_BYTES { + return Err("providerResponseTooLarge".to_string()); + } + } + let body = response + .bytes() + .await + .map_err(|_| "providerReadResponseFailed".to_string())?; + if body.len() > MAX_ASR_VALIDATE_BODY_BYTES { + return Err("providerResponseTooLarge".to_string()); + } + let json: Value = serde_json::from_slice(&body).map_err(|_| "asrInvalidJson".to_string())?; if !json.is_object() || json.get("text").is_none() { - return Err("ASR 转写响应缺少 text 字段".to_string()); + return Err("asrMissingTextField".to_string()); } Ok(()) } +fn asr_transcriptions_url(base_url: &str) -> Result { + let trimmed = base_url.trim().trim_end_matches('/'); + let parsed = reqwest::Url::parse(trimmed).map_err(|_| "endpointInvalid".to_string())?; + let host = parsed.host_str().unwrap_or_default(); + let localhost = host.eq_ignore_ascii_case("localhost") || host == "127.0.0.1"; + if parsed.scheme() != "https" && !localhost { + return Err("endpointMustUseHttps".to_string()); + } + if trimmed.ends_with("/audio/transcriptions") { + return Ok(trimmed.to_string()); + } + Ok(format!("{trimmed}/audio/transcriptions")) +} + fn encode_wav_16k_mono_silence(duration_ms: u32) -> Vec { let sample_rate: u32 = 16_000; let num_channels: u16 = 1; @@ -661,8 +683,8 @@ fn _ensure_snapshot_used(_: CredentialsSnapshot) {} #[cfg(test)] mod tests { use super::{ - fetch_provider_models, models_url, parse_model_ids, persist_settings, ProviderConfig, - SettingsWriter, + asr_transcriptions_url, fetch_provider_models, models_url, parse_model_ids, + persist_settings, ProviderConfig, SettingsWriter, }; use crate::types::{ HotkeyBinding, HotkeyMode, HotkeyTrigger, QaHotkeyBinding, UserPreferences, @@ -706,6 +728,18 @@ mod tests { ); } + #[test] + fn asr_transcriptions_url_accepts_base_or_transcriptions_endpoint() { + assert_eq!( + asr_transcriptions_url("https://api.openai.com/v1").unwrap(), + "https://api.openai.com/v1/audio/transcriptions" + ); + assert_eq!( + asr_transcriptions_url("https://api.openai.com/v1/audio/transcriptions").unwrap(), + "https://api.openai.com/v1/audio/transcriptions" + ); + } + #[test] fn parse_model_ids_sorts_and_deduplicates() { let models = diff --git a/openless-all/app/src/i18n/en.ts b/openless-all/app/src/i18n/en.ts index 1097d6fe..069b6f52 100644 --- a/openless-all/app/src/i18n/en.ts +++ b/openless-all/app/src/i18n/en.ts @@ -322,13 +322,17 @@ export const en: typeof zhCN = { fetchModels: 'Fetch models', loadingModels: 'Fetching models…', modelMissing: 'No model is configured. Please enter a model ID first.', - asrModelUnavailable: 'Current ASR model is not in the provider model list. Please select or enter a valid model.', modelsEmpty: 'Credentials are valid, but no models were returned.', modelsLoaded: 'Fetched {{count}} models.', selectModel: 'Select a model to fill the field above', modelSaved: 'Saved model {{model}}.', validateSuccess: 'Connection check passed.', providerHttpStatus: 'Provider returned HTTP {{status}}. Check the API key permissions or endpoint.', + endpointMustUseHttps: 'Endpoint must use HTTPS (localhost/127.0.0.1 are allowed for local testing).', + endpointInvalid: 'Endpoint format is invalid.', + responseTooLarge: 'Provider response is too large to validate safely.', + asrInvalidJson: 'ASR response is not valid JSON.', + asrMissingTextField: 'ASR response is missing the text field.', apiKeyMissing: 'API Key is empty.', endpointMissing: 'Endpoint is empty.', requestTimeout: 'Request timed out. Try again later.', diff --git a/openless-all/app/src/i18n/zh-CN.ts b/openless-all/app/src/i18n/zh-CN.ts index d55004ef..d156ef1c 100644 --- a/openless-all/app/src/i18n/zh-CN.ts +++ b/openless-all/app/src/i18n/zh-CN.ts @@ -320,13 +320,17 @@ export const zhCN = { fetchModels: '拉取模型', loadingModels: '拉取模型中…', modelMissing: '未配置模型，请先填写模型 ID。', - asrModelUnavailable: '当前 ASR 模型不在供应商返回列表中，请选择或填写有效模型。', modelsEmpty: '鉴权成功，但没有返回可用模型。', modelsLoaded: '已拉取 {{count}} 个模型。', selectModel: '选择一个模型写入上方字段', modelSaved: '已保存模型 {{model}}。', validateSuccess: '连接检查通过。', providerHttpStatus: '供应商接口返回 {{status}}，请检查 API Key 权限或 Endpoint。', + endpointMustUseHttps: 'Endpoint 必须使用 HTTPS（本地 localhost/127.0.0.1 测试除外）。', + endpointInvalid: 'Endpoint 格式不合法。', + responseTooLarge: '供应商响应过大，已停止验证以保证安全。', + asrInvalidJson: 'ASR 响应不是有效 JSON。', + asrMissingTextField: 'ASR 响应缺少 text 字段。', apiKeyMissing: 'API Key 为空。', endpointMissing: 'Endpoint 为空。', requestTimeout: '请求超时，请稍后重试。', diff --git a/openless-all/app/src/pages/Settings.tsx b/openless-all/app/src/pages/Settings.tsx index 618261f8..71c1abfd 100644 --- a/openless-all/app/src/pages/Settings.tsx +++ b/openless-all/app/src/pages/Settings.tsx @@ -597,10 +597,6 @@ function ProviderTools({ kind, modelAccount, onModelSelected }: { kind: 'llm' | setResult('empty', t('settings.providers.modelMissing')); return; } - if (kind === 'asr' && message === 'asrModelUnavailable') { - setResult('empty', t('settings.providers.asrModelUnavailable')); - return; - } if (message === 'modelsEmpty') { setResult('empty', t('settings.providers.modelsEmpty')); return; @@ -672,6 +668,14 @@ function providerErrorMessage(error: unknown, t: ReturnType