Skip to content

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

docs: list all AST extraction languages (#3511)

Rocke Dongb62a4d2cfa6d
diff --git a/docs/en/concepts/06-extraction.md b/docs/en/concepts/06-extraction.md
index 20e2027fa..08c24be40 100644
--- a/docs/en/concepts/06-extraction.md
+++ b/docs/en/concepts/06-extraction.md
@@ -161,10 +161,13 @@ The following languages have dedicated extractors built on tree-sitter:
|----------|--------|
| Python | Supported |
| JavaScript / TypeScript | Supported |
-| Rust | Supported |
-| Go | Supported |
| Java | Supported |
| C / C++ | Supported |
+| Rust | Supported |
+| Go | Supported |
+| C# | Supported |
+| PHP | Supported |
+| Lua | Supported |
Other languages automatically fall back to LLM.
diff --git a/docs/en/guides/01-configuration.md b/docs/en/guides/01-configuration.md
index ef08e90f9..97fc5fee9 100644
--- a/docs/en/guides/01-configuration.md
+++ b/docs/en/guides/01-configuration.md
@@ -818,7 +818,9 @@ Set `code_summary_mode` to one of:
| `"llm"` | Always use LLM for summarization (higher cost) | |
| `"ast_llm"` | Extract AST skeleton (with full docstrings) first, then pass it as context to LLM (highest quality, moderate cost) | |
-AST extraction supports: Python, JavaScript/TypeScript, Rust, Go, Java, C/C++. Other languages, extraction failures, or empty skeletons automatically fall back to LLM.
+AST extraction supports: Python, JavaScript/TypeScript, Java, C/C++, Rust, Go, C#, PHP,
+and Lua. Other languages, extraction failures, or empty skeletons automatically fall back
+to LLM.
See [Code Skeleton Extraction](../concepts/06-extraction.md#code-skeleton-extraction-ast-mode) for details.
diff --git a/docs/zh/concepts/06-extraction.md b/docs/zh/concepts/06-extraction.md
index a38e3e5bd..574a58b27 100644
--- a/docs/zh/concepts/06-extraction.md
+++ b/docs/zh/concepts/06-extraction.md
@@ -160,10 +160,13 @@ SemanticMsg(
|------|------|
| Python | 完整支持 |
| JavaScript / TypeScript | 完整支持 |
-| Rust | 完整支持 |
-| Go | 完整支持 |
| Java | 完整支持 |
| C / C++ | 完整支持 |
+| Rust | 完整支持 |
+| Go | 完整支持 |
+| C# | 完整支持 |
+| PHP | 完整支持 |
+| Lua | 完整支持 |
其他语言不在支持列表内,自动 fallback 到 LLM。
diff --git a/docs/zh/guides/01-configuration.md b/docs/zh/guides/01-configuration.md
index 93fa75613..0016b7700 100644
--- a/docs/zh/guides/01-configuration.md
+++ b/docs/zh/guides/01-configuration.md
@@ -787,7 +787,8 @@ ollama pull guoxuter/ov_intent_analysis_sft:v7_q8
| `"llm"` | 全部走 LLM 生成摘要(成本较高) | |
| `"ast_llm"` | 先提取 AST 骨架(含完整注释),再将骨架作为上下文辅助 LLM 生成摘要(质量最高,成本居中) | |
-AST 提取支持:Python、JavaScript/TypeScript、Rust、Go、Java、C/C++。其他语言、提取失败或骨架为空时自动 fallback 到 LLM。
+AST 提取支持:Python、JavaScript/TypeScript、Java、C/C++、Rust、Go、C#、PHP 和 Lua。
+其他语言、提取失败或骨架为空时自动 fallback 到 LLM。
详见 [代码骨架提取](../concepts/06-extraction.md#代码骨架提取ast-模式)。