测试DSML

This commit is contained in:
CJACK
2026-04-27 00:21:26 +08:00
parent 645fce41c8
commit 40d5e3ebb5
50 changed files with 1112 additions and 265 deletions

View File

@@ -11,44 +11,45 @@ import "strings"
func BuildToolCallInstructions(toolNames []string) string {
return `TOOL CALL FORMAT — FOLLOW EXACTLY:
<tool_calls>
<invoke name="TOOL_NAME_HERE">
<parameter name="PARAMETER_NAME"><![CDATA[PARAMETER_VALUE]]></parameter>
</invoke>
</tool_calls>
<|DSML|tool_calls>
<|DSML|invoke name="TOOL_NAME_HERE">
<|DSML|parameter name="PARAMETER_NAME"><![CDATA[PARAMETER_VALUE]]></|DSML|parameter>
</|DSML|invoke>
</|DSML|tool_calls>
RULES:
1) Use the <tool_calls> XML wrapper format only.
2) Put one or more <invoke> entries under a single <tool_calls> root.
3) Put the tool name in the invoke name attribute: <invoke name="TOOL_NAME">.
1) Use the <|DSML|tool_calls> wrapper format.
2) Put one or more <|DSML|invoke> entries under a single <|DSML|tool_calls> root.
3) Put the tool name in the invoke name attribute: <|DSML|invoke name="TOOL_NAME">.
4) All string values must use <![CDATA[...]]>, even short ones. This includes code, scripts, file contents, prompts, paths, names, and queries.
5) Every top-level argument must be a <parameter name="ARG_NAME">...</parameter> node.
5) Every top-level argument must be a <|DSML|parameter name="ARG_NAME">...</|DSML|parameter> node.
6) Objects use nested XML elements inside the parameter body. Arrays may repeat <item> children.
7) Numbers, booleans, and null stay plain text.
8) Use only the parameter names in the tool schema. Do not invent fields.
9) Do NOT wrap XML in markdown fences. Do NOT output explanations, role markers, or internal monologue.
10) If you call a tool, the first non-whitespace characters of that tool block must be exactly <tool_calls>.
11) Never omit the opening <tool_calls> tag, even if you already plan to close with </tool_calls>.
10) If you call a tool, the first non-whitespace characters of that tool block must be exactly <|DSML|tool_calls>.
11) Never omit the opening <|DSML|tool_calls> tag, even if you already plan to close with </|DSML|tool_calls>.
12) Compatibility note: the runtime also accepts the legacy XML tags <tool_calls> / <invoke> / <parameter>, but prefer the DSML-prefixed form above.
PARAMETER SHAPES:
- string => <parameter name="x"><![CDATA[value]]></parameter>
- object => <parameter name="x"><field>...</field></parameter>
- array => <parameter name="x"><item>...</item><item>...</item></parameter>
- number/bool/null => <parameter name="x">plain_text</parameter>
- string => <|DSML|parameter name="x"><![CDATA[value]]></|DSML|parameter>
- object => <|DSML|parameter name="x"><field>...</field></|DSML|parameter>
- array => <|DSML|parameter name="x"><item>...</item><item>...</item></|DSML|parameter>
- number/bool/null => <|DSML|parameter name="x">plain_text</|DSML|parameter>
【WRONG — Do NOT do these】:
Wrong 1 — mixed text after XML:
<tool_calls>...</tool_calls> I hope this helps.
<|DSML|tool_calls>...</|DSML|tool_calls> I hope this helps.
Wrong 2 — Markdown code fences:
` + "```xml" + `
<tool_calls>...</tool_calls>
<|DSML|tool_calls>...</|DSML|tool_calls>
` + "```" + `
Wrong 3 — missing opening wrapper:
<invoke name="TOOL_NAME">...</invoke>
</tool_calls>
<|DSML|invoke name="TOOL_NAME">...</|DSML|invoke>
</|DSML|tool_calls>
Remember: The ONLY valid way to use tools is the <tool_calls>...</tool_calls> XML block at the end of your response.
Remember: The ONLY valid way to use tools is the <|DSML|tool_calls>...</|DSML|tool_calls> block at the end of your response.
` + buildCorrectToolExamples(toolNames)
}
@@ -140,21 +141,21 @@ func firstScriptExample(names []string) (promptToolExample, bool) {
func renderToolExampleBlock(calls []promptToolExample) string {
var b strings.Builder
b.WriteString("<tool_calls>\n")
b.WriteString("<|DSML|tool_calls>\n")
for _, call := range calls {
b.WriteString(` <invoke name="`)
b.WriteString(` <|DSML|invoke name="`)
b.WriteString(call.name)
b.WriteString("\">\n")
b.WriteString(`">` + "\n")
b.WriteString(indentPromptParameters(call.params, " "))
b.WriteString("\n </invoke>\n")
b.WriteString("\n </|DSML|invoke>\n")
}
b.WriteString("</tool_calls>")
b.WriteString("</|DSML|tool_calls>")
return b.String()
}
func indentPromptParameters(body, indent string) string {
if strings.TrimSpace(body) == "" {
return indent + `<parameter name="content"></parameter>`
return indent + `<|DSML|parameter name="content"></|DSML|parameter>`
}
lines := strings.Split(body, "\n")
for i, line := range lines {
@@ -168,7 +169,7 @@ func indentPromptParameters(body, indent string) string {
}
func wrapParameter(name, inner string) string {
return `<parameter name="` + name + `">` + inner + `</parameter>`
return `<|DSML|parameter name="` + name + `">` + inner + `</|DSML|parameter>`
}
func exampleBasicParams(name string) (string, bool) {
@@ -194,7 +195,7 @@ func exampleBasicParams(name string) (string, bool) {
case "Edit":
return wrapParameter("file_path", promptCDATA("README.md")) + "\n" + wrapParameter("old_string", promptCDATA("foo")) + "\n" + wrapParameter("new_string", promptCDATA("bar")), true
case "MultiEdit":
return wrapParameter("file_path", promptCDATA("README.md")) + "\n" + `<parameter name="edits"><item><old_string>` + promptCDATA("foo") + `</old_string><new_string>` + promptCDATA("bar") + `</new_string></item></parameter>`, true
return wrapParameter("file_path", promptCDATA("README.md")) + "\n" + `<|DSML|parameter name="edits"><item><old_string>` + promptCDATA("foo") + `</old_string><new_string>` + promptCDATA("bar") + `</new_string></item></|DSML|parameter>`, true
}
return "", false
}
@@ -202,11 +203,11 @@ func exampleBasicParams(name string) (string, bool) {
func exampleNestedParams(name string) (string, bool) {
switch strings.TrimSpace(name) {
case "MultiEdit":
return wrapParameter("file_path", promptCDATA("README.md")) + "\n" + `<parameter name="edits"><item><old_string>` + promptCDATA("foo") + `</old_string><new_string>` + promptCDATA("bar") + `</new_string></item></parameter>`, true
return wrapParameter("file_path", promptCDATA("README.md")) + "\n" + `<|DSML|parameter name="edits"><item><old_string>` + promptCDATA("foo") + `</old_string><new_string>` + promptCDATA("bar") + `</new_string></item></|DSML|parameter>`, true
case "Task":
return wrapParameter("description", promptCDATA("Investigate flaky tests")) + "\n" + wrapParameter("prompt", promptCDATA("Run targeted tests and summarize failures")), true
case "ask_followup_question":
return wrapParameter("question", promptCDATA("Which approach do you prefer?")) + "\n" + `<parameter name="follow_up"><item><text>` + promptCDATA("Option A") + `</text></item><item><text>` + promptCDATA("Option B") + `</text></item></parameter>`, true
return wrapParameter("question", promptCDATA("Which approach do you prefer?")) + "\n" + `<|DSML|parameter name="follow_up"><item><text>` + promptCDATA("Option A") + `</text></item><item><text>` + promptCDATA("Option B") + `</text></item></|DSML|parameter>`, true
}
return "", false
}

View File

@@ -7,20 +7,20 @@ import (
func TestBuildToolCallInstructions_ExecCommandUsesCmdExample(t *testing.T) {
out := BuildToolCallInstructions([]string{"exec_command"})
if !strings.Contains(out, `<invoke name="exec_command">`) {
if !strings.Contains(out, `<|DSML|invoke name="exec_command">`) {
t.Fatalf("expected exec_command in examples, got: %s", out)
}
if !strings.Contains(out, `<parameter name="cmd"><![CDATA[pwd]]></parameter>`) {
if !strings.Contains(out, `<|DSML|parameter name="cmd"><![CDATA[pwd]]></|DSML|parameter>`) {
t.Fatalf("expected cmd parameter example for exec_command, got: %s", out)
}
}
func TestBuildToolCallInstructions_ExecuteCommandUsesCommandExample(t *testing.T) {
out := BuildToolCallInstructions([]string{"execute_command"})
if !strings.Contains(out, `<invoke name="execute_command">`) {
if !strings.Contains(out, `<|DSML|invoke name="execute_command">`) {
t.Fatalf("expected execute_command in examples, got: %s", out)
}
if !strings.Contains(out, `<parameter name="command"><![CDATA[pwd]]></parameter>`) {
if !strings.Contains(out, `<|DSML|parameter name="command"><![CDATA[pwd]]></|DSML|parameter>`) {
t.Fatalf("expected command parameter example for execute_command, got: %s", out)
}
}
@@ -34,20 +34,20 @@ func TestBuildToolCallInstructions_BashUsesCommandAndDescriptionExamples(t *test
sawDescription := false
for _, block := range blocks {
if !strings.Contains(block, `<parameter name="command">`) {
if !strings.Contains(block, `<|DSML|parameter name="command">`) {
t.Fatalf("expected every Bash example to use command parameter, got: %s", block)
}
if strings.Contains(block, `<parameter name="path">`) || strings.Contains(block, `<parameter name="content">`) {
if strings.Contains(block, `<|DSML|parameter name="path">`) || strings.Contains(block, `<|DSML|parameter name="content">`) {
t.Fatalf("expected Bash examples not to use file write parameters, got: %s", block)
}
if strings.Contains(block, `<parameter name="description">`) {
if strings.Contains(block, `<|DSML|parameter name="description">`) {
sawDescription = true
}
}
if !sawDescription {
t.Fatalf("expected Bash long-script example to include description, got: %s", out)
}
if strings.Contains(out, `<invoke name="Read">`) {
if strings.Contains(out, `<|DSML|invoke name="Read">`) {
t.Fatalf("expected examples to avoid unavailable hard-coded Read tool, got: %s", out)
}
}
@@ -60,10 +60,10 @@ func TestBuildToolCallInstructions_ExecuteCommandLongScriptUsesCommand(t *testin
}
for _, block := range blocks {
if !strings.Contains(block, `<parameter name="command">`) {
if !strings.Contains(block, `<|DSML|parameter name="command">`) {
t.Fatalf("expected execute_command examples to use command parameter, got: %s", block)
}
if strings.Contains(block, `<parameter name="path">`) || strings.Contains(block, `<parameter name="content">`) {
if strings.Contains(block, `<|DSML|parameter name="path">`) || strings.Contains(block, `<|DSML|parameter name="content">`) {
t.Fatalf("expected execute_command examples not to use file write parameters, got: %s", block)
}
}
@@ -80,10 +80,10 @@ func TestBuildToolCallInstructions_ExecCommandLongScriptUsesCmd(t *testing.T) {
}
for _, block := range blocks {
if !strings.Contains(block, `<parameter name="cmd">`) {
if !strings.Contains(block, `<|DSML|parameter name="cmd">`) {
t.Fatalf("expected exec_command examples to use cmd parameter, got: %s", block)
}
if strings.Contains(block, `<parameter name="command">`) || strings.Contains(block, `<parameter name="path">`) || strings.Contains(block, `<parameter name="content">`) {
if strings.Contains(block, `<|DSML|parameter name="command">`) || strings.Contains(block, `<|DSML|parameter name="path">`) || strings.Contains(block, `<|DSML|parameter name="content">`) {
t.Fatalf("expected exec_command examples not to use command or file write parameters, got: %s", block)
}
}
@@ -100,10 +100,10 @@ func TestBuildToolCallInstructions_WriteUsesFilePathAndContent(t *testing.T) {
}
for _, block := range blocks {
if !strings.Contains(block, `<parameter name="file_path">`) || !strings.Contains(block, `<parameter name="content">`) {
if !strings.Contains(block, `<|DSML|parameter name="file_path">`) || !strings.Contains(block, `<|DSML|parameter name="content">`) {
t.Fatalf("expected Write examples to use file_path and content, got: %s", block)
}
if strings.Contains(block, `<parameter name="path">`) {
if strings.Contains(block, `<|DSML|parameter name="path">`) {
t.Fatalf("expected Write examples not to use path, got: %s", block)
}
}
@@ -111,7 +111,7 @@ func TestBuildToolCallInstructions_WriteUsesFilePathAndContent(t *testing.T) {
func TestBuildToolCallInstructions_AnchorsMissingOpeningWrapperFailureMode(t *testing.T) {
out := BuildToolCallInstructions([]string{"read_file"})
if !strings.Contains(out, "Never omit the opening <tool_calls> tag") {
if !strings.Contains(out, "Never omit the opening <|DSML|tool_calls> tag") {
t.Fatalf("expected explicit missing-opening-tag warning, got: %s", out)
}
if !strings.Contains(out, "Wrong 3 — missing opening wrapper") {
@@ -120,7 +120,7 @@ func TestBuildToolCallInstructions_AnchorsMissingOpeningWrapperFailureMode(t *te
}
func findInvokeBlocks(text, name string) []string {
open := `<invoke name="` + name + `">`
open := `<|DSML|invoke name="` + name + `">`
remaining := text
blocks := []string{}
for {
@@ -129,11 +129,11 @@ func findInvokeBlocks(text, name string) []string {
return blocks
}
remaining = remaining[start:]
end := strings.Index(remaining, `</invoke>`)
end := strings.Index(remaining, `</|DSML|invoke>`)
if end < 0 {
return blocks
}
end += len(`</invoke>`)
end += len(`</|DSML|invoke>`)
blocks = append(blocks, remaining[:end])
remaining = remaining[end:]
}

View File

@@ -0,0 +1,108 @@
package toolcall
import "strings"
func normalizeDSMLToolCallMarkup(text string) (string, bool) {
if text == "" {
return "", true
}
hasDSML, hasCanonical := toolMarkupStylesOutsideIgnored(text)
if hasDSML && hasCanonical {
return text, false
}
if !hasDSML {
return text, true
}
return replaceDSMLToolMarkupOutsideIgnored(text), true
}
var dsmlToolMarkupAliases = []struct {
from string
to string
}{
{"<|dsml|tool_calls", "<tool_calls"},
{"</|dsml|tool_calls>", "</tool_calls>"},
{"<|dsml|invoke", "<invoke"},
{"</|dsml|invoke>", "</invoke>"},
{"<|dsml|parameter", "<parameter"},
{"</|dsml|parameter>", "</parameter>"},
}
var canonicalToolMarkupPrefixes = []string{
"<tool_calls",
"</tool_calls>",
"<invoke",
"</invoke>",
"<parameter",
"</parameter>",
}
func toolMarkupStylesOutsideIgnored(text string) (hasDSML, hasCanonical bool) {
lower := strings.ToLower(text)
for i := 0; i < len(text); {
next, advanced, blocked := skipXMLIgnoredSection(lower, i)
if blocked {
return hasDSML, hasCanonical
}
if advanced {
i = next
continue
}
if hasPrefixAt(lower, i, canonicalToolMarkupPrefixes) {
hasCanonical = true
}
for _, alias := range dsmlToolMarkupAliases {
if strings.HasPrefix(lower[i:], alias.from) {
hasDSML = true
break
}
}
if hasDSML && hasCanonical {
return true, true
}
i++
}
return hasDSML, hasCanonical
}
func replaceDSMLToolMarkupOutsideIgnored(text string) string {
lower := strings.ToLower(text)
var b strings.Builder
b.Grow(len(text))
for i := 0; i < len(text); {
next, advanced, blocked := skipXMLIgnoredSection(lower, i)
if blocked {
b.WriteString(text[i:])
break
}
if advanced {
b.WriteString(text[i:next])
i = next
continue
}
replaced := false
for _, alias := range dsmlToolMarkupAliases {
if strings.HasPrefix(lower[i:], alias.from) {
b.WriteString(alias.to)
i += len(alias.from)
replaced = true
break
}
}
if replaced {
continue
}
b.WriteByte(text[i])
i++
}
return b.String()
}
func hasPrefixAt(text string, idx int, prefixes []string) bool {
for _, prefix := range prefixes {
if strings.HasPrefix(text[idx:], prefix) {
return true
}
}
return false
}

View File

@@ -60,7 +60,11 @@ func parseToolCallsDetailedXMLOnly(text string) ToolCallParseResult {
return result
}
parsed := parseXMLToolCalls(trimmed)
normalized, ok := normalizeDSMLToolCallMarkup(trimmed)
if !ok {
return result
}
parsed := parseXMLToolCalls(normalized)
if len(parsed) == 0 {
return result
}

View File

@@ -30,6 +30,37 @@ func TestParseToolCallsSupportsToolCallsWrapper(t *testing.T) {
}
}
func TestParseToolCallsSupportsDSMLShell(t *testing.T) {
text := `<|DSML|tool_calls><|DSML|invoke name="Bash"><|DSML|parameter name="command"><![CDATA[pwd]]></|DSML|parameter></|DSML|invoke></|DSML|tool_calls>`
calls := ParseToolCalls(text, []string{"Bash"})
if len(calls) != 1 {
t.Fatalf("expected 1 DSML call, got %#v", calls)
}
if calls[0].Name != "Bash" || calls[0].Input["command"] != "pwd" {
t.Fatalf("unexpected DSML parse result: %#v", calls[0])
}
}
func TestParseToolCallsSupportsDSMLShellWithCanonicalExampleInCDATA(t *testing.T) {
content := `<tool_calls><invoke name="demo"><parameter name="value">x</parameter></invoke></tool_calls>`
text := `<|DSML|tool_calls><|DSML|invoke name="Write"><|DSML|parameter name="file_path">notes.md</|DSML|parameter><|DSML|parameter name="content"><![CDATA[` + content + `]]></|DSML|parameter></|DSML|invoke></|DSML|tool_calls>`
calls := ParseToolCalls(text, []string{"Write"})
if len(calls) != 1 {
t.Fatalf("expected 1 DSML call with XML-looking CDATA, got %#v", calls)
}
if calls[0].Name != "Write" || calls[0].Input["content"] != content {
t.Fatalf("unexpected DSML CDATA parse result: %#v", calls[0])
}
}
func TestParseToolCallsRejectsMixedDSMLAndCanonicalToolTags(t *testing.T) {
text := `<|DSML|tool_calls><invoke name="Bash"><|DSML|parameter name="command">pwd</|DSML|parameter></invoke></|DSML|tool_calls>`
calls := ParseToolCalls(text, []string{"Bash"})
if len(calls) != 0 {
t.Fatalf("expected mixed DSML/XML tool tags to be rejected, got %#v", calls)
}
}
func TestParseToolCallsSupportsStandaloneToolWithMultilineCDATAAndRepeatedXMLTags(t *testing.T) {
text := `<tool_calls><invoke name="write_file"><parameter name="path">script.sh</parameter><parameter name="content"><![CDATA[#!/bin/bash
echo "hello"