volcengine · MaojiaSheng · Mar 10, 2026 · Mar 10, 2026 · Mar 10, 2026 · Mar 10, 2026
diff --git a/.gitignore b/.gitignore
@@ -162,3 +162,4 @@ test_scripts/
 examples/data/
 openviking/_version.py
 specs/
+.trae/
diff --git a/openviking/prompts/templates/compression/field_compress.yaml b/openviking/prompts/templates/compression/field_compress.yaml
@@ -0,0 +1,38 @@
+metadata:
+  id: "compression.field_compress"
+  name: "Field Content Compression"
+  description: "Compress field content while preserving key information"
+  version: "1.0.0"
+  language: "en"
+  category: "compression"
+
+variables:
+  - name: "field_name"
+    type: "string"
+    description: "Field name (e.g., best_for, optimal_params)"
+    required: true
+  - name: "content"
+    type: "string"
+    description: "Original content to compress"
+    required: true
+  - name: "max_length"
+    type: "integer"
+    description: "Maximum length in characters"
+    required: true
+
+template: |
+  Compress the following "{{ field_name }}" field content to fit within {{ max_length }} characters.
+
+  Original content:
+  {{ content }}
+
+  Requirements:
+  - Preserve the most important and unique information
+  - Remove redundancy and duplicates
+  - Use concise language
+  - Maintain semantic structure (keep items separated by semicolons if applicable)
+  - Output must be <= {{ max_length }} characters
+  - Return compressed content only, no explanation
+
+llm_config:
+  temperature: 0.0
diff --git a/openviking/prompts/templates/compression/memory_extraction.yaml b/openviking/prompts/templates/compression/memory_extraction.yaml
@@ -338,8 +338,12 @@ template: |
     "category": "tools",
     "tool_name": "web_search",
     "abstract": "web_search: Technical docs search optimal, needs specific query terms",
-    "overview": "## Tool Info\\n- **Name**: web_search\\n- **Type**: external_api\\n\\n## Statistics\\n- **Success Rate**: 92%\\n- **Avg Time**: 2.3s\\n\\n## Best Scenarios\\n- Technical documentation (95%)\\n- Tutorials (90%)\\n\\n## Optimal Parameters\\n- max_results: 5-20\\n- language: 'en'",
-    "content": "## Recommendations\\n\\n### Query Optimization\\n- Use specific multi-word queries\\n- Add qualifiers like 'tutorial', 'guide'\\n\\n## Good Cases\\n- 'Python asyncio tutorial' → 3 high-quality results\\n\\n## Bad Cases\\n- 'programming' → timeout (too broad)"
+    "best_for": "Technical documentation, tutorials, API references",
+    "optimal_params": "max_results: 5-20 (larger values may timeout); language: 'en' for better results; query: specific multi-word phrases with qualifiers",
+    "common_failures": "Single-word queries return irrelevant results; max_results>50 causes timeout; non-English queries have lower quality",
+    "recommendation": "Use specific multi-word queries like 'Python asyncio tutorial'; add qualifiers like 'guide', 'docs', 'example'",
+    "overview": "## Tool Info\\n- **Name**: web_search\\n- **Type**: external_api\\n\\n## Statistics\\n- **Success Rate**: 92%\\n- **Avg Time**: 2.3s\\n\\n## Tool Memory Context\\n- Best for: Technical documentation, tutorials, API references\\n- Optimal params: max_results: 5-20; language: 'en'; query: specific multi-word phrases\\n- Common failures: Single-word queries; max_results>50 timeout\\n- Recommendation: Use specific multi-word queries with qualifiers",
+    "content": "## Guidelines\\n\\n### Query Optimization\\n- Use specific multi-word queries (e.g., 'FastAPI dependency injection guide')\\n- Add qualifiers: 'tutorial', 'guide', 'docs', 'example'\\n- Prefer English for technical content\\n\\n### Good Cases\\n- Query: 'Python asyncio tutorial for beginners' → Found 3 high-quality beginner tutorials\\n- Query: 'FastAPI dependency injection docs' → Located official documentation accurately\\n\\n### Bad Cases\\n- Query: 'programming' → Timeout, results too broad\\n- Query: 'how to code' → Irrelevant results, no specific context"
   }
   ```
 
@@ -350,8 +354,13 @@ template: |
     "category": "skills",
     "skill_name": "create_presentation",
     "abstract": "create_presentation: Collect materials first for better efficiency",
-    "overview": "## Skill Info\\n- **Name**: create_presentation\\n- **Type**: workflow\\n\\n## Statistics\\n- **Success Rate**: 85%\\n- **Avg Time**: 120s\\n\\n## Recommended Flow\\n1. Collect materials\\n2. Generate outline\\n3. Create slides\\n4. Refine content\\n\\n## Key Dependencies\\n- Clear topic\\n- Target audience",
-    "content": "## Execution Strategy\\n\\n### Preparation\\n1. Confirm topic and audience\\n2. Collect reference materials\\n\\n## Good Cases\\n- Tech sharing: collected asyncio docs first → 90s, high quality\\n\\n## Bad Cases\\n- 'Make a PPT' without topic → multiple reworks needed"
+    "best_for": "Slide creation tasks with clear topic and target audience",
+    "recommended_flow": "1. Confirm topic and audience → 2. Collect reference materials → 3. Generate outline → 4. Create slides → 5. Refine content",
+    "key_dependencies": "Clear topic (e.g., 'Q3 project update', 'Python tutorial'); Target audience (e.g., 'executives', 'beginners'); Reference materials (optional but recommended)",
+    "common_failures": "Vague topic like 'make a PPT' leads to multiple rework cycles; Missing audience info causes style mismatch; No reference materials results in generic content",
+    "recommendation": "Always confirm topic and audience before starting; Collect 2-3 reference materials for better quality",
+    "overview": "## Skill Info\\n- **Name**: create_presentation\\n- **Type**: workflow\\n\\n## Statistics\\n- **Success Rate**: 85%\\n\\n## Skill Memory Context\\n- Best for: Slide creation with clear topic and audience\\n- Recommended flow: Confirm → Collect → Outline → Create → Refine\\n- Key dependencies: Clear topic; target audience; reference materials\\n- Common failures: Vague topic; missing audience; no references\\n- Recommendation: Confirm topic/audience first; collect reference materials",
+    "content": "## Guidelines\\n\\n### Preparation\\n1. Confirm topic (e.g., 'Q3 Sales Report', 'Python Basics Tutorial')\\n2. Identify audience (e.g., executives, beginners, engineers)\\n3. Collect 2-3 reference materials or examples\\n\\n### Good Cases\\n- Topic: 'Python asyncio tutorial for beginners' + Audience: 'developers new to async' → Collected official docs first, generated 10 slides with code examples, completed in 90s\\n- Topic: 'Q3 project update' + Audience: 'stakeholders' → Gathered metrics first, created data-driven slides, positive feedback\\n\\n### Bad Cases\\n- Request: 'Make a PPT' (no topic specified) → Generated generic content, required 3 rounds of rework\\n- Request: 'Create presentation' (no audience) → Style mismatch, had to regenerate for different audience"
   }
   ```
 
@@ -365,8 +374,14 @@ template: |
         "abstract": "Merge types use `[Merge key]: [Description]`, independent types use specific description",
         "overview": "Structured Markdown, use different heading templates by category",
         "content": "Free Markdown, complete narrative",
-        "tool_name": "Only for tools category: the tool name from input [ToolCall] record (must copy exactly)",
-        "skill_name": "Only for skills category: inferred from full conversation context (descriptive name for the skill/workflow)"
+        "tool_name": "[REQUIRED for tools] The tool name from [ToolCall] record - MUST copy exactly, no modification",
+        "skill_name": "[REQUIRED for skills] The skill name - copy from [ToolCall] skill_name if present, otherwise infer from context",
+        "best_for": "Optional: tools/skills only, what this tool/skill is best used for",
+        "optimal_params": "Optional: tools only, GENERAL parameter ranges/best practices (NOT specific case values)",
+        "recommended_flow": "Optional: skills only, recommended execution flow",
+        "key_dependencies": "Optional: skills only, prerequisites/inputs needed",
+        "common_failures": "Optional: tools/skills only, common failure patterns",
+        "recommendation": "Optional: tools/skills only, short actionable recommendations"
       }
     ]
   }
@@ -376,8 +391,11 @@ template: |
   - Only extract truly valuable personalized information
   - If nothing worth recording, return {"memories": []}
   - For preferences, keep each memory as one independently updatable facet; do not combine unrelated facets in one memory
-  - For tools category: tool_name MUST be copied from [ToolCall] tool_name field exactly, do NOT modify it
-  - For skills category: skill_name should be inferred from the full conversation context (skill may involve internal tools not shown in [ToolCall]). Use a descriptive name that represents the skill/workflow.
+  - **CRITICAL for tools category**: "tool_name" is REQUIRED. You MUST copy the exact tool_name value from the [ToolCall] record. Do NOT omit this field. Do NOT modify the name.
+  - **CRITICAL for skills category**: "skill_name" is REQUIRED. If [ToolCall] contains skill_name, copy it exactly. If not present, infer a descriptive name from context. Do NOT omit this field.
+  - **CRITICAL for tools/skills content field**: The "content" field MUST include structured sections with EXACT English headings: `## Guidelines` (with best practices), `### Good Cases` (successful usage examples), and `### Bad Cases` (failed usage examples). The section content can be in {{ output_language }}, but the headings MUST remain in English.
+  - For tools/skills category: Fill "best_for/recommended_flow/key_dependencies/common_failures/recommendation" based on observed usage patterns. Infer reasonable values from the tool/skill nature when direct evidence is limited.
+  - For tools category: "optimal_params" should describe GENERAL best practices (e.g., "max_results=5-20", "timeout>30s for large files"), NOT specific case values (e.g., "command: 'echo hello'", "file: '/path/to/specific/file'").
 
 llm_config:
   temperature: 0.0
diff --git a/openviking/session/compressor.py b/openviking/session/compressor.py
@@ -156,6 +156,10 @@ async def extract_long_term_memories(
         viking_fs = get_viking_fs()
 
         tool_parts = self._extract_tool_parts(messages)
+        from .tool_skill_utils import collect_skill_stats, collect_tool_stats
+
+        tool_stats_map = collect_tool_stats(tool_parts)
+        skill_stats_map = collect_skill_stats(tool_parts)
 
         for candidate in candidates:
             # Profile: skip dedup, always merge
@@ -176,6 +180,31 @@ async def extract_long_term_memories(
                         candidate, tool_parts
                     )
                     candidate.tool_status = tool_status
+                    if tool_name:
+                        candidate.tool_name = tool_name
+                    if skill_name:
+                        candidate.skill_name = skill_name
+
+                    if tool_name and candidate.call_time == 0:
+                        tool_stats = tool_stats_map.get(tool_name, {})
+                        candidate.call_time = tool_stats.get("call_count", candidate.call_time)
+                        candidate.success_time = tool_stats.get(
+                            "success_time", candidate.success_time
+                        )
+                        candidate.duration_ms = tool_stats.get("duration_ms", candidate.duration_ms)
+                        candidate.prompt_tokens = tool_stats.get(
+                            "prompt_tokens", candidate.prompt_tokens
+                        )
+                        candidate.completion_tokens = tool_stats.get(
+                            "completion_tokens", candidate.completion_tokens
+                        )
+
+                    if skill_name and candidate.call_time == 0:
+                        skill_stats = skill_stats_map.get(skill_name, {})
+                        candidate.call_time = skill_stats.get("call_count", candidate.call_time)
+                        candidate.success_time = skill_stats.get(
+                            "success_time", candidate.success_time
+                        )
                     if skill_name:
                         memory = await self.extractor._merge_skill_memory(
                             skill_name, candidate, ctx=ctx
@@ -292,43 +321,22 @@ def _get_tool_skill_info(
         Returns:
             (tool_name, skill_name, tool_status) tuple
         """
-        candidate_tool = candidate.tool_name
-        candidate_skill = candidate.skill_name
-
-        calibrated_tool = ""
-        calibrated_skill = ""
-        tool_status = "completed"
-
-        for part in tool_parts:
-            if part.skill_uri:
-                part_skill_name = self._extract_skill_name_from_uri(part.skill_uri)
-                if candidate_skill:
-                    if self._is_similar_name(candidate_skill, part_skill_name):
-                        calibrated_skill = part_skill_name
-                        tool_status = part.tool_status or "completed"
-                    else:
-                        calibrated_skill = candidate_skill
-                else:
-                    calibrated_skill = part_skill_name
+        from .tool_skill_utils import calibrate_skill_name, calibrate_tool_name
+
+        if candidate.category == MemoryCategory.TOOLS:
+            candidate_tool = (candidate.tool_name or "").strip()
+            if not candidate_tool:
+                return ("", "", "completed")
+            calibrated_name, status = calibrate_tool_name(candidate_tool, tool_parts)
+            return (calibrated_name, "", status)
+
+        if candidate.category == MemoryCategory.SKILLS:
+            candidate_skill = (candidate.skill_name or "").strip()
+            if not candidate_skill:
+                return ("", "", "completed")
+            calibrated_name, status = calibrate_skill_name(candidate_skill, tool_parts)
+            return ("", calibrated_name, status)
 
-            elif part.tool_name:
-                if candidate_tool:
-                    if self._is_similar_name(candidate_tool, part.tool_name):
-                        calibrated_tool = part.tool_name
-                        tool_status = part.tool_status or "completed"
-                    else:
-                        calibrated_tool = candidate_tool
-                else:
-                    calibrated_tool = part.tool_name
-
-        if calibrated_skill:
-            return ("", calibrated_skill, tool_status)
-        if calibrated_tool:
-            return (calibrated_tool, "", tool_status)
-        if candidate_skill:
-            return ("", candidate_skill, "completed")
-        if candidate_tool:
-            return (candidate_tool, "", "completed")
         return ("", "", "completed")
 
     def _is_similar_name(self, name1: str, name2: str) -> bool:
@@ -353,13 +361,6 @@ def _is_similar_name(self, name1: str, name2: str) -> bool:
         ratio = SequenceMatcher(None, n1, n2).ratio()
         return ratio >= 0.7
 
-    def _extract_skill_name_from_uri(self, skill_uri: str) -> str:
-        """从 skill_uri 提取 skill_name
-
-        例如: viking://agent/skills/create_presentation -> create_presentation
-        """
-        return skill_uri.rstrip("/").split("/")[-1]
-
     def _extract_used_uris(self, messages: List[Message]) -> Dict[str, List[str]]:
         """Extract URIs used in messages."""
         uris = {"memories": set(), "resources": set(), "skills": set()}
-Original file line number
+Diff line change
@@ Expand Up / @@ -162,3 +162,4 @@ test_scripts/ @@
     examples/data/
     openviking/_version.py
     specs/
+    .trae/