mirror of
https://github.com/CJackHwang/ds2api.git
synced 2026-05-10 19:27:41 +08:00
feat: support PascalCase local-name drift in DSML tool markup parsing
Detect camelCase→PascalCase boundaries between arbitrary prefixes and fixed local names (tool_calls/invoke/parameter), so that fused forms like <DSmartToolCalls> are recognized without explicit separator characters. Also add the underscore-free alias "toolcalls" as a valid DSML local name. Includes lookalike rejection tests to ensure near-matches like <DSmartToolCallsExtra> are not falsely accepted. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -40,7 +40,7 @@ Docs: [Overview](README.en.md) / [Architecture](docs/ARCHITECTURE.en.md) / [Depl
|
||||
|
||||
- OpenAI / Claude / Gemini protocols are now mounted on one shared `chi` router tree assembled in `internal/server/router.go`.
|
||||
- Adapter responsibilities are streamlined to: **request normalization → DeepSeek invocation → protocol-shaped rendering**, reducing legacy split-logic paths.
|
||||
- Tool-calling semantics are aligned between Go and Node runtime: models should output the fullwidth-separator DSML shell `<|DSML|tool_calls>` → `<|DSML|invoke name="...">` → `<|DSML|parameter name="...">`; DS2API also accepts the halfwidth DSML wrapper `<|DSML|tool_calls>`, DSML wrapper aliases such as `<dsml|tool_calls>`, `<|tool_calls>`, `<|tool_calls>`, common DSML separator drift such as `<|DSML tool_calls>`, collapsed DSML local names such as `<DSMLtool_calls>`, control-separator drift such as `<DSML␂tool_calls>` / raw STX `\x02`, CJK angle bracket, fullwidth-bang / ideographic-comma separator drift, and trailing attribute separator drift such as `<DSM|parameter name="command"|>...〈/DSM|parameter〉`, `<!DSML!invoke name=“Bash”>`, `<、DSML、tool_calls>`, or `<DSMLtool_calls※>`, arbitrary protocol prefixes such as `<proto💥tool_calls>`, and legacy canonical XML `<tool_calls>` → `<invoke name="...">` → `<parameter name="...">`. The scanner normalizes fixed local names (`tool_calls` / `invoke` / `parameter`) with non-structural separators before or after them back to XML before parsing, and also tolerates CDATA opener drift such as `<![CDATA[` / `<、[CDATA[`; only wrapped tool blocks or the narrow missing-opening-wrapper repair path enter the tool path, while bare `<invoke>` does not count as supported syntax. JSON literal parameter bodies are preserved as structured values, explicit empty or whitespace-only parameters are preserved as empty strings, malformed complete wrappers are released as plain text, and loose CDATA is narrowly repaired at final parse/flush when it can preserve a complete outer tool call.
|
||||
- Tool-calling semantics are aligned between Go and Node runtime: models should output the fullwidth-separator DSML shell `<|DSML|tool_calls>` → `<|DSML|invoke name="...">` → `<|DSML|parameter name="...">`; DS2API also accepts the halfwidth DSML wrapper `<|DSML|tool_calls>`, DSML wrapper aliases such as `<dsml|tool_calls>`, `<|tool_calls>`, `<|tool_calls>`, common DSML separator drift such as `<|DSML tool_calls>`, collapsed DSML local names such as `<DSMLtool_calls>`, control-separator drift such as `<DSML␂tool_calls>` / raw STX `\x02`, CJK angle bracket, fullwidth-bang / ideographic-comma separator drift, PascalCase local-name drift, and trailing attribute separator drift such as `<DSM|parameter name="command"|>...〈/DSM|parameter〉`, `<!DSML!invoke name=“Bash”>`, `<、DSML、tool_calls>`, `<DSmartToolCalls>`, or `<DSMLtool_calls※>`, arbitrary protocol prefixes such as `<proto💥tool_calls>`, and legacy canonical XML `<tool_calls>` → `<invoke name="...">` → `<parameter name="...">`. The scanner normalizes fixed local names (`tool_calls` / `invoke` / `parameter`) with non-structural separators before or after them back to XML before parsing, and also tolerates CDATA opener drift such as `<![CDATA[` / `<、[CDATA[`; only wrapped tool blocks or the narrow missing-opening-wrapper repair path enter the tool path, while bare `<invoke>` does not count as supported syntax. JSON literal parameter bodies are preserved as structured values, explicit empty or whitespace-only parameters are preserved as empty strings, malformed complete wrappers are released as plain text, and loose CDATA is narrowly repaired at final parse/flush when it can preserve a complete outer tool call.
|
||||
- `Admin API` separates static config from runtime policy: `/admin/config*` for configuration state, `/admin/settings*` for runtime behavior.
|
||||
- When upstream returns a thinking-only response with no visible text, the Go main path for both streaming and non-streaming completions retries once in the same DeepSeek session: it appends the prompt suffix `"Previous reply had no visible output. Please regenerate the visible final answer or tool call now."` and sets `parent_message_id`. If that same-account retry would still end as `429 upstream_empty_output`, managed-account mode switches to the next available account, creates a fresh session, and retries the original payload once before returning 429.
|
||||
- Citation/reference marker boundary: streaming output hides upstream `[citation:N]` / `[reference:N]` placeholders by default; non-stream output converts DeepSeek search reference markers into Markdown links.
|
||||
@@ -355,7 +355,7 @@ When `tools` is present, DS2API performs anti-leak handling:
|
||||
|
||||
Additional notes:
|
||||
|
||||
- The parser treats the recommended DSML shell tool blocks (`<|DSML|tool_calls>` / `<|DSML|invoke name="...">` / `<|DSML|parameter name="...">`), halfwidth DSML shell blocks (`<|DSML|tool_calls>` / `<|DSML|invoke name="...">` / `<|DSML|parameter name="...">`), DSML wrapper aliases (`<dsml|tool_calls>`, `<|tool_calls>`, `<|tool_calls>`), common DSML separator drift (`<|DSML tool_calls>` / `<|DSML invoke>` / `<|DSML parameter>`), collapsed DSML local names (`<DSMLtool_calls>` / `<DSMLinvoke>` / `<DSMLparameter>`), control-separator drift (`<DSML␂tool_calls>` / raw STX `\x02`), CJK angle bracket, fullwidth-bang / ideographic-comma separator drift, and trailing attribute separator drift (`<DSM|parameter name="command"|>...〈/DSM|parameter〉` / `<!DSML!invoke name=“Bash”>` / `<、DSML、tool_calls>` / `<DSMLtool_calls※>`), arbitrary protocol prefixes (`<proto💥tool_calls>`), and legacy canonical XML tool blocks (`<tool_calls>` / `<invoke name="...">` / `<parameter name="...">`) as executable tool calls. These shells normalize non-structural separators back to XML first, while internal parsing remains XML-based; CDATA opener drift such as `<![CDATA[` / `<、[CDATA[` is also normalized for parameter bodies. Legacy `<tools>`, `<tool_call>`, `<tool_name>`, `<param>`, `<function_call>`, `tool_use`, antml variants, and standalone JSON `tool_calls` payloads are treated as plain text; complete but malformed wrappers are also released as plain text.
|
||||
- The parser treats the recommended DSML shell tool blocks (`<|DSML|tool_calls>` / `<|DSML|invoke name="...">` / `<|DSML|parameter name="...">`), halfwidth DSML shell blocks (`<|DSML|tool_calls>` / `<|DSML|invoke name="...">` / `<|DSML|parameter name="...">`), DSML wrapper aliases (`<dsml|tool_calls>`, `<|tool_calls>`, `<|tool_calls>`), common DSML separator drift (`<|DSML tool_calls>` / `<|DSML invoke>` / `<|DSML parameter>`), collapsed DSML local names (`<DSMLtool_calls>` / `<DSMLinvoke>` / `<DSMLparameter>`), control-separator drift (`<DSML␂tool_calls>` / raw STX `\x02`), CJK angle bracket, fullwidth-bang / ideographic-comma separator drift, PascalCase local-name drift, and trailing attribute separator drift (`<DSM|parameter name="command"|>...〈/DSM|parameter〉` / `<!DSML!invoke name=“Bash”>` / `<、DSML、tool_calls>` / `<DSmartToolCalls>` / `<DSMLtool_calls※>`), arbitrary protocol prefixes (`<proto💥tool_calls>`), and legacy canonical XML tool blocks (`<tool_calls>` / `<invoke name="...">` / `<parameter name="...">`) as executable tool calls. These shells normalize non-structural separators back to XML first, while internal parsing remains XML-based; CDATA opener drift such as `<![CDATA[` / `<、[CDATA[` is also normalized for parameter bodies. Legacy `<tools>`, `<tool_call>`, `<tool_name>`, `<param>`, `<function_call>`, `tool_use`, antml variants, and standalone JSON `tool_calls` payloads are treated as plain text; complete but malformed wrappers are also released as plain text.
|
||||
- The parser no longer drops tool calls solely because parameter values are empty; explicit empty strings or whitespace-only parameters become empty strings in structured `tool_calls`. Prompting still tells the model not to emit blank parameters, and missing/empty argument rejection belongs in the tool executor or client schema validation.
|
||||
- If the final visible response text is empty but the reasoning stream contains an executable tool call, Chat / Responses emits a standard OpenAI `tool_calls` / `function_call` output during finalization. If thinking/reasoning was not enabled by the client, that reasoning text is used only for detection and is not exposed as visible text or `reasoning_content`.
|
||||
- `tool_calls` shown inside fenced markdown code blocks (for example, ```json ... ```) are treated as examples, not executable calls.
|
||||
|
||||
4
API.md
4
API.md
@@ -40,7 +40,7 @@
|
||||
|
||||
- OpenAI / Claude / Gemini 三套协议已统一挂在同一 `chi` 路由树上,由 `internal/server/router.go` 负责装配。
|
||||
- 适配器层职责收敛为:**请求归一化 → DeepSeek 调用 → 协议形态渲染**,减少历史版本中“同能力多处实现”的分叉。
|
||||
- Tool Calling 的解析策略在 Go 与 Node Runtime 间保持一致:推荐模型输出全角分隔符 DSML 外壳 `<|DSML|tool_calls>` → `<|DSML|invoke name="...">` → `<|DSML|parameter name="...">`;兼容层也接受半角 DSML wrapper `<|DSML|tool_calls>`、DSML wrapper 别名 `<dsml|tool_calls>`、`<|tool_calls>`、`<|tool_calls>`、常见 DSML 分隔符漏写形态(如 `<|DSML tool_calls>`)、`DSML` 与工具标签名黏连的常见 typo(如 `<DSMLtool_calls>`)、控制分隔符漂移(如 `<DSML␂tool_calls>` / 原始 STX `\x02`)、CJK 尖括号、全角感叹号、顿号、弯引号属性值与属性尾部分隔符漂移(如 `<DSM|parameter name="command"|>...〈/DSM|parameter〉` / `<!DSML!invoke name=“Bash”>` / `<、DSML、tool_calls>` / `<DSMLtool_calls※>`)、任意协议前缀壳(如 `<proto💥tool_calls>`),以及旧式 canonical XML `<tool_calls>` → `<invoke name="...">` → `<parameter name="...">`。实现上采用结构扫描:只要固定本地标签名是 `tool_calls` / `invoke` / `parameter`,标签名前或标签名后的非结构性分隔符会在解析入口归一化;CDATA 开头也会容错 `<![CDATA[` / `<、[CDATA[` 这类分隔符漂移;只有 `tool_calls` wrapper 或可修复的缺失 opening wrapper 会进入工具路径,裸 `<invoke>` 不计为已支持语法;流式场景继续执行防泄漏筛分。若参数体本身是合法 JSON 字面量(如 `123`、`true`、`null`、数组或对象),会按结构化值输出,不再一律当作字符串;显式空字符串和纯空白参数会结构化保留为空字符串,是否拒绝缺参由工具执行侧决定;完整但 malformed 的 wrapper 会作为普通文本释放,不会吞掉或伪造成工具调用;若 CDATA 偶发漏闭合,则会在最终 parse / flush 恢复阶段做窄修复,尽量保住已完整包裹的外层工具调用。
|
||||
- Tool Calling 的解析策略在 Go 与 Node Runtime 间保持一致:推荐模型输出全角分隔符 DSML 外壳 `<|DSML|tool_calls>` → `<|DSML|invoke name="...">` → `<|DSML|parameter name="...">`;兼容层也接受半角 DSML wrapper `<|DSML|tool_calls>`、DSML wrapper 别名 `<dsml|tool_calls>`、`<|tool_calls>`、`<|tool_calls>`、常见 DSML 分隔符漏写形态(如 `<|DSML tool_calls>`)、`DSML` 与工具标签名黏连的常见 typo(如 `<DSMLtool_calls>`)、控制分隔符漂移(如 `<DSML␂tool_calls>` / 原始 STX `\x02`)、CJK 尖括号、全角感叹号、顿号、PascalCase 本地名、弯引号属性值与属性尾部分隔符漂移(如 `<DSM|parameter name="command"|>...〈/DSM|parameter〉` / `<!DSML!invoke name=“Bash”>` / `<、DSML、tool_calls>` / `<DSmartToolCalls>` / `<DSMLtool_calls※>`)、任意协议前缀壳(如 `<proto💥tool_calls>`),以及旧式 canonical XML `<tool_calls>` → `<invoke name="...">` → `<parameter name="...">`。实现上采用结构扫描:只要固定本地标签名是 `tool_calls` / `invoke` / `parameter`,标签名前或标签名后的非结构性分隔符会在解析入口归一化;CDATA 开头也会容错 `<![CDATA[` / `<、[CDATA[` 这类分隔符漂移;只有 `tool_calls` wrapper 或可修复的缺失 opening wrapper 会进入工具路径,裸 `<invoke>` 不计为已支持语法;流式场景继续执行防泄漏筛分。若参数体本身是合法 JSON 字面量(如 `123`、`true`、`null`、数组或对象),会按结构化值输出,不再一律当作字符串;显式空字符串和纯空白参数会结构化保留为空字符串,是否拒绝缺参由工具执行侧决定;完整但 malformed 的 wrapper 会作为普通文本释放,不会吞掉或伪造成工具调用;若 CDATA 偶发漏闭合,则会在最终 parse / flush 恢复阶段做窄修复,尽量保住已完整包裹的外层工具调用。
|
||||
- `Admin API` 将配置与运行时策略分开:`/admin/config*` 管静态配置,`/admin/settings*` 管运行时行为。
|
||||
- 当上游返回 thinking-only 响应(模型输出了推理链但无可见文本)时,Go 主路径的流式与非流式补全都会先自动重试一次:以多轮对话 follow-up 方式追加 prompt 后缀 `"Previous reply had no visible output. Please regenerate the visible final answer or tool call now."` 并设置 `parent_message_id` 在同一 DeepSeek session 内让模型重新输出;同账号重试最大 1 次。若同账号重试后仍即将返回 `429 upstream_empty_output`,托管账号模式会在返回 429 前自动切换到下一个可用账号,新建 session,用原始 payload 再 fresh retry 一次。
|
||||
- 引用标记处理边界:流式输出默认隐藏 `[citation:N]` / `[reference:N]` 这类上游内部占位符;非流式输出默认把 DeepSeek 搜索引用标记转换为 Markdown 引用链接。
|
||||
@@ -357,7 +357,7 @@ data: [DONE]
|
||||
补充说明:
|
||||
|
||||
- **非代码块上下文**下,工具负载即使与普通文本混合,也会按特征识别并产出可执行 tool call(前后普通文本仍可透传)。
|
||||
- 解析器当前把推荐 DSML 外壳(`<|DSML|tool_calls>` / `<|DSML|invoke name="...">` / `<|DSML|parameter name="...">`)、半角 DSML 外壳(`<|DSML|tool_calls>` / `<|DSML|invoke name="...">` / `<|DSML|parameter name="...">`)、DSML wrapper 别名(`<dsml|tool_calls>`、`<|tool_calls>`、`<|tool_calls>`)、常见 DSML 分隔符漏写形态(如 `<|DSML tool_calls>` / `<|DSML invoke>` / `<|DSML parameter>`)、`DSML` 与工具标签名黏连的常见 typo(如 `<DSMLtool_calls>` / `<DSMLinvoke>` / `<DSMLparameter>`)、控制分隔符漂移(如 `<DSML␂tool_calls>` / 原始 STX `\x02`)、CJK 尖括号、全角感叹号、顿号、弯引号属性值与属性尾部分隔符漂移(如 `<DSM|parameter name="command"|>...〈/DSM|parameter〉` / `<!DSML!invoke name=“Bash”>` / `<、DSML、tool_calls>` / `<DSMLtool_calls※>`)、任意协议前缀壳(如 `<proto💥tool_calls>`)和旧式 canonical XML 工具块(`<tool_calls>` / `<invoke name="...">` / `<parameter name="...">`)作为可执行调用解析;这些非结构性分隔符壳会先归一化回 XML,内部仍以 XML 解析语义为准,CDATA 开头也会容错 `<![CDATA[` / `<、[CDATA[`。旧式 `<tools>`、`<tool_call>`、`<tool_name>`、`<param>`、`<function_call>`、`tool_use`、antml 风格与纯 JSON `tool_calls` 片段默认都会按普通文本处理;完整但 malformed 的 wrapper 同样会作为普通文本释放。
|
||||
- 解析器当前把推荐 DSML 外壳(`<|DSML|tool_calls>` / `<|DSML|invoke name="...">` / `<|DSML|parameter name="...">`)、半角 DSML 外壳(`<|DSML|tool_calls>` / `<|DSML|invoke name="...">` / `<|DSML|parameter name="...">`)、DSML wrapper 别名(`<dsml|tool_calls>`、`<|tool_calls>`、`<|tool_calls>`)、常见 DSML 分隔符漏写形态(如 `<|DSML tool_calls>` / `<|DSML invoke>` / `<|DSML parameter>`)、`DSML` 与工具标签名黏连的常见 typo(如 `<DSMLtool_calls>` / `<DSMLinvoke>` / `<DSMLparameter>`)、控制分隔符漂移(如 `<DSML␂tool_calls>` / 原始 STX `\x02`)、CJK 尖括号、全角感叹号、顿号、PascalCase 本地名、弯引号属性值与属性尾部分隔符漂移(如 `<DSM|parameter name="command"|>...〈/DSM|parameter〉` / `<!DSML!invoke name=“Bash”>` / `<、DSML、tool_calls>` / `<DSmartToolCalls>` / `<DSMLtool_calls※>`)、任意协议前缀壳(如 `<proto💥tool_calls>`)和旧式 canonical XML 工具块(`<tool_calls>` / `<invoke name="...">` / `<parameter name="...">`)作为可执行调用解析;这些非结构性分隔符壳会先归一化回 XML,内部仍以 XML 解析语义为准,CDATA 开头也会容错 `<![CDATA[` / `<、[CDATA[`。旧式 `<tools>`、`<tool_call>`、`<tool_name>`、`<param>`、`<function_call>`、`tool_use`、antml 风格与纯 JSON `tool_calls` 片段默认都会按普通文本处理;完整但 malformed 的 wrapper 同样会作为普通文本释放。
|
||||
- 解析层不会因为参数值为空而丢弃工具调用;显式空字符串或纯空白参数会按空字符串进入结构化 `tool_calls`。Prompt 会要求模型不要主动输出空参数,缺参/空命令的拒绝应由工具执行侧或客户端 schema 校验负责。
|
||||
- 当最终可见正文为空但思维链里包含可执行工具调用时,Chat / Responses 会在收尾阶段补发标准 OpenAI `tool_calls` / `function_call` 输出;如果客户端未开启 thinking / reasoning,该思维链只用于检测,不会作为可见正文或 `reasoning_content` 暴露。
|
||||
- Markdown fenced code block(例如 ```json ... ```)中的 `tool_calls` 仅视为示例文本,不会被执行。
|
||||
|
||||
@@ -168,7 +168,7 @@ OpenAI Chat / Responses 在标准化后、current input file 之前,会默认
|
||||
4. 把这整段内容并入 system prompt。
|
||||
|
||||
工具调用正例现在优先示范全角分隔符 DSML 风格:`<|DSML|tool_calls>` → `<|DSML|invoke name="...">` → `<|DSML|parameter name="...">`。
|
||||
兼容层仍接受旧式纯 `<tool_calls>` wrapper,并会容错若干 DSML 标签变体,包括短横线形式 `<dsml-tool-calls>` / `<dsml-invoke>` / `<dsml-parameter>`、下划线形式 `<dsml_tool_calls>` / `<dsml_invoke>` / `<dsml_parameter>`,以及其他前缀分隔形态如 `<vendor|tool_calls>` / `<vendor_tool_calls>` / `<vendor - tool_calls>`;标签壳扫描还会把全角 ASCII 漂移归一化,例如 `<dSML|tool_calls>` 与全角 `>` 结束符,也会容错 CJK 尖括号、全角感叹号或顿号分隔符、弯引号属性值和属性尾部分隔符漂移,例如 `<DSM|parameter name="command"|>...〈/DSM|parameter〉`、`<!DSML!invoke name=“Bash”>`、`<、DSML、tool_calls>`、`<DSMLtool_calls※>`。更一般地,Go / Node tag 扫描以固定本地标签名 `tool_calls` / `invoke` / `parameter` 为准,标签名前或标签名后的非结构性协议分隔符都会在解析入口剥离,例如 `<DSML␂tool_calls>`、`<proto💥tool_calls>` 这类控制符或非 ASCII 分隔符漂移也会归一化回现有 XML 标签后继续走同一套 parser;结构性字符如 `<` / `>` / `/` / `=` / 引号、空白和 ASCII 字母数字不会被当作这类分隔符。CDATA 开头也使用同一类扫描式容错,`<![CDATA[` / `<![CDATA[` / `<、[CDATA[` 都会作为参数原文容器处理。但提示词会优先要求模型输出官方 DSML 标签,并强调不能只输出 closing wrapper 而漏掉 opening tag。需要注意:这是“兼容 DSML 外壳,内部仍以 XML 解析语义为准”,不是原生 DSML 全链路实现。解析器会先截获非代码块中的疑似工具 wrapper,完整解析失败或工具语义无效时再按普通文本放行。
|
||||
兼容层仍接受旧式纯 `<tool_calls>` wrapper,并会容错若干 DSML 标签变体,包括短横线形式 `<dsml-tool-calls>` / `<dsml-invoke>` / `<dsml-parameter>`、下划线形式 `<dsml_tool_calls>` / `<dsml_invoke>` / `<dsml_parameter>`,以及其他前缀分隔形态如 `<vendor|tool_calls>` / `<vendor_tool_calls>` / `<vendor - tool_calls>`;标签壳扫描还会把全角 ASCII 漂移归一化,例如 `<dSML|tool_calls>` 与全角 `>` 结束符,也会容错 CJK 尖括号、全角感叹号或顿号分隔符、弯引号属性值、PascalCase 本地名和属性尾部分隔符漂移,例如 `<DSM|parameter name="command"|>...〈/DSM|parameter〉`、`<!DSML!invoke name=“Bash”>`、`<、DSML、tool_calls>`、`<DSmartToolCalls>`、`<DSMLtool_calls※>`。更一般地,Go / Node tag 扫描以固定本地标签名 `tool_calls` / `invoke` / `parameter` 为准,标签名前或标签名后的非结构性协议分隔符都会在解析入口剥离,例如 `<DSML␂tool_calls>`、`<proto💥tool_calls>` 这类控制符或非 ASCII 分隔符漂移也会归一化回现有 XML 标签后继续走同一套 parser;结构性字符如 `<` / `>` / `/` / `=` / 引号、空白和 ASCII 字母数字不会被当作这类分隔符。CDATA 开头也使用同一类扫描式容错,`<![CDATA[` / `<![CDATA[` / `<、[CDATA[` 都会作为参数原文容器处理。但提示词会优先要求模型输出官方 DSML 标签,并强调不能只输出 closing wrapper 而漏掉 opening tag。需要注意:这是“兼容 DSML 外壳,内部仍以 XML 解析语义为准”,不是原生 DSML 全链路实现。解析器会先截获非代码块中的疑似工具 wrapper,完整解析失败或工具语义无效时再按普通文本放行。
|
||||
数组参数使用 `<item>...</item>` 子节点表示;当某个参数体只包含 item 子节点时,Go / Node 解析器会把它还原成数组,避免 `questions` / `options` 这类 schema 中要求 array 的参数被误解析成 `{ "item": ... }` 对象。除此之外,解析器还会回收一些更松散的列表写法,例如 JSON array 字面量或逗号分隔的 JSON 项序列,只要它们足够明确;但 `<item>` 仍然是首选形态。若模型把完整结构化 XML fragment 误包进 CDATA,兼容层会在保护 `content` / `command` 等原文字段的前提下,尝试把非原文字段中的 CDATA XML fragment 还原成 object / array。不过,如果 CDATA 只是单个平面的 XML/HTML 标签,例如 `<b>urgent</b>` 这种行内标记,兼容层会保留原始字符串,不会强行升成 object / array;只有明显表示结构的 CDATA 片段,例如多兄弟节点、嵌套子节点或 `item` 列表,才会触发结构化恢复。对 `command` / `content` 等长文本参数,CDATA 内部的 Markdown fenced DSML / XML 示例会作为原文保护;示例里的 `]]></parameter>` 或 `</tool_calls>` 不会截断外层工具调用,解析器会继续等待围栏外真正的参数 / wrapper 结束标签。
|
||||
Go 侧读取 DeepSeek SSE 时不再依赖 `bufio.Scanner` 的固定 2MiB 单行上限;当写文件类工具把很长的 `content` 放在单个 `data:` 行里返回时,非流式收集、流式解析和 auto-continue 透传都会保留完整行,再进入同一套工具解析与序列化流程。
|
||||
在 assistant 最终回包阶段,如果某个 tool 参数在声明 schema 中明确是 `string`,兼容层会在把解析后的 `tool_calls` / `function_call` 重新序列化成 OpenAI / Responses / Claude 可见参数前,递归把该路径上的 number / bool / object / array 统一转成字符串;其中 object / array 会压成紧凑 JSON 字符串。这个保护只对 schema 明确声明为 string 的路径生效,不会改写本来就是 `number` / `boolean` / `object` / `array` 的参数。这样可以兼容 DeepSeek 输出了结构化片段、但上游客户端工具 schema 又严格要求字符串参数的场景(例如 `content`、`prompt`、`path`、`taskId` 等)。
|
||||
|
||||
@@ -39,7 +39,7 @@
|
||||
兼容修复:
|
||||
|
||||
- 如果模型漏掉 opening wrapper,但后面仍输出了一个或多个 invoke 并以 closing wrapper 收尾,Go 解析链路会在解析前补回缺失的 opening wrapper。
|
||||
- Go / Node 解析层不再枚举每一种 DSML typo。它以固定本地标签名 `tool_calls` / `invoke` / `parameter` 为准,把标签名前的任意协议前缀壳视为可容忍噪声,并继续兼容管道符 `|` / `|`、全角感叹号 `!`、顿号 `、`、空白、重复 leading `<`、可视控制符 `␂`、原始 STX `\x02`、非 ASCII 分隔符、CJK 尖括号 `〈` / `〉`、弯引号属性值等漂移。例如 `<DSML|tool_calls>`、`<<|DSML|tool_calls>`、`<|DSML tool_calls>`、`<DSMLtool_calls>`、`<<DSML|DSML|tool_calls>`、`<DSML␂tool_calls>`、`<proto💥tool_calls>`、`<DSM|tool_calls>...〈/DSM|tool_calls〉`、`<!DSML!tool_calls>...<!/DSML!tool_calls>`、`<、DSML、tool_calls>...<、/DSML、tool_calls>` 都会归一化;相似但非固定标签名(如 `tool_calls_extra`)仍按普通文本处理。
|
||||
- Go / Node 解析层不再枚举每一种 DSML typo。它以固定本地标签名 `tool_calls` / `invoke` / `parameter` 为准,把标签名前的任意协议前缀壳视为可容忍噪声,并继续兼容管道符 `|` / `|`、全角感叹号 `!`、顿号 `、`、空白、重复 leading `<`、可视控制符 `␂`、原始 STX `\x02`、非 ASCII 分隔符、CJK 尖括号 `〈` / `〉`、弯引号属性值、PascalCase 本地名等漂移。例如 `<DSML|tool_calls>`、`<<|DSML|tool_calls>`、`<|DSML tool_calls>`、`<DSMLtool_calls>`、`<DSmartToolCalls>`、`<<DSML|DSML|tool_calls>`、`<DSML␂tool_calls>`、`<proto💥tool_calls>`、`<DSM|tool_calls>...〈/DSM|tool_calls〉`、`<!DSML!tool_calls>...<!/DSML!tool_calls>`、`<、DSML、tool_calls>...<、/DSML、tool_calls>` 都会归一化;相似但非固定标签名(如 `tool_calls_extra` / `ToolCallsExtra`)仍按普通文本处理。
|
||||
- 如果模型在固定工具标签名后多输出一个非结构性分隔符,例如 `<|DSML|tool_calls|` / `<|DSML|invoke|` / `<|DSML|parameter|` / `<DSMLtool_calls※>`,或在带属性标签的结束符前多输出一个尾部分隔符(如 `<DSM|parameter name="command"|>`),兼容层会把这个尾部分隔符当作异常标签终止符并补齐或归一化;如果后面已经有 `>` / `〉`,也会消费这个多余分隔符后再归一化。结构性字符如 `<` / `>` / `/` / `=` / 引号、空白和 ASCII 字母数字不会被当作这类分隔符。
|
||||
- 这是一个针对常见模型失误的窄修复,不改变推荐输出格式;prompt 仍要求模型直接输出完整 DSML 外壳。
|
||||
- 裸 `<invoke ...>` / `<parameter ...>` 不会被当成“已支持的工具语法”;只有 `tool_calls` wrapper 或可修复的缺失 opening wrapper 才会进入工具调用路径。
|
||||
@@ -103,7 +103,7 @@ go test -v -run 'TestParseToolCalls|TestProcessToolSieve' ./internal/toolcall ./
|
||||
|
||||
- DSML `<|DSML|tool_calls>` wrapper 正常解析
|
||||
- legacy canonical `<tool_calls>` wrapper 正常解析
|
||||
- 固定本地标签名的 DSML 噪声容错形态(如 `<DSML|tool_calls>`、`<<|DSML|tool_calls>`、`<|DSML tool_calls>`、`<DSMLtool_calls>`、`<<DSML|DSML|tool_calls>`、`<DSM|tool_calls>...〈/DSM|tool_calls〉`、`<!DSML!tool_calls>...<!/DSML!tool_calls>`)正常解析
|
||||
- 固定本地标签名的 DSML 噪声容错形态(如 `<DSML|tool_calls>`、`<<|DSML|tool_calls>`、`<|DSML tool_calls>`、`<DSMLtool_calls>`、`<DSmartToolCalls>`、`<<DSML|DSML|tool_calls>`、`<DSM|tool_calls>...〈/DSM|tool_calls〉`、`<!DSML!tool_calls>...<!/DSML!tool_calls>`)正常解析
|
||||
- 混搭标签(DSML wrapper + canonical inner)归一化后正常解析
|
||||
- 波浪线围栏 `~~~` 内的示例不执行
|
||||
- 嵌套围栏(4 反引号嵌套 3 反引号)内的示例不执行
|
||||
|
||||
@@ -5,6 +5,7 @@ const XML_ATTR_PATTERN = /\b([a-z0-9_:-]+)\s*=\s*("([^"]*)"|'([^']*)')/gi;
|
||||
const TOOL_MARKUP_NAMES = [
|
||||
{ raw: 'tool_calls', canonical: 'tool_calls' },
|
||||
{ raw: 'tool-calls', canonical: 'tool_calls', dsmlOnly: true },
|
||||
{ raw: 'toolcalls', canonical: 'tool_calls', dsmlOnly: true },
|
||||
{ raw: 'invoke', canonical: 'invoke' },
|
||||
{ raw: 'parameter', canonical: 'parameter' },
|
||||
];
|
||||
@@ -698,7 +699,7 @@ function matchToolMarkupNameAfterArbitraryPrefix(raw, start) {
|
||||
for (const name of TOOL_MARKUP_NAMES) {
|
||||
const matched = matchNormalizedASCII(raw, idx, name.raw);
|
||||
if (!matched.ok) continue;
|
||||
if (!toolMarkupPrefixAllowsLocalName(raw.slice(start, idx))) continue;
|
||||
if (!toolMarkupPrefixAllowsLocalNameAt(raw, start, idx)) continue;
|
||||
return { ok: true, name: name.canonical, start: idx, len: matched.len };
|
||||
}
|
||||
idx += 1;
|
||||
@@ -711,10 +712,10 @@ function hasPartialToolMarkupNameAfterArbitraryPrefix(raw, start) {
|
||||
if (isToolMarkupTagTerminator(raw, idx)) {
|
||||
return false;
|
||||
}
|
||||
if (toolMarkupPrefixAllowsLocalName(raw.slice(start, idx)) && hasToolMarkupNamePrefix(raw, idx)) {
|
||||
if (toolMarkupPrefixAllowsLocalNameAt(raw, start, idx) && hasToolMarkupNamePrefix(raw, idx)) {
|
||||
return true;
|
||||
}
|
||||
if (toolMarkupPrefixAllowsLocalName(raw.slice(start, idx)) && hasDSMLNamePrefixOrPartial(raw, idx)) {
|
||||
if (toolMarkupPrefixAllowsLocalNameAt(raw, start, idx) && hasDSMLNamePrefixOrPartial(raw, idx)) {
|
||||
return true;
|
||||
}
|
||||
idx += 1;
|
||||
@@ -741,6 +742,22 @@ function toolMarkupPrefixAllowsLocalName(prefix) {
|
||||
return !/^[A-Za-z0-9]$/.test(previous);
|
||||
}
|
||||
|
||||
function toolMarkupPrefixAllowsLocalNameAt(raw, start, localStart) {
|
||||
if (start < 0 || localStart <= start || localStart > raw.length) {
|
||||
return false;
|
||||
}
|
||||
const prefix = raw.slice(start, localStart);
|
||||
if (toolMarkupPrefixAllowsLocalName(prefix)) {
|
||||
return true;
|
||||
}
|
||||
if (/[="'"]/.test(prefix)) {
|
||||
return false;
|
||||
}
|
||||
const previous = normalizeFullwidthASCIIChar(prefix[prefix.length - 1] || '');
|
||||
const next = normalizeFullwidthASCIIChar(raw[localStart] || '');
|
||||
return /^[A-Za-z0-9]$/.test(previous) && /^[A-Z]$/.test(next);
|
||||
}
|
||||
|
||||
function toolMarkupPrefixContainsSlash(prefix) {
|
||||
for (const ch of toStringSafe(prefix)) {
|
||||
if (normalizeFullwidthASCIIChar(ch) === '/') {
|
||||
|
||||
@@ -14,6 +14,7 @@ type toolMarkupNameAlias struct {
|
||||
var toolMarkupNames = []toolMarkupNameAlias{
|
||||
{raw: "tool_calls", canonical: "tool_calls"},
|
||||
{raw: "tool-calls", canonical: "tool_calls", dsmlOnly: true},
|
||||
{raw: "toolcalls", canonical: "tool_calls", dsmlOnly: true},
|
||||
{raw: "invoke", canonical: "invoke"},
|
||||
{raw: "parameter", canonical: "parameter"},
|
||||
}
|
||||
@@ -369,7 +370,7 @@ func matchToolMarkupNameAfterArbitraryPrefix(text string, start int) (string, in
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
if !toolMarkupPrefixAllowsLocalName(text[start:idx]) {
|
||||
if !toolMarkupPrefixAllowsLocalNameAt(text, start, idx) {
|
||||
continue
|
||||
}
|
||||
return name.canonical, idx, nameLen, true
|
||||
@@ -388,10 +389,10 @@ func hasPartialToolMarkupNameAfterArbitraryPrefix(text string, start int) bool {
|
||||
if isToolMarkupTagTerminator(text, idx) {
|
||||
return false
|
||||
}
|
||||
if toolMarkupPrefixAllowsLocalName(text[start:idx]) && hasToolMarkupNamePrefix(text, idx) {
|
||||
if toolMarkupPrefixAllowsLocalNameAt(text, start, idx) && hasToolMarkupNamePrefix(text, idx) {
|
||||
return true
|
||||
}
|
||||
if toolMarkupPrefixAllowsLocalName(text[start:idx]) && hasDSMLNamePrefixOrPartial(text, idx) {
|
||||
if toolMarkupPrefixAllowsLocalNameAt(text, start, idx) && hasDSMLNamePrefixOrPartial(text, idx) {
|
||||
return true
|
||||
}
|
||||
_, size := utf8.DecodeRuneInString(text[idx:])
|
||||
@@ -403,6 +404,25 @@ func hasPartialToolMarkupNameAfterArbitraryPrefix(text string, start int) bool {
|
||||
return toolMarkupPrefixAllowsLocalName(text[start:])
|
||||
}
|
||||
|
||||
func toolMarkupPrefixAllowsLocalNameAt(text string, start, localStart int) bool {
|
||||
if start < 0 || localStart <= start || localStart > len(text) {
|
||||
return false
|
||||
}
|
||||
prefix := text[start:localStart]
|
||||
if toolMarkupPrefixAllowsLocalName(prefix) {
|
||||
return true
|
||||
}
|
||||
if strings.ContainsAny(prefix, "=\"'") {
|
||||
return false
|
||||
}
|
||||
prev, prevSize := utf8.DecodeLastRuneInString(prefix)
|
||||
next, _ := utf8.DecodeRuneInString(text[localStart:])
|
||||
if prevSize <= 0 || next == utf8.RuneError {
|
||||
return false
|
||||
}
|
||||
return isASCIIAlphaNumeric(normalizeFullwidthASCII(prev)) && isASCIIUpper(normalizeFullwidthASCII(next))
|
||||
}
|
||||
|
||||
func hasDSMLNamePrefixOrPartial(text string, start int) bool {
|
||||
return hasASCIIPrefixFoldAt(text, start, "dsml") || hasASCIIPartialPrefixFoldAt(text, start, "dsml")
|
||||
}
|
||||
@@ -437,6 +457,14 @@ func normalizedASCIILowerString(text string) string {
|
||||
return b.String()
|
||||
}
|
||||
|
||||
func isASCIIAlphaNumeric(r rune) bool {
|
||||
return (r >= 'a' && r <= 'z') || (r >= 'A' && r <= 'Z') || (r >= '0' && r <= '9')
|
||||
}
|
||||
|
||||
func isASCIIUpper(r rune) bool {
|
||||
return r >= 'A' && r <= 'Z'
|
||||
}
|
||||
|
||||
func isToolMarkupTagTerminator(text string, idx int) bool {
|
||||
if idx >= len(text) {
|
||||
return false
|
||||
|
||||
@@ -111,6 +111,25 @@ func TestParseToolCallsSupportsArbitraryPrefixedToolMarkup(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestParseToolCallsSupportsCamelPrefixedToolMarkup(t *testing.T) {
|
||||
text := `<DSmartToolCalls><DSmartInvoke name="Bash"><DSmartParameter name="command"><![CDATA[git push]]></DSmartParameter><DSmartParameter name="description"><![CDATA[Push dev branch to origin]]></DSmartParameter></DSmartInvoke></DSmartToolCalls>`
|
||||
calls := ParseToolCalls(text, []string{"Bash"})
|
||||
if len(calls) != 1 {
|
||||
t.Fatalf("expected one camel-prefixed tool call, got %#v", calls)
|
||||
}
|
||||
if calls[0].Name != "Bash" || calls[0].Input["command"] != "git push" || calls[0].Input["description"] != "Push dev branch to origin" {
|
||||
t.Fatalf("unexpected camel-prefixed tool call: %#v", calls[0])
|
||||
}
|
||||
}
|
||||
|
||||
func TestParseToolCallsRejectsCamelPrefixedToolMarkupLookalike(t *testing.T) {
|
||||
text := `<DSmartToolCallsExtra><DSmartInvoke name="Bash"><DSmartParameter name="command">git push</DSmartParameter></DSmartInvoke></DSmartToolCallsExtra>`
|
||||
calls := ParseToolCalls(text, []string{"Bash"})
|
||||
if len(calls) != 0 {
|
||||
t.Fatalf("expected camel-prefixed lookalike to be ignored, got %#v", calls)
|
||||
}
|
||||
}
|
||||
|
||||
func TestParseToolCallsSupportsFullwidthDSMLShell(t *testing.T) {
|
||||
text := `<dSML|tool_calls>
|
||||
<dSML|invoke name="Read">
|
||||
|
||||
@@ -112,6 +112,23 @@ test('parseToolCalls parses arbitrary-prefixed tool markup shells', () => {
|
||||
}
|
||||
});
|
||||
|
||||
test('parseToolCalls parses camel-prefixed tool markup shell', () => {
|
||||
const payload = '<DSmartToolCalls><DSmartInvoke name="Bash"><DSmartParameter name="command"><![CDATA[git push]]></DSmartParameter><DSmartParameter name="description"><![CDATA[Push dev branch to origin]]></DSmartParameter></DSmartInvoke></DSmartToolCalls>';
|
||||
const calls = parseToolCalls(payload, ['Bash']);
|
||||
assert.equal(calls.length, 1);
|
||||
assert.equal(calls[0].name, 'Bash');
|
||||
assert.deepEqual(calls[0].input, {
|
||||
command: 'git push',
|
||||
description: 'Push dev branch to origin',
|
||||
});
|
||||
});
|
||||
|
||||
test('parseToolCalls ignores camel-prefixed tool markup lookalike', () => {
|
||||
const payload = '<DSmartToolCallsExtra><DSmartInvoke name="Bash"><DSmartParameter name="command">git push</DSmartParameter></DSmartInvoke></DSmartToolCallsExtra>';
|
||||
const calls = parseToolCalls(payload, ['Bash']);
|
||||
assert.equal(calls.length, 0);
|
||||
});
|
||||
|
||||
test('parseToolCalls parses fullwidth DSML shell drift', () => {
|
||||
const payload = `<dSML|tool_calls>
|
||||
<dSML|invoke name="Read">
|
||||
|
||||
Reference in New Issue
Block a user