refactor: remove resume (CV) workflow DSL template and Go handling code (#18177)

internal/agent/dsl/testdata/resume.json

@@ -1,461 +0,0 @@
-{
-  "globals": {
-    "sys.conversation_turns": 0,
-    "sys.date": "",
-    "sys.files": [],
-    "sys.history": [],
-    "sys.query": "",
-    "sys.user_id": ""
-  },
-  "graph": {
-    "edges": [
-      {
-        "data": {
-          "isHovered": false
-        },
-        "id": "xy-edge__Filestart-Parser:HipSignsRhymeend",
-        "source": "File",
-        "sourceHandle": "start",
-        "target": "Parser:HipSignsRhyme",
-        "targetHandle": "end"
-      },
-      {
-        "data": {
-          "isHovered": false
-        },
-        "id": "xy-edge__Parser:HipSignsRhymestart-TitleChunker:FlatMiceFixend",
-        "source": "Parser:HipSignsRhyme",
-        "sourceHandle": "start",
-        "target": "TitleChunker:FlatMiceFix",
-        "targetHandle": "end"
-      },
-      {
-        "data": {
-          "isHovered": false
-        },
-        "id": "xy-edge__TitleChunker:FlatMiceFixstart-Extractor:ThreeDrinksActend",
-        "markerEnd": "logo",
-        "source": "TitleChunker:FlatMiceFix",
-        "sourceHandle": "start",
-        "target": "Extractor:ThreeDrinksAct",
-        "targetHandle": "end",
-        "type": "buttonEdge",
-        "zIndex": 1001
-      },
-      {
-        "data": {
-          "isHovered": false
-        },
-        "id": "xy-edge__Extractor:ThreeDrinksActstart-Extractor:ItchyFoxesStriveend",
-        "source": "Extractor:ThreeDrinksAct",
-        "sourceHandle": "start",
-        "target": "Extractor:ItchyFoxesStrive",
-        "targetHandle": "end"
-      },
-      {
-        "data": {
-          "isHovered": false
-        },
-        "id": "xy-edge__Extractor:ItchyFoxesStrivestart-Extractor:BusyClocksRushend",
-        "source": "Extractor:ItchyFoxesStrive",
-        "sourceHandle": "start",
-        "target": "Extractor:BusyClocksRush",
-        "targetHandle": "end"
-      },
-      {
-        "data": {
-          "isHovered": false
-        },
-        "id": "xy-edge__Extractor:BusyClocksRushstart-Extractor:CuteSignsCutend",
-        "source": "Extractor:BusyClocksRush",
-        "sourceHandle": "start",
-        "target": "Extractor:CuteSignsCut",
-        "targetHandle": "end"
-      },
-      {
-        "data": {
-          "isHovered": false
-        },
-        "id": "xy-edge__Extractor:CuteSignsCutstart-Tokenizer:KindHandsWinend",
-        "markerEnd": "logo",
-        "source": "Extractor:CuteSignsCut",
-        "sourceHandle": "start",
-        "target": "Tokenizer:KindHandsWin",
-        "targetHandle": "end",
-        "type": "buttonEdge",
-        "zIndex": 1001
-      }
-    ],
-    "nodes": [
-      {
-        "data": {
-          "label": "File",
-          "name": "File"
-        },
-        "dragging": false,
-        "id": "File",
-        "measured": {
-          "height": 49,
-          "width": 200
-        },
-        "position": {
-          "x": 239.52494800353588,
-          "y": 92.44515504032671
-        },
-        "selected": false,
-        "sourcePosition": "left",
-        "targetPosition": "right",
-        "type": "beginNode"
-      },
-      {
-        "data": {
-          "form": {
-            "outputs": {
-              "html": {
-                "type": "string",
-                "value": ""
-              },
-              "json": {
-                "type": "Array<object>",
-                "value": []
-              },
-              "markdown": {
-                "type": "string",
-                "value": ""
-              },
-              "text": {
-                "type": "string",
-                "value": ""
-              }
-            },
-            "setups": [
-              {
-                "fileFormat": "pdf",
-                "flatten_media_to_text": true,
-                "output_format": "json",
-                "parse_method": "DeepDOC"
-              },
-              {
-                "fileFormat": "spreadsheet",
-                "flatten_media_to_text": true,
-                "output_format": "html",
-                "parse_method": "DeepDOC"
-              },
-              {
-                "fileFormat": "image",
-                "output_format": "text",
-                "parse_method": "ocr"
-              },
-              {
-                "fields": [
-                  "from",
-                  "to",
-                  "cc",
-                  "bcc",
-                  "date",
-                  "subject",
-                  "body",
-                  "attachments"
-                ],
-                "fileFormat": "email",
-                "output_format": "text"
-              },
-              {
-                "fileFormat": "markdown",
-                "flatten_media_to_text": true,
-                "output_format": "json"
-              },
-              {
-                "fileFormat": "text&code",
-                "output_format": "json"
-              },
-              {
-                "fileFormat": "html",
-                "output_format": "json"
-              },
-              {
-                "fileFormat": "doc",
-                "output_format": "json",
-                "vlm": {}
-              },
-              {
-                "fileFormat": "docx",
-                "flatten_media_to_text": true,
-                "output_format": "json"
-              },
-              {
-                "fileFormat": "slides",
-                "output_format": "json",
-                "parse_method": "DeepDOC"
-              }
-            ]
-          },
-          "label": "Parser",
-          "name": "Parser_0"
-        },
-        "dragging": false,
-        "id": "Parser:HipSignsRhyme",
-        "measured": {
-          "height": 197,
-          "width": 200
-        },
-        "position": {
-          "x": 252.18327231534056,
-          "y": 157.25954787377458
-        },
-        "selected": true,
-        "sourcePosition": "right",
-        "targetPosition": "left",
-        "type": "parserNode"
-      },
-      {
-        "data": {
-          "form": {
-            "fields": "text",
-            "filename_embd_weight": 0.1,
-            "outputs": {},
-            "search_method": [
-              "embedding",
-              "full_text"
-            ]
-          },
-          "label": "Tokenizer",
-          "name": "Indexer_0"
-        },
-        "dragging": false,
-        "id": "Tokenizer:KindHandsWin",
-        "measured": {
-          "height": 113,
-          "width": 200
-        },
-        "position": {
-          "x": 663.5327731044026,
-          "y": 544.5236681687471
-        },
-        "selected": false,
-        "sourcePosition": "right",
-        "targetPosition": "left",
-        "type": "tokenizerNode"
-      },
-      {
-        "data": {
-          "form": {
-            "hierarchy": "1",
-            "include_heading_content": false,
-            "method": "hierarchy",
-            "outputs": {
-              "chunks": {
-                "type": "Array<Object>",
-                "value": []
-              }
-            },
-            "promote_first_heading_to_root": false,
-            "root_chunk_as_heading": true,
-            "rules": [
-              {
-                "levels": [
-                  {
-                    "expression": "^\\s*(?i:(?:\\d+[\\.\\)]\\s*)?(?:EDUCATION|ACADEMIC\\s*BACKGROUND|ACADEMIC\\s*HISTORY|EDUCATIONAL\\s*BACKGROUND|RELEVANT\\s*COURSEWORK|COURSEWORK|EXPERIENCE|WORK\\s*EXPERIENCE|PROFESSIONAL\\s*EXPERIENCE|RELEVANT\\s*EXPERIENCE|EMPLOYMENT\\s*HISTORY|CAREER\\s*HISTORY|INTERNSHIP\\s*EXPERIENCE|PROJECTS|PROJECT\\s*EXPERIENCE|ACADEMIC\\s*PROJECTS|PROFESSIONAL\\s*PROJECTS|SKILLS|TECHNICAL\\s*SKILLS|CORE\\s*COMPETENCIES|COMPETENCIES|QUALIFICATIONS|SUMMARY\\s*OF\\s*QUALIFICATIONS|CERTIFICATIONS|LICENSES|CERTIFICATES|AWARDS|HONORS|HONOURS|ACHIEVEMENTS|PUBLICATIONS|RESEARCH|RESEARCH\\s*EXPERIENCE|LEADERSHIP|LEADERSHIP\\s*EXPERIENCE|ACTIVITIES|EXTRACURRICULAR\\s*ACTIVITIES|ACTIVITIES\\s*(?:&|AND)\\s*SKILLS|INVOLVEMENT|CAMPUS\\s*INVOLVEMENT|VOLUNTEER\\s*EXPERIENCE|VOLUNTEERING|COMMUNITY\\s*SERVICE|LANGUAGES|INTERESTS|HOBBIES|PROFILE|PROFESSIONAL\\s*PROFILE|SUMMARY|PROFESSIONAL\\s*SUMMARY|CAREER\\s*SUMMARY|OBJECTIVE|CAREER\\s*OBJECTIVE|PERSONAL\\s*INFORMATION|CONTACT\\s*INFORMATION|ADDITIONAL\\s*INFORMATION|TRAINING))\\s*[:：]?\\s*$"
-                  }
-                ]
-              },
-              {
-                "levels": [
-                  {
-                    "expression": "^\\s*(?:\\d+[\\.、\\)]\\s*)?(?:教育背景|教育经历|学历背景|学术背景|技术背景|工作经历|工作经验|实习经历|项目经历|项目经验|科研经历|研究经历|校园经历|实践经历|专业经历|职业经历|技能|专业技能|技能特长|核心技能|技术栈|个人技能|工作技能|职业技能|技能与评价|技能与自我评价|工作技能与自我评价|职业技能与自我评价|证书|资格证书|职业资格|资质证书|获奖情况|获奖经历|荣誉|荣誉奖项|奖项|科研成果|论文发表|发表论文|领导经历|学生工作|校园活动|社团经历|活动经历|志愿经历|志愿服务|社会实践|语言能力|语言|自我评价|个人评价|自我总结|个人总结|个人优势|个人简介|个人信息|基本信息|联系方式|求职意向|应聘意向|职业目标|求职目标|兴趣爱好|兴趣特长|培训经历|其他信息|附加信息)\\s*[:：]?\\s*$"
-                  }
-                ]
-              }
-            ]
-          },
-          "label": "TitleChunker",
-          "name": "Title Chunker_0"
-        },
-        "dragging": false,
-        "id": "TitleChunker:FlatMiceFix",
-        "measured": {
-          "height": 73,
-          "width": 200
-        },
-        "position": {
-          "x": 524.2908769627791,
-          "y": 53.05515313482098
-        },
-        "selected": false,
-        "sourcePosition": "right",
-        "targetPosition": "left",
-        "type": "chunkerNode"
-      },
-      {
-        "data": {
-          "form": {
-            "field_name": "metadata",
-            "frequencyPenaltyEnabled": true,
-            "frequency_penalty": 0.7,
-            "llm_id": "MiniMax-M2.7@MiniMax",
-            "maxTokensEnabled": false,
-            "max_tokens": 256,
-            "outputs": {
-              "chunks": {
-                "type": "Array<Object>",
-                "value": []
-              }
-            },
-            "presencePenaltyEnabled": true,
-            "presence_penalty": 0.4,
-            "prompts": "Content: {TitleChunker:FlatMiceFix@chunks}",
-            "sys_prompt": "Act as a precise resume metadata extractor. Extract stable, chunk-supported metadata from the provided resume content.\n\nRules:\n1. Use only information explicitly stated in the content. Do not infer, guess, normalize, or add missing facts.\n2. The input may be only one chunk of a resume. Extract only what this content directly supports.\n3. Use only these field names:\ncandidate_name, gender, phone, email, city, location, nationality, linkedin, github, website, highest_degree, degree_levels, school_names, majors, graduation_years, work_experience_years, current_job_title, job_titles, company_names, job_experience, industries, target_job_titles, target_locations, employment_types, skills, certificates, awards, summary_tags\n4. Ignore detailed responsibilities, project descriptions, achievement narratives, self-evaluation, and other low-value local details.\n5. Keep values in the same language as the source text whenever possible.\n6. Remove duplicates and keep only concise, high-value metadata.\n7. Return only fields that are explicitly supported by the content. Do not return empty or unsupported fields.\n\nField guidance:\n- highest_degree: highest explicit degree level mentioned\n- degree_levels: all explicit degree levels mentioned\n- school_names: explicit school, college, or university names\n- majors: explicit fields of study\n- graduation_years: explicit graduation years only\n- work_experience_years: only if explicitly stated\n- current_job_title: only if explicitly current or most recent\n- job_titles: explicit role titles\n- company_names: explicit employer names\n- job_experience: concise structured work entries explicitly supported by the content, preferably including title, company, and time information when available\n- industries: explicit industry names only\n- target_job_titles: explicit desired roles only\n- target_locations: explicit desired work locations only\n- skills: concise, core, search-useful skills explicitly mentioned\n- certificates: explicit certificate names only\n- awards: explicit award names only\n- summary_tags: short, high-value tags strictly supported by the content\n\nReturn only the extracted metadata. Do not output explanatory text.",
-            "temperature": 0.1,
-            "temperatureEnabled": true,
-            "tenant_llm_id": 29,
-            "topPEnabled": true,
-            "top_p": 0.3
-          },
-          "label": "Extractor",
-          "name": "Auto Metadata"
-        },
-        "dragging": false,
-        "id": "Extractor:ThreeDrinksAct",
-        "measured": {
-          "height": 89,
-          "width": 200
-        },
-        "position": {
-          "x": 550.8123774842874,
-          "y": 161.4998493859579
-        },
-        "selected": false,
-        "sourcePosition": "right",
-        "targetPosition": "left",
-        "type": "contextNode"
-      },
-      {
-        "data": {
-          "form": {
-            "field_name": "keywords",
-            "frequencyPenaltyEnabled": true,
-            "frequency_penalty": 0.7,
-            "llm_id": "MiniMax-M2.7@MiniMax",
-            "maxTokensEnabled": false,
-            "max_tokens": 256,
-            "outputs": {
-              "chunks": {
-                "type": "Array<Object>",
-                "value": []
-              }
-            },
-            "presencePenaltyEnabled": true,
-            "presence_penalty": 0.4,
-            "prompts": "文本内容\n[在此处插入文本]",
-            "sys_prompt": "角色\n你是一名文本分析员。\n\n任务\n从给定的文本内容中提取最重要的关键词/短语。\n\n要求\n- 总结文本内容，并给出最重要的5个关键词/短语。\n- 关键词必须与给定的文本内容使用相同的语言。\n- 关键词之间用英文逗号分隔。\n- 仅输出关键词。",
-            "temperature": 0.1,
-            "temperatureEnabled": true,
-            "topPEnabled": true,
-            "top_p": 0.3
-          },
-          "label": "Extractor",
-          "name": "提取器_0"
-        },
-        "dragging": false,
-        "id": "Extractor:ItchyFoxesStrive",
-        "measured": {
-          "height": 89,
-          "width": 200
-        },
-        "position": {
-          "x": 558.7638130889704,
-          "y": 260.698149098317
-        },
-        "selected": false,
-        "sourcePosition": "right",
-        "targetPosition": "left",
-        "type": "contextNode"
-      },
-      {
-        "data": {
-          "form": {
-            "field_name": "questions",
-            "frequencyPenaltyEnabled": true,
-            "frequency_penalty": 0.7,
-            "llm_id": "MiniMax-M2.7@MiniMax",
-            "maxTokensEnabled": false,
-            "max_tokens": 256,
-            "outputs": {
-              "chunks": {
-                "type": "Array<Object>",
-                "value": []
-              }
-            },
-            "presencePenaltyEnabled": true,
-            "presence_penalty": 0.4,
-            "prompts": "文本内容\n[在此处插入文本]",
-            "sys_prompt": "角色\n你是一名文本分析员。\n\n任务\n针对给定的文本内容提出3个问题。\n\n要求\n- 理解并总结文本内容，并提出最重要的3个问题。\n- 问题的含义不应重叠。\n- 问题应尽可能涵盖文本的主要内容。\n- 问题必须与给定的文本内容使用相同的语言。\n- 每行一个问题。\n- 仅输出问题。",
-            "temperature": 0.1,
-            "temperatureEnabled": true,
-            "topPEnabled": true,
-            "top_p": 0.3
-          },
-          "label": "Extractor",
-          "name": "提取器_1"
-        },
-        "dragging": false,
-        "id": "Extractor:BusyClocksRush",
-        "measured": {
-          "height": 89,
-          "width": 200
-        },
-        "position": {
-          "x": 592.4119346324834,
-          "y": 353.6113302354397
-        },
-        "selected": false,
-        "sourcePosition": "right",
-        "targetPosition": "left",
-        "type": "contextNode"
-      },
-      {
-        "data": {
-          "form": {
-            "field_name": "summary",
-            "frequencyPenaltyEnabled": true,
-            "frequency_penalty": 0.7,
-            "llm_id": "MiniMax-M2.7@MiniMax",
-            "maxTokensEnabled": false,
-            "max_tokens": 256,
-            "outputs": {
-              "chunks": {
-                "type": "Array<Object>",
-                "value": []
-              }
-            },
-            "presencePenaltyEnabled": true,
-            "presence_penalty": 0.4,
-            "prompts": "要总结的文本：\n[在此处插入文本]",
-            "sys_prompt": "扮演一个精准的摘要者。你的任务是为提供的内容创建一个简洁且忠实于原文的摘要。\n\n关键说明：\n1. 准确性：摘要必须严格基于所提供的信息。请勿引入任何未明确说明的新事实、结论或解释。\n2. 语言：摘要必须使用与原文相同的语言。\n3. 客观性：不带偏见地呈现要点，保留内容的原始意图和语气。请勿进行编辑。\n4. 简洁性：专注于最重要的思想，省略细节和多余的内容。",
-            "temperature": 0.1,
-            "temperatureEnabled": true,
-            "topPEnabled": true,
-            "top_p": 0.3
-          },
-          "label": "Extractor",
-          "name": "提取器_2"
-        },
-        "dragging": false,
-        "id": "Extractor:CuteSignsCut",
-        "measured": {
-          "height": 89,
-          "width": 200
-        },
-        "position": {
-          "x": 616.822830981782,
-          "y": 449.2756537664745
-        },
-        "selected": false,
-        "sourcePosition": "right",
-        "targetPosition": "left",
-        "type": "contextNode"
-      }
-    ]
-  },
-  "variables": []
-}

internal/ingestion/component/extractor.go

@@ -1540,8 +1540,7 @@ func fitExtractorMessages(ctx context.Context, db *gorm.DB, llmID string, msgs [
 // when chunks is non-empty. The python rag/flow/extractor/extractor.py
 // build_existing_prompt path performs the same substitution at
 // runtime; the Go port surfaces it as a regex on the prompt
-// template so the resume template's `{TitleChunker:FlatMiceFix@chunks}`
-// reference resolves without invoking a template engine.
+// template so the reference resolves without invoking a template engine.
 //
 // Substitution is opt-in: when chunks is nil/empty the placeholder
 // is left intact so a misconfigured template surfaces as a
@@ -1582,9 +1581,7 @@ func buildExtractorMessages(system, prompt, chunkText string, chunks []map[strin
 //	{CmpName:ParamName@chunks}
 //
 // The CmpName and ParamName are both matched but ignored — the
-// substitute is always "the joined chunk text" today, because the
-// only @chunks reference in production templates is the resume
-// template's `{TitleChunker:FlatMiceFix@chunks}` pattern. The
+// substitute is always "the joined chunk text" today. The
 // CmpName/ParamName parsing exists so a future per-component
 // substitution can extend the function without breaking the
 // existing call sites.

internal/ingestion/component/extractor_test.go

@@ -1722,51 +1722,6 @@ func TestExtractorComponent_Invoke_AppendsChunkTextWhenNoPlaceholder(t *testing.
 	}
 }
 
-// TestExtractorComponent_Invoke_ResumeTemplateChunksPath verifies the resume
-// template path: a prompt referencing {@chunks} (e.g. {TitleChunker:FlatMiceFix@chunks})
-// must still deliver the chunk body to the LLM. {@chunks} is resolved by
-// substitutePromptPlaceholders in buildExtractorMessages, NOT by the simple
-// placeholder loop — so contentPlaceholders does not see it, suppression must
-// not trigger, and the chunk text arrives via the automatic append. Regression
-// guard: if someone adds {@chunks} to contentPlaceholders or the suppression
-// logic starts matching regex-style placeholders, the resume path silently
-// breaks (chunk body vanishes from the LLM call).
-func TestExtractorComponent_Invoke_ResumeTemplateChunksPath(t *testing.T) {
-	stub := withStubChatInvoker(t,
-		stubResponse{Content: "answer"},
-	)
-
-	c := &ExtractorComponent{Param: schema.ExtractorParam{
-		FieldName: "out",
-		Prompt:    "Resume: {TitleChunker:FlatMiceFix@chunks}",
-		LLMID:     "gpt-4o-mini",
-	}}
-	_, err := c.Invoke(t.Context(), nil, map[string]any{
-		"chunks": []map[string]any{{"text": "resume chunk body"}},
-	})
-	if err != nil {
-		t.Fatalf("Invoke: %v", err)
-	}
-
-	stub.mu.Lock()
-	defer stub.mu.Unlock()
-	var userContent string
-	for _, msg := range stub.lastReq.Messages {
-		if msg.Role == eschema.User {
-			userContent = msg.Content
-		}
-	}
-	// {@chunks} must be resolved by substitutePromptPlaceholders.
-	if strings.Contains(userContent, "{TitleChunker:FlatMiceFix@chunks}") {
-		t.Errorf("prompt still contains literal @chunks placeholder: %q", userContent)
-	}
-	// Chunk body must arrive in the final message (via the append path,
-	// since {@chunks} does not suppress the automatic chunk-text append).
-	if !strings.Contains(userContent, "resume chunk body") {
-		t.Errorf("chunk body missing from LLM call — resume path broken: %q", userContent)
-	}
-}
-
 // TestExtractorComponent_Invoke_SystemPromptPlaceholderSuppressesAppend
 // verifies that a content-bearing placeholder in systemPrompt (not just
 // prompt) also suppresses the automatic chunk-text append. The chunk body

internal/ingestion/component/slice3_test.go

@@ -26,7 +26,7 @@ import (
 )
 
 // TestSubstitutePromptPlaceholders_ReplacesAtChunks pins the
-// resume-template pattern `{TitleChunker:FlatMiceFix@chunks}`.
+// `{ComponentName:ParamName@chunks}` placeholder substitution.
 // The substitute is the joined chunk text.
 func TestSubstitutePromptPlaceholders_ReplacesAtChunks(t *testing.T) {
 	prompt := "Extract metadata from: {TitleChunker:FlatMiceFix@chunks}"