fix: 为 TSX 初检使用独立 grammar

Author: loong10k

README.md

@@ -94,9 +94,9 @@ cargo build --locked -p codeguard-cli
 
 Version output includes `cli_version`, `target`, and protocol information. Discovery and init preview return observations and unknowns. Dry-run creates neither `AGENTS.md` nor a project data directory. Add Cargo `--offline` only when dependencies are cached.
 
-The workspace requires `std`. The opt-in `wasm-precheck` build feature uses a bounded Rust worker with pinned Java/TypeScript grammar candidates. It currently reaches only single-file `lint java` and `lint typescript` requests without explicit native context; it is absent from the published npm `0.1.2` package. No `no_std`, completed project-wide WASM fallback, zero-unsafe, or fastest-runtime claim is made. Runtime OS calls require safety review; a comprehensive security audit is not claimed.
+The workspace requires `std`. The opt-in `wasm-precheck` build feature uses a bounded Rust worker with pinned Java, TypeScript, and TSX grammar candidates. It currently reaches only single-file `lint java` and `lint typescript` requests without explicit native context; `.tsx` uses its own grammar. It is absent from the published npm `0.1.2` package. No `no_std`, completed project-wide WASM fallback, zero-unsafe, or fastest-runtime claim is made. Runtime OS calls require safety review; a comprehensive security audit is not claimed.
 
-The current source-built CLI's `codeguard grammar status --format=json` reports the coverage gap without loading grammars or running lint: the pinned CodeGraph source has 30 vendored WASM files plus two distinct grammars resolved through its dependency; CodeGuard has two unqualified candidates and zero released syntax capabilities. The separate [coverage inventory](grammars/codegraph-coverage.json) is not an approved asset manifest. COBOL's 16.4 MB source asset also exceeds the current Rust loader's 8 MiB limit.
+The current source-built CLI's `codeguard grammar status --format=json` reports the coverage gap without loading grammars or running lint: the pinned CodeGraph source has 30 vendored WASM files plus two distinct grammars resolved through its dependency; CodeGuard has three unqualified candidates and zero released syntax capabilities. The separate [coverage inventory](grammars/codegraph-coverage.json) is not an approved asset manifest. COBOL's 16.4 MB source asset also exceeds the current Rust loader's 8 MiB limit.
 
 ### npm installation and one-off use
 

README.zh-CN.md

@@ -94,9 +94,9 @@ cargo build --locked -p codeguard-cli
 
 版本输出包含 `cli_version`、`target` 和协议信息。发现与 init 预览返回观察及未知项。Dry-run 不创建 `AGENTS.md` 或项目数据目录。仅在依赖已缓存时为 Cargo 添加 `--offline`。
 
-工作区要求 `std`。可选 `wasm-precheck` 构建特性已用固定的 Java/TypeScript grammar 候选资产与有界 Rust worker，为缺少显式原生上下文的 `lint java`、`lint typescript` 单文件请求提供疑似语法观察；公开 npm `0.1.2` 不含该路径。不声称 `no_std`、已完成项目级 WASM 兜底、零 unsafe 或性能最快。运行层系统调用需要安全审查，当前不宣称已完成整体安全审计。
+工作区要求 `std`。可选 `wasm-precheck` 构建特性已用固定的 Java、TypeScript、TSX grammar 候选资产与有界 Rust worker，为缺少显式原生上下文的 `lint java`、`lint typescript` 单文件请求提供疑似语法观察；`.tsx` 使用独立 grammar。公开 npm `0.1.2` 不含该路径。不声称 `no_std`、已完成项目级 WASM 兜底、零 unsafe 或性能最快。运行层系统调用需要安全审查，当前不宣称已完成整体安全审计。
 
-当前源码构建的 CLI 可用 `codeguard grammar status --format=json` 只读展示来源覆盖缺口，不加载 grammar 或运行 lint：固定 CodeGraph 来源含 30 份随仓 WASM，另有两种独立 grammar 从其依赖取得；CodeGuard 当前只有两份未验收候选，已发行语法能力为零。[覆盖库存](grammars/codegraph-coverage.json)不是已批准资产清单。COBOL 来源资产约 16.4 MB，还超过当前 Rust 加载器的 8 MiB 限额。
+当前源码构建的 CLI 可用 `codeguard grammar status --format=json` 只读展示来源覆盖缺口，不加载 grammar 或运行 lint：固定 CodeGraph 来源含 30 份随仓 WASM，另有两种独立 grammar 从其依赖取得；CodeGuard 当前有三份未验收候选，已发行语法能力为零。[覆盖库存](grammars/codegraph-coverage.json)不是已批准资产清单。COBOL 来源资产约 16.4 MB，还超过当前 Rust 加载器的 8 MiB 限额。
 
 ### npm 安装与一次性调用
 

crates/codeguard-adapters/src/grammar_asset_manifest.rs

@@ -68,7 +68,7 @@ pub struct GrammarAsset {
     pub release_status: String,
 }
 
-/// 读取仓内固定清单，并检查 CodeGraph 许可证及两份资产的原始字节。
+/// 读取仓内固定清单，并检查 CodeGraph 许可证及三份资产的原始字节。
 pub fn bundled_grammar_candidates() -> Result<GrammarAssetManifest, String> {
     let manifest = parse_grammar_asset_manifest(include_bytes!("../../../grammars/manifest.json"))?;
     let codegraph_license = include_bytes!("../../../grammars/LICENSE.codegraph");
@@ -85,6 +85,10 @@ pub fn bundled_grammar_candidates() -> Result<GrammarAssetManifest, String> {
                 include_bytes!("../../../grammars/typescript/parser.wasm").as_slice(),
                 include_bytes!("../../../grammars/typescript/LICENSE").as_slice(),
             ),
+            "tsx" => (
+                include_bytes!("../../../grammars/tsx/parser.wasm").as_slice(),
+                include_bytes!("../../../grammars/typescript/LICENSE").as_slice(),
+            ),
             _ => return Err("候选语言未知".into()),
         };
         verify_grammar_asset(asset, wasm, license)?;
@@ -106,7 +110,7 @@ pub fn parse_grammar_asset_manifest(raw: &[u8]) -> Result<GrammarAssetManifest,
         || manifest.codegraph_license != "LICENSE.codegraph"
         || manifest.codegraph_license_sha256 != CODEGRAPH_LICENSE_SHA256
         || manifest.build_tool != "tree-sitter-cli 0.25.10 build --wasm"
-        || manifest.assets.len() != 2
+        || manifest.assets.len() != 3
     {
         return Err("grammar 清单版本、来源或资产数量不符".into());
     }
@@ -115,7 +119,7 @@ pub fn parse_grammar_asset_manifest(raw: &[u8]) -> Result<GrammarAssetManifest,
         .iter()
         .map(|asset| asset.language.as_str())
         .collect();
-    if languages != BTreeSet::from(["java", "typescript"]) {
+    if languages != BTreeSet::from(["java", "typescript", "tsx"]) {
         return Err("grammar 语言资产缺失或重复".into());
     }
     for asset in &manifest.assets {
@@ -141,6 +145,16 @@ pub fn parse_grammar_asset_manifest(raw: &[u8]) -> Result<GrammarAssetManifest,
                     "typescript/LICENSE",
                     "49bf33cf78ef5897e4e161ce1517df7de1ae5042a65b6bcfd44401e0fc606559",
                 ),
+                "tsx" => (
+                    "https://github.com/tree-sitter/tree-sitter-typescript",
+                    TYPESCRIPT_COMMIT,
+                    "v0.23.2",
+                    "tsx/parser.wasm",
+                    "8f647a1b2cafe9ab00fb2056d79021d2a144ba17a72f45511072311c1b05d08e",
+                    1445641,
+                    "typescript/LICENSE",
+                    "49bf33cf78ef5897e4e161ce1517df7de1ae5042a65b6bcfd44401e0fc606559",
+                ),
                 _ => return Err("grammar 语言未知".into()),
             };
         if asset.dialect != asset.language

crates/codeguard-adapters/src/syntax_precheck_candidate_report.rs

@@ -100,6 +100,9 @@ pub fn parse_syntax_precheck_candidate_report(
     }
     let mut observations = Vec::with_capacity(report.files.len());
     for file in report.files {
+        if !path_matches_language(&file.path, &report.backend.language) {
+            return Err("syntax_precheck_source_dialect_mismatch".into());
+        }
         let source = source_bytes
             .get(&file.path)
             .ok_or("syntax_precheck_source_missing")?;
@@ -132,3 +135,14 @@ pub fn parse_syntax_precheck_candidate_report(
     }
     Ok(actual)
 }
+
+fn path_matches_language(path: &str, language: &str) -> bool {
+    match language {
+        "java" => path.ends_with(".java"),
+        "typescript" => [".ts", ".mts", ".cts"]
+            .iter()
+            .any(|suffix| path.ends_with(suffix)),
+        "tsx" => path.ends_with(".tsx"),
+        _ => false,
+    }
+}

crates/codeguard-adapters/tests/grammar_asset_manifest.rs

@@ -5,7 +5,7 @@ use codeguard_adapters::{
 #[test]
 fn bundled_candidates_pin_source_bytes_license_and_abi_without_claiming_support() {
     let manifest = bundled_grammar_candidates().expect("bundled manifest");
-    assert_eq!(manifest.assets.len(), 2);
+    assert_eq!(manifest.assets.len(), 3);
     for asset in &manifest.assets {
         let (wasm, license) = match asset.language.as_str() {
             "java" => (
@@ -16,6 +16,10 @@ fn bundled_candidates_pin_source_bytes_license_and_abi_without_claiming_support(
                 include_bytes!("../../../grammars/typescript/parser.wasm").as_slice(),
                 include_bytes!("../../../grammars/typescript/LICENSE").as_slice(),
             ),
+            "tsx" => (
+                include_bytes!("../../../grammars/tsx/parser.wasm").as_slice(),
+                include_bytes!("../../../grammars/typescript/LICENSE").as_slice(),
+            ),
             other => panic!("unexpected language {other}"),
         };
         verify_grammar_asset(asset, wasm, license).expect("pinned candidate bytes");

crates/codeguard-adapters/tests/syntax_precheck_report_contract.rs

@@ -105,3 +105,20 @@ fn candidate_schema_declares_closed_versioned_contract() {
     assert_eq!(schema["additionalProperties"], false);
     assert_eq!(schema["properties"]["precheck"]["$ref"], "#/$defs/precheck");
 }
+
+#[test]
+fn tsx_candidate_requires_tsx_source_and_cannot_relabel_java() {
+    let mut report = candidate();
+    report["backend"]["language"] = json!("tsx");
+    report["backend"]["dialect"] = json!("tsx");
+    report["backend"]["grammar_sha256"] =
+        json!("8f647a1b2cafe9ab00fb2056d79021d2a144ba17a72f45511072311c1b05d08e");
+    assert!(read(&report).is_err());
+
+    report["files"][0]["path"] = json!("src/Component.tsx");
+    let sources = BTreeMap::from([("src/Component.tsx".into(), b"hello".to_vec())]);
+    let status =
+        parse_syntax_precheck_candidate_report(&serde_json::to_vec(&report).unwrap(), &sources)
+            .unwrap();
+    assert_eq!(status.status, SyntaxPrecheckStatus::Incomplete);
+}

crates/codeguard-cli/src/syntax_worker_command.rs

@@ -63,6 +63,7 @@ fn observe(language: &str, source: &[u8]) -> Result<SyntaxWorkerEnvelope, String
     let wasm = match language {
         "java" => include_bytes!("../../../grammars/java/parser.wasm").as_slice(),
         "typescript" => include_bytes!("../../../grammars/typescript/parser.wasm").as_slice(),
+        "tsx" => include_bytes!("../../../grammars/tsx/parser.wasm").as_slice(),
         _ => return Err("不支持的 grammar 语种".into()),
     };
     let mut grammar = WasmGrammar::load(language, wasm, &asset.sha256, asset.abi_version as usize)?;

crates/codeguard-cli/src/typescript_syntax_precheck.rs

@@ -28,15 +28,24 @@ pub(crate) fn eligible(args: &EslintLintArguments) -> bool {
 }
 
 /// 使用本轮源码快照与私有 Rust worker 补充疑似语法观察；原生仍未运行。
-/// 参数为受支持的单文件请求及共同截止时间；返回无交付权威的 0.3.0 反馈。
+/// 参数为受支持的单文件请求及共同截止时间；返回无交付权威的 TypeScript 0.3.0 或 TSX 0.4.0 反馈。
 pub(crate) fn observe(args: &EslintLintArguments, deadline: Instant) -> Value {
+    let language = if args
+        .source
+        .extension()
+        .is_some_and(|extension| extension == "tsx")
+    {
+        "tsx"
+    } else {
+        "typescript"
+    };
     let source_name = args
         .source
         .file_name()
         .and_then(|name| name.to_str())
         .unwrap_or("source.ts");
     let mut report = json!({
-        "schema_version": "0.3.0",
+        "schema_version": if language == "tsx" { "0.4.0" } else { "0.3.0" },
         "report_type": "eslint_local_feedback",
         "status": "incomplete",
         "local_coherent": false,
@@ -51,7 +60,7 @@ pub(crate) fn observe(args: &EslintLintArguments, deadline: Instant) -> Value {
         "setup": {"requirement": "required", "reason": "native_confirmation_needed", "task_id": null},
         "syntax_precheck": {
             "backend": "bundled_tree_sitter_wasm_candidate",
-            "language": "typescript",
+            "language": language,
             "status": "incomplete",
             "reason": "not_run",
             "source_path": source_name,
@@ -82,7 +91,7 @@ pub(crate) fn observe(args: &EslintLintArguments, deadline: Instant) -> Value {
     };
     let observation = match run_syntax_worker_candidate(
         &executable,
-        "typescript",
+        language,
         source_name,
         &source,
         deadline,

crates/codeguard-cli/tests/grammar_status_cli.rs

@@ -12,7 +12,7 @@ fn codegraph_coverage_is_explicit_and_never_claims_parser_or_gate_completion() {
     assert_eq!(report["report_type"], "grammar_coverage_inventory");
     assert_eq!(report["codegraph_grammar_count"], 32);
     assert_eq!(report["codegraph_vendored_count"], 30);
-    assert_eq!(report["candidate_count"], 2);
+    assert_eq!(report["candidate_count"], 3);
     assert_eq!(report["released_count"], 0);
     assert_eq!(report["authority"], "source_inventory_only");
     assert_eq!(report["parser_capability"], "unverified");
@@ -25,7 +25,7 @@ fn codegraph_coverage_is_explicit_and_never_claims_parser_or_gate_completion() {
         assert_eq!(asset["released"], false);
         assert!(!asset["gap"].as_str().unwrap().is_empty());
     }
-    for language in ["java", "typescript"] {
+    for language in ["java", "typescript", "tsx"] {
         let asset = assets
             .iter()
             .find(|row| row["language"] == language)

crates/codeguard-cli/tests/typescript_syntax_fallback_candidate.rs

@@ -90,6 +90,72 @@ fn no_recovery_remains_incomplete_and_javascript_does_not_use_typescript_grammar
     assert!(js_report.get("syntax_precheck").is_none());
 }
 
+#[test]
+fn tsx_uses_its_own_grammar_instead_of_reporting_valid_jsx_as_suspect() {
+    let project = Project::new();
+    fs::write(
+        project.0.join("component.tsx"),
+        "const node = <div title=\"ok\">hello</div>;\n",
+    )
+    .unwrap();
+    let (status, report) = project.lint("component.tsx");
+    assert_eq!(status, 3);
+    assert_eq!(report["schema_version"], "0.4.0");
+    assert_eq!(report["native"]["status"], "not_run");
+    assert_eq!(report["syntax_precheck"]["language"], "tsx");
+    assert_eq!(report["syntax_precheck"]["checked_files"], 1);
+    assert_eq!(
+        report["syntax_precheck"]["grammar_sha256"],
+        "8f647a1b2cafe9ab00fb2056d79021d2a144ba17a72f45511072311c1b05d08e"
+    );
+    assert!(
+        report["syntax_precheck"]["observations"]
+            .as_array()
+            .unwrap()
+            .is_empty()
+    );
+    assert_eq!(report["delivery_decision"], "not_evaluated");
+
+    fs::write(
+        project.0.join("broken.tsx"),
+        "const node = <div title=></div>;\n",
+    )
+    .unwrap();
+    let (_, broken) = project.lint("broken.tsx");
+    assert_eq!(broken["syntax_precheck"]["language"], "tsx");
+    assert!(
+        !broken["syntax_precheck"]["observations"]
+            .as_array()
+            .unwrap()
+            .is_empty()
+    );
+    assert_eq!(broken["syntax_precheck"]["status"], "incomplete");
+    assert!(broken["findings"].as_array().unwrap().is_empty());
+
+    let schema: Value = serde_json::from_str(include_str!(
+        "../../../schemas/eslint-local-feedback-v0.4.schema.json"
+    ))
+    .unwrap();
+    assert_eq!(schema["properties"]["schema_version"]["const"], "0.4.0");
+    assert_eq!(
+        schema["properties"]["syntax_precheck"]["properties"]["language"]["const"],
+        "tsx"
+    );
+    let actual: std::collections::BTreeSet<_> = report
+        .as_object()
+        .unwrap()
+        .keys()
+        .map(String::as_str)
+        .collect();
+    let required: std::collections::BTreeSet<_> = schema["required"]
+        .as_array()
+        .unwrap()
+        .iter()
+        .map(|item| item.as_str().unwrap())
+        .collect();
+    assert_eq!(actual, required);
+}
+
 #[test]
 fn candidate_feedback_schema_is_versioned_and_closed() {
     let schema: Value = serde_json::from_str(include_str!(