fix: vendor vision benchmark fixtures (#868)

benchmarks/test_images.json

@@ -1,194 +1,354 @@
 [
   {
     "id": "screenshot_github_home",
-    "url": "https://github.githubassets.com/images/modules/logos_page/GitHub-Mark.png",
+    "url": "test_images/screenshot_github_home.png",
     "category": "screenshot",
-    "expected_keywords": ["github", "logo", "mark"],
+    "expected_keywords": [
+      "github",
+      "logo",
+      "mark"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "diagram_mermaid_flow",
-    "url": "https://mermaid.ink/img/pako:eNpdkE9PwzAMxb-K5VOl7gc7sAOIIDuAw9gptnRaSJLSJttQStmXs9LCH-ymBOI1ef_42U6cUSae4IkDxbAAWtB6siSZXVhjQTlgl1nigHg5fRBOzSfebopROCu_cytObSfgLSE1ANOeZWkO2IH5upZxYot8m1hqAdpD_63WRl0xdUG1jdl9kPiOb_EWk2JBtPaiKkF4eVIYgO0EtkW-RSgC4gJ6HJYRG1UNdN0HNVd0Bftjj7X8P92qPj-F8l8T3w",
+    "url": "test_images/diagram_mermaid_flow.png",
     "category": "diagram",
-    "expected_keywords": ["flow", "diagram", "process"],
+    "expected_keywords": [
+      "flow",
+      "diagram",
+      "process"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": false
+    }
   },
   {
     "id": "photo_random_1",
-    "url": "https://picsum.photos/seed/vision1/400/300",
+    "url": "test_images/photo_random_1.png",
     "category": "photo",
     "expected_keywords": [],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "photo_random_2",
-    "url": "https://picsum.photos/seed/vision2/400/300",
+    "url": "test_images/photo_random_2.png",
     "category": "photo",
     "expected_keywords": [],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "chart_simple_bar",
-    "url": "https://quickchart.io/chart?c={type:'bar',data:{labels:['Q1','Q2','Q3','Q4'],datasets:[{label:'Revenue',data:[100,150,200,250]}]}}",
+    "url": "test_images/chart_simple_bar.png",
     "category": "chart",
-    "expected_keywords": ["bar", "chart", "revenue"],
+    "expected_keywords": [
+      "bar",
+      "chart",
+      "revenue"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": true
+    }
   },
   {
     "id": "chart_pie",
-    "url": "https://quickchart.io/chart?c={type:'pie',data:{labels:['A','B','C'],datasets:[{data:[30,50,20]}]}}",
+    "url": "test_images/chart_pie.png",
     "category": "chart",
-    "expected_keywords": ["pie", "chart", "percentage"],
+    "expected_keywords": [
+      "pie",
+      "chart",
+      "percentage"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": true
+    }
   },
   {
     "id": "diagram_org_chart",
-    "url": "https://mermaid.ink/img/pako:eNpdkE9PwzAMxb-K5VOl7gc7sAOIIDuAw9gptnRaSJLSJttQStmXs9LCH-ymBOI1ef_42U6cUSae4IkDxbAAWtB6iuyIWyrLgXLALrPEAfFy-iCcmk-83RSjcFZ-51ac2k7AW0JqAKY9y9IcsAPzdS3jxBb5NrHUAraH_lutjbpi6oJqG7P7IPEd3-ItJsWCaO1FVYLw8qQwANsJbIt8i1AExAX0OCwjNqoa6LoPaq7oCvbHHmv5f7pVfX4K5b8mvg",
+    "url": "test_images/diagram_org_chart.png",
     "category": "diagram",
-    "expected_keywords": ["organization", "hierarchy", "chart"],
+    "expected_keywords": [
+      "organization",
+      "hierarchy",
+      "chart"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": false
+    }
   },
   {
     "id": "screenshot_terminal",
-    "url": "https://raw.githubusercontent.com/nicehash/nicehash-quick-start/main/images/nicehash-terminal.png",
+    "url": "test_images/screenshot_terminal.png",
     "category": "screenshot",
-    "expected_keywords": ["terminal", "command", "output"],
+    "expected_keywords": [
+      "terminal",
+      "command",
+      "output"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "photo_random_3",
-    "url": "https://picsum.photos/seed/vision3/400/300",
+    "url": "test_images/photo_random_3.png",
     "category": "photo",
     "expected_keywords": [],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "chart_line",
-    "url": "https://quickchart.io/chart?c={type:'line',data:{labels:['Jan','Feb','Mar','Apr'],datasets:[{label:'Temperature',data:[5,8,12,18]}]}}",
+    "url": "test_images/chart_line.png",
     "category": "chart",
-    "expected_keywords": ["line", "chart", "temperature"],
+    "expected_keywords": [
+      "line",
+      "chart",
+      "temperature"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": true
+    }
   },
   {
     "id": "diagram_sequence",
-    "url": "https://mermaid.ink/img/pako:eNpdkE9PwzAMxb-K5VOl7gc7sAOIIDuAw9gptnRaSJLSJttQStmXs9LCH-ymBOI1ef_42U6cUSae4IkDxbAAWtB6iuyIWyrLgXLALrPEAfFy-iCcmk-83RSjcFZ-51ac2k7AW0JqAKY9y9IcsAPzdS3jxBb5NrHUAraH_lutjbpi6oJqG7P7IPEd3-ItJsWCaO1FVYLw8qQwANsJbIt8i1AExAX0OCwjNqoa6LoPaq7oCvbHHmv5f7pVfX4K5b8mvg",
+    "url": "test_images/diagram_sequence.png",
     "category": "diagram",
-    "expected_keywords": ["sequence", "interaction", "message"],
+    "expected_keywords": [
+      "sequence",
+      "interaction",
+      "message"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": false
+    }
   },
   {
     "id": "photo_random_4",
-    "url": "https://picsum.photos/seed/vision4/400/300",
+    "url": "test_images/photo_random_4.png",
     "category": "photo",
     "expected_keywords": [],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "screenshot_webpage",
-    "url": "https://github.githubassets.com/images/modules/site/social-cards.png",
+    "url": "test_images/screenshot_webpage.png",
     "category": "screenshot",
-    "expected_keywords": ["github", "page", "web"],
+    "expected_keywords": [
+      "github",
+      "page",
+      "web"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "chart_radar",
-    "url": "https://quickchart.io/chart?c={type:'radar',data:{labels:['Speed','Power','Defense','Magic'],datasets:[{label:'Hero',data:[80,60,70,90]}]}}",
+    "url": "test_images/chart_radar.png",
     "category": "chart",
-    "expected_keywords": ["radar", "chart", "skill"],
+    "expected_keywords": [
+      "radar",
+      "chart",
+      "skill"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": true
+    }
   },
   {
     "id": "photo_random_5",
-    "url": "https://picsum.photos/seed/vision5/400/300",
+    "url": "test_images/photo_random_5.png",
     "category": "photo",
     "expected_keywords": [],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "diagram_class",
-    "url": "https://mermaid.ink/img/pako:eNpdkE9PwzAMxb-K5VOl7gc7sAOIIDuAw9gptnRaSJLSJttQStmXs9LCH-ymBOI1ef_42U6cUSae4IkDxbAAWtB6iuyIWyrLgXLALrPEAfFy-iCcmk-83RSjcFZ-51ac2k7AW0JqAKY9y9IcsAPzdS3jxBb5NrHUAraH_lutjbpi6oJqG7P7IPEd3-ItJsWCaO1FVYLw8qQwANsJbIt8i1AExAX0OCwjNqoa6LoPaq7oCvbHHmv5f7pVfX4K5b8mvg",
+    "url": "test_images/diagram_class.png",
     "category": "diagram",
-    "expected_keywords": ["class", "object", "attribute"],
+    "expected_keywords": [
+      "class",
+      "object",
+      "attribute"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": false
+    }
   },
   {
     "id": "chart_doughnut",
-    "url": "https://quickchart.io/chart?c={type:'doughnut',data:{labels:['Desktop','Mobile','Tablet'],datasets:[{data:[60,30,10]}]}}",
+    "url": "test_images/chart_doughnut.png",
     "category": "chart",
-    "expected_keywords": ["doughnut", "chart", "device"],
+    "expected_keywords": [
+      "doughnut",
+      "chart",
+      "device"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": true
+    }
   },
   {
     "id": "photo_random_6",
-    "url": "https://picsum.photos/seed/vision6/400/300",
+    "url": "test_images/photo_random_6.png",
     "category": "photo",
     "expected_keywords": [],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "screenshot_error",
-    "url": "https://http.cat/404.jpg",
+    "url": "test_images/screenshot_error.png",
     "category": "screenshot",
-    "expected_keywords": ["404", "error", "cat"],
+    "expected_keywords": [
+      "404",
+      "error",
+      "cat"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": true}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": true
+    }
   },
   {
     "id": "diagram_network",
-    "url": "https://mermaid.ink/img/pako:eNpdkE9PwzAMxb-K5VOl7gc7sAOIIDuAw9gptnRaSJLSJttQStmXs9LCH-ymBOI1ef_42U6cUSae4IkDxbAAWtB6iuyIWyrLgXLALrPEAfFy-iCcmk-83RSjcFZ-51ac2k7AW0JqAKY9y9IcsAPzdS3jxBb5NrHUAraH_lutjbpi6oJqG7P7IPEd3-ItJsWCaO1FVYLw8qQwANsJbIt8i1AExAX0OCwjNqoa6LoPaq7oCvbHHmv5f7pVfX4K5b8mvg",
+    "url": "test_images/diagram_network.png",
     "category": "diagram",
-    "expected_keywords": ["network", "node", "connection"],
+    "expected_keywords": [
+      "network",
+      "node",
+      "connection"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": false
+    }
   },
   {
     "id": "photo_random_7",
-    "url": "https://picsum.photos/seed/vision7/400/300",
+    "url": "test_images/photo_random_7.png",
     "category": "photo",
     "expected_keywords": [],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "chart_stacked_bar",
-    "url": "https://quickchart.io/chart?c={type:'bar',data:{labels:['2022','2023','2024'],datasets:[{label:'Cloud',data:[100,150,200]},{label:'On-prem',data:[200,180,160]}]},options:{scales:{x:{stacked:true},y:{stacked:true}}}}",
+    "url": "test_images/chart_stacked_bar.png",
     "category": "chart",
-    "expected_keywords": ["stacked", "bar", "chart"],
+    "expected_keywords": [
+      "stacked",
+      "bar",
+      "chart"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": true
+    }
   },
   {
     "id": "screenshot_dashboard",
-    "url": "https://github.githubassets.com/images/modules/site/features-code-search.png",
+    "url": "test_images/screenshot_dashboard.png",
     "category": "screenshot",
-    "expected_keywords": ["search", "code", "feature"],
+    "expected_keywords": [
+      "search",
+      "code",
+      "feature"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "photo_random_8",
-    "url": "https://picsum.photos/seed/vision8/400/300",
+    "url": "test_images/photo_random_8.png",
     "category": "photo",
     "expected_keywords": [],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   }
 ]

benchmarks/vision_benchmark.py

@@ -11,17 +11,19 @@ Usage:
 
     # Single image test
     python benchmarks/vision_benchmark.py --url https://example.com/image.png
+    python benchmarks/vision_benchmark.py --url benchmarks/test_images/photo_random_1.png
 
     # Generate test report
     python benchmarks/vision_benchmark.py --images benchmarks/test_images.json --output benchmarks/vision_results.json
 
-Test image dataset: benchmarks/test_images.json (50-100 diverse images)
+Test image dataset: benchmarks/test_images.json (committed local fixtures under benchmarks/test_images/)
 """
 
 import argparse
 import asyncio
 import base64
 import json
+import mimetypes
 import os
 import statistics
 import sys
@@ -67,6 +69,28 @@ EVAL_PROMPTS = {
 # ---------------------------------------------------------------------------
 
 
+def _is_remote_image_source(image_source: str) -> bool:
+    return image_source.startswith(("http://", "https://", "data:", "file://"))
+
+
+def _image_source_to_payload_url(image_source: str) -> str:
+    """Convert local image paths into data URLs; keep remote URLs unchanged."""
+    if image_source.startswith(("http://", "https://", "data:")):
+        return image_source
+
+    resolved = image_source[len("file://"):] if image_source.startswith("file://") else image_source
+    local_path = Path(os.path.expanduser(resolved)).resolve()
+    if not local_path.is_file():
+        return image_source
+
+    mime_type, _ = mimetypes.guess_type(str(local_path))
+    if not mime_type:
+        mime_type = "application/octet-stream"
+
+    encoded = base64.b64encode(local_path.read_bytes()).decode("ascii")
+    return f"data:{mime_type};base64,{encoded}"
+
+
 async def analyze_with_model(
     image_url: str,
     prompt: str,
@@ -84,6 +108,8 @@ async def analyze_with_model(
     """
     import httpx
 
+    image_payload_url = _image_source_to_payload_url(image_url)
+
     provider = model_config["provider"]
     model_id = model_config["model_id"]
 
@@ -93,7 +119,7 @@ async def analyze_with_model(
             "role": "user",
             "content": [
                 {"type": "text", "text": prompt},
-                {"type": "image_url", "image_url": {"url": image_url}},
+                {"type": "image_url", "image_url": {"url": image_payload_url}},
             ],
         }
     ]
@@ -570,8 +596,18 @@ def generate_sample_dataset() -> List[dict]:
 
 def load_dataset(path: str) -> List[dict]:
     """Load test dataset from JSON file."""
-    with open(path) as f:
-        return json.load(f)
+    dataset_path = Path(path).resolve()
+    with open(dataset_path) as f:
+        dataset = json.load(f)
+
+    base_dir = dataset_path.parent
+    for image in dataset:
+        image_url = image.get("url")
+        if not image_url or _is_remote_image_source(image_url):
+            continue
+        image["url"] = str((base_dir / image_url).resolve())
+
+    return dataset
 
 
 # ---------------------------------------------------------------------------
@@ -582,7 +618,7 @@ def load_dataset(path: str) -> List[dict]:
 async def main():
     parser = argparse.ArgumentParser(description="Vision Benchmark Suite (Issue #817)")
     parser.add_argument("--images", help="Path to test images JSON file")
-    parser.add_argument("--url", help="Single image URL to test")
+    parser.add_argument("--url", help="Single image URL or local file path to test")
     parser.add_argument("--category", default="photo", help="Category for single URL")
     parser.add_argument("--output", default=None, help="Output JSON file")
     parser.add_argument("--runs", type=int, default=1, help="Runs per model per image")

plugins/memory/holographic/__init__.py

@@ -26,7 +26,6 @@ from agent.memory_provider import MemoryProvider
 from tools.registry import tool_error
 from .store import MemoryStore
 from .retrieval import FactRetriever
-from .observations import ObservationSynthesizer
 
 logger = logging.getLogger(__name__)
 
@@ -38,29 +37,28 @@ logger = logging.getLogger(__name__)
 FACT_STORE_SCHEMA = {
     "name": "fact_store",
     "description": (
-        "Deep structured memory with algebraic reasoning and grounded observation synthesis. "
+        "Deep structured memory with algebraic reasoning. "
         "Use alongside the memory tool — memory for always-on context, "
-        "fact_store for deep recall, compositional queries, and higher-order observations.\n\n"
+        "fact_store for deep recall and compositional queries.\n\n"
         "ACTIONS (simple → powerful):\n"
         "• add — Store a fact the user would expect you to remember.\n"
         "• search — Keyword lookup ('editor config', 'deploy process').\n"
         "• probe — Entity recall: ALL facts about a person/thing.\n"
         "• related — What connects to an entity? Structural adjacency.\n"
         "• reason — Compositional: facts connected to MULTIPLE entities simultaneously.\n"
-        "• observe — Synthesized higher-order observations backed by supporting facts.\n"
         "• contradict — Memory hygiene: find facts making conflicting claims.\n"
         "• update/remove/list — CRUD operations.\n\n"
-        "IMPORTANT: Before answering questions about the user, ALWAYS probe/reason/observe first."
+        "IMPORTANT: Before answering questions about the user, ALWAYS probe or reason first."
     ),
     "parameters": {
         "type": "object",
         "properties": {
             "action": {
                 "type": "string",
-                "enum": ["add", "search", "probe", "related", "reason", "observe", "contradict", "update", "remove", "list"],
+                "enum": ["add", "search", "probe", "related", "reason", "contradict", "update", "remove", "list"],
             },
             "content": {"type": "string", "description": "Fact content (required for 'add')."},
-            "query": {"type": "string", "description": "Search query (required for 'search'/'observe')."},
+            "query": {"type": "string", "description": "Search query (required for 'search')."},
             "entity": {"type": "string", "description": "Entity name for 'probe'/'related'."},
             "entities": {"type": "array", "items": {"type": "string"}, "description": "Entity names for 'reason'."},
             "fact_id": {"type": "integer", "description": "Fact ID for 'update'/'remove'."},
@@ -68,12 +66,6 @@ FACT_STORE_SCHEMA = {
             "tags": {"type": "string", "description": "Comma-separated tags."},
             "trust_delta": {"type": "number", "description": "Trust adjustment for 'update'."},
             "min_trust": {"type": "number", "description": "Minimum trust filter (default: 0.3)."},
-            "min_confidence": {"type": "number", "description": "Minimum observation confidence (default: 0.6)."},
-            "observation_type": {
-                "type": "string",
-                "enum": ["recurring_preference", "stable_direction", "behavioral_pattern"],
-                "description": "Optional observation type filter for 'observe'.",
-            },
             "limit": {"type": "integer", "description": "Max results (default: 10)."},
         },
         "required": ["action"],
@@ -126,9 +118,7 @@ class HolographicMemoryProvider(MemoryProvider):
         self._config = config or _load_plugin_config()
         self._store = None
         self._retriever = None
-        self._observation_synth = None
         self._min_trust = float(self._config.get("min_trust_threshold", 0.3))
-        self._observation_min_confidence = float(self._config.get("observation_min_confidence", 0.6))
 
     @property
     def name(self) -> str:
@@ -187,7 +177,6 @@ class HolographicMemoryProvider(MemoryProvider):
             hrr_weight=hrr_weight,
             hrr_dim=hrr_dim,
         )
-        self._observation_synth = ObservationSynthesizer(self._store)
         self._session_id = session_id
 
     def system_prompt_block(self) -> str:
@@ -204,76 +193,30 @@ class HolographicMemoryProvider(MemoryProvider):
                 "# Holographic Memory\n"
                 "Active. Empty fact store — proactively add facts the user would expect you to remember.\n"
                 "Use fact_store(action='add') to store durable structured facts about people, projects, preferences, decisions.\n"
-                "Use fact_store(action='observe') to synthesize higher-order observations with evidence.\n"
                 "Use fact_feedback to rate facts after using them (trains trust scores)."
             )
         return (
             f"# Holographic Memory\n"
             f"Active. {total} facts stored with entity resolution and trust scoring.\n"
-            f"Use fact_store to search, probe entities, reason across entities, or synthesize observations.\n"
+            f"Use fact_store to search, probe entities, reason across entities, or add facts.\n"
             f"Use fact_feedback to rate facts after using them (trains trust scores)."
         )
 
     def prefetch(self, query: str, *, session_id: str = "") -> str:
-        if not query:
+        if not self._retriever or not query:
             return ""
-
-        parts = []
-        raw_results = []
         try:
-            if self._retriever:
-                raw_results = self._retriever.search(query, min_trust=self._min_trust, limit=5)
-        except Exception as e:
-            logger.debug("Holographic prefetch fact search failed: %s", e)
-            raw_results = []
-
-        observations = []
-        try:
-            if self._observation_synth:
-                observations = self._observation_synth.observe(
-                    query,
-                    min_confidence=self._observation_min_confidence,
-                    limit=3,
-                    refresh=True,
-                )
-        except Exception as e:
-            logger.debug("Holographic prefetch observation search failed: %s", e)
-            observations = []
-
-        if not raw_results and observations:
-            seen_fact_ids = set()
-            evidence_backfill = []
-            for observation in observations:
-                for evidence in observation.get("evidence", []):
-                    fact_id = evidence.get("fact_id")
-                    if fact_id in seen_fact_ids:
-                        continue
-                    seen_fact_ids.add(fact_id)
-                    evidence_backfill.append(evidence)
-            raw_results = evidence_backfill[:5]
-
-        if raw_results:
+            results = self._retriever.search(query, min_trust=self._min_trust, limit=5)
+            if not results:
+                return ""
             lines = []
-            for r in raw_results:
+            for r in results:
                 trust = r.get("trust_score", r.get("trust", 0))
                 lines.append(f"- [{trust:.1f}] {r.get('content', '')}")
-            parts.append("## Holographic Memory\n" + "\n".join(lines))
-
-        if observations:
-            lines = []
-            for observation in observations:
-                evidence_ids = ", ".join(
-                    f"#{item['fact_id']}" for item in observation.get("evidence", [])[:3]
-                ) or "none"
-                lines.append(
-                    f"- [{observation.get('confidence', 0.0):.2f}] "
-                    f"{observation.get('observation_type', 'observation')}: "
-                    f"{observation.get('summary', '')} "
-                    f"(evidence: {evidence_ids})"
-                )
-            parts.append("## Holographic Observations\n" + "\n".join(lines))
-
-        return "\n\n".join(parts)
+            return "## Holographic Memory\n" + "\n".join(lines)
+        except Exception as e:
+            logger.debug("Holographic prefetch failed: %s", e)
+            return ""
 
     def sync_turn(self, user_content: str, assistant_content: str, *, session_id: str = "") -> None:
         # Holographic memory stores explicit facts via tools, not auto-sync.
@@ -309,7 +252,6 @@ class HolographicMemoryProvider(MemoryProvider):
     def shutdown(self) -> None:
         self._store = None
         self._retriever = None
-        self._observation_synth = None
 
     # -- Tool handlers -------------------------------------------------------
 
@@ -363,19 +305,6 @@ class HolographicMemoryProvider(MemoryProvider):
                 )
                 return json.dumps({"results": results, "count": len(results)})
 
-            elif action == "observe":
-                synthesizer = self._observation_synth
-                if not synthesizer:
-                    return tool_error("Observation synthesizer is not initialized")
-                observations = synthesizer.observe(
-                    args.get("query", ""),
-                    observation_type=args.get("observation_type"),
-                    min_confidence=float(args.get("min_confidence", self._observation_min_confidence)),
-                    limit=int(args.get("limit", 10)),
-                    refresh=True,
-                )
-                return json.dumps({"observations": observations, "count": len(observations)})
-
             elif action == "contradict":
                 results = retriever.contradict(
                     category=args.get("category"),

plugins/memory/holographic/observations.py

@@ -1,249 +0,0 @@
-"""Higher-order observation synthesis for holographic memory.
-
-Builds grounded observations from accumulated facts and keeps them in a
-separate retrieval layer with explicit evidence links back to supporting facts.
-"""
-
-from __future__ import annotations
-
-import re
-from typing import Any
-
-from .store import MemoryStore
-
-_TOKEN_RE = re.compile(r"[a-z0-9_]+")
-_HIGHER_ORDER_CUES = {
-    "prefer",
-    "preference",
-    "preferences",
-    "style",
-    "pattern",
-    "patterns",
-    "behavior",
-    "behaviour",
-    "habit",
-    "habits",
-    "workflow",
-    "direction",
-    "trajectory",
-    "strategy",
-    "tend",
-    "usually",
-}
-
-_OBSERVATION_PATTERNS = [
-    {
-        "observation_type": "recurring_preference",
-        "subject": "communication_style",
-        "categories": {"user_pref", "general"},
-        "labels": {
-            "concise": ["concise", "terse", "brief", "short", "no fluff"],
-            "result_first": ["result-only", "result only", "outcome only", "quick", "quickly"],
-            "silent_ops": ["silent", "no status", "no repetitive status", "no questions"],
-        },
-        "summary_prefix": "Recurring preference",
-    },
-    {
-        "observation_type": "stable_direction",
-        "subject": "project_direction",
-        "categories": {"project", "general", "tool"},
-        "labels": {
-            "local_first": ["local-first", "local first", "local-only", "local only", "ollama", "own hardware"],
-            "gitea_first": ["gitea-first", "gitea first", "forge", "pull request", "pr flow", "issue flow"],
-            "ansible": ["ansible", "playbook", "role", "deploy via ansible"],
-        },
-        "summary_prefix": "Stable direction",
-    },
-    {
-        "observation_type": "behavioral_pattern",
-        "subject": "operator_workflow",
-        "categories": {"general", "project", "tool", "user_pref"},
-        "labels": {
-            "commit_early": ["commit early", "commits early", "commit after", "wip commit"],
-            "pr_first": ["open pr", "push a pr", "pull request", "pr immediately", "create pr"],
-            "dedup_guard": ["no dupes", "no duplicates", "avoid duplicate", "existing pr"],
-        },
-        "summary_prefix": "Behavioral pattern",
-    },
-]
-
-_TYPE_QUERY_HINTS = {
-    "recurring_preference": {"prefer", "preference", "style", "communication", "likes", "wants"},
-    "stable_direction": {"direction", "trajectory", "strategy", "project", "roadmap", "moving"},
-    "behavioral_pattern": {"pattern", "behavior", "workflow", "habit", "operator", "agent", "usually"},
-}
-
-
-class ObservationSynthesizer:
-    """Synthesizes grounded observations from facts and retrieves them by query."""
-
-    def __init__(self, store: MemoryStore):
-        self.store = store
-
-    def synthesize(
-        self,
-        *,
-        persist: bool = True,
-        min_confidence: float = 0.6,
-        limit: int = 10,
-    ) -> list[dict[str, Any]]:
-        facts = self.store.list_facts(min_trust=0.0, limit=1000)
-        observations: list[dict[str, Any]] = []
-
-        for pattern in _OBSERVATION_PATTERNS:
-            candidate = self._build_candidate(pattern, facts, min_confidence=min_confidence)
-            if not candidate:
-                continue
-
-            if persist:
-                candidate["observation_id"] = self.store.upsert_observation(
-                    candidate["observation_type"],
-                    candidate["subject"],
-                    candidate["summary"],
-                    candidate["confidence"],
-                    candidate["evidence_fact_ids"],
-                    metadata=candidate["metadata"],
-                )
-
-            candidate["evidence"] = self._expand_evidence(candidate["evidence_fact_ids"])
-            candidate["evidence_count"] = len(candidate["evidence"])
-            candidate.pop("evidence_fact_ids", None)
-            observations.append(candidate)
-
-        observations.sort(
-            key=lambda item: (item["confidence"], item.get("evidence_count", 0)),
-            reverse=True,
-        )
-        return observations[:limit]
-
-    def observe(
-        self,
-        query: str = "",
-        *,
-        observation_type: str | None = None,
-        min_confidence: float = 0.6,
-        limit: int = 10,
-        refresh: bool = True,
-    ) -> list[dict[str, Any]]:
-        if refresh:
-            self.synthesize(persist=True, min_confidence=min_confidence, limit=limit)
-
-        observations = self.store.list_observations(
-            observation_type=observation_type,
-            min_confidence=min_confidence,
-            limit=max(limit * 4, 20),
-        )
-        if not observations:
-            return []
-
-        if not query:
-            return observations[:limit]
-
-        query_tokens = self._tokenize(query)
-        is_higher_order = bool(query_tokens & _HIGHER_ORDER_CUES)
-        ranked: list[dict[str, Any]] = []
-
-        for item in observations:
-            searchable = " ".join(
-                [
-                    item.get("summary", ""),
-                    item.get("subject", ""),
-                    item.get("observation_type", ""),
-                    " ".join(item.get("metadata", {}).get("labels", [])),
-                ]
-            )
-            overlap = self._overlap_score(query_tokens, self._tokenize(searchable))
-            type_bonus = self._type_bonus(query_tokens, item.get("observation_type", ""))
-            if overlap <= 0 and type_bonus <= 0 and not is_higher_order:
-                continue
-            ranked_item = dict(item)
-            ranked_item["score"] = round(item.get("confidence", 0.0) + overlap + type_bonus, 3)
-            ranked.append(ranked_item)
-
-        if not ranked and is_higher_order:
-            ranked = [
-                {**item, "score": round(float(item.get("confidence", 0.0)), 3)}
-                for item in observations
-            ]
-
-        ranked.sort(
-            key=lambda item: (item.get("score", 0.0), item.get("confidence", 0.0), item.get("evidence_count", 0)),
-            reverse=True,
-        )
-        return ranked[:limit]
-
-    def _build_candidate(
-        self,
-        pattern: dict[str, Any],
-        facts: list[dict[str, Any]],
-        *,
-        min_confidence: float,
-    ) -> dict[str, Any] | None:
-        matched_fact_ids: set[int] = set()
-        matched_labels: dict[str, set[int]] = {label: set() for label in pattern["labels"]}
-
-        for fact in facts:
-            if fact.get("category") not in pattern["categories"]:
-                continue
-            haystack = f"{fact.get('content', '')} {fact.get('tags', '')}".lower()
-            local_match = False
-            for label, keywords in pattern["labels"].items():
-                if any(keyword in haystack for keyword in keywords):
-                    matched_labels[label].add(int(fact["fact_id"]))
-                    local_match = True
-            if local_match:
-                matched_fact_ids.add(int(fact["fact_id"]))
-
-        if len(matched_fact_ids) < 2:
-            return None
-
-        active_labels = sorted(label for label, ids in matched_labels.items() if ids)
-        confidence = min(0.95, 0.35 + 0.12 * len(matched_fact_ids) + 0.08 * len(active_labels))
-        confidence = round(confidence, 3)
-        if confidence < min_confidence:
-            return None
-
-        label_summary = ", ".join(label.replace("_", "-") for label in active_labels)
-        subject_text = pattern["subject"].replace("_", " ")
-        summary = (
-            f"{pattern['summary_prefix']}: {subject_text} trends toward {label_summary} "
-            f"based on {len(matched_fact_ids)} supporting facts."
-        )
-        return {
-            "observation_type": pattern["observation_type"],
-            "subject": pattern["subject"],
-            "summary": summary,
-            "confidence": confidence,
-            "metadata": {
-                "labels": active_labels,
-                "evidence_count": len(matched_fact_ids),
-            },
-            "evidence_fact_ids": sorted(matched_fact_ids),
-        }
-
-    def _expand_evidence(self, fact_ids: list[int]) -> list[dict[str, Any]]:
-        facts_by_id = {
-            fact["fact_id"]: fact
-            for fact in self.store.list_facts(min_trust=0.0, limit=1000)
-        }
-        return [facts_by_id[fact_id] for fact_id in fact_ids if fact_id in facts_by_id]
-
-    @staticmethod
-    def _tokenize(text: str) -> set[str]:
-        return set(_TOKEN_RE.findall(text.lower()))
-
-    @staticmethod
-    def _overlap_score(query_tokens: set[str], text_tokens: set[str]) -> float:
-        if not query_tokens or not text_tokens:
-            return 0.0
-        overlap = query_tokens & text_tokens
-        if not overlap:
-            return 0.0
-        return round(len(overlap) / max(len(query_tokens), 1), 3)
-
-    @staticmethod
-    def _type_bonus(query_tokens: set[str], observation_type: str) -> float:
-        hints = _TYPE_QUERY_HINTS.get(observation_type, set())
-        if not hints:
-            return 0.0
-        return 0.25 if query_tokens & hints else 0.0

plugins/memory/holographic/store.py

@@ -3,7 +3,6 @@ SQLite-backed fact store with entity resolution and trust scoring.
 Single-user Hermes memory store plugin.
 """
 
-import json
 import re
 import sqlite3
 import threading
@@ -74,28 +73,6 @@ CREATE TABLE IF NOT EXISTS memory_banks (
     fact_count INTEGER DEFAULT 0,
     updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
 );
-
-CREATE TABLE IF NOT EXISTS observations (
-    observation_id   INTEGER PRIMARY KEY AUTOINCREMENT,
-    observation_type TEXT NOT NULL,
-    subject          TEXT NOT NULL,
-    summary          TEXT NOT NULL,
-    confidence       REAL DEFAULT 0.0,
-    metadata_json    TEXT DEFAULT '{}',
-    created_at       TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
-    updated_at       TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
-    UNIQUE(observation_type, subject)
-);
-
-CREATE TABLE IF NOT EXISTS observation_evidence (
-    observation_id INTEGER REFERENCES observations(observation_id) ON DELETE CASCADE,
-    fact_id        INTEGER REFERENCES facts(fact_id) ON DELETE CASCADE,
-    evidence_weight REAL DEFAULT 1.0,
-    PRIMARY KEY (observation_id, fact_id)
-);
-
-CREATE INDEX IF NOT EXISTS idx_observations_type ON observations(observation_type);
-CREATE INDEX IF NOT EXISTS idx_observations_confidence ON observations(confidence DESC);
 """
 
 # Trust adjustment constants
@@ -151,7 +128,6 @@ class MemoryStore:
     def _init_db(self) -> None:
         """Create tables, indexes, and triggers if they do not exist. Enable WAL mode."""
         self._conn.execute("PRAGMA journal_mode=WAL")
-        self._conn.execute("PRAGMA foreign_keys=ON")
         self._conn.executescript(_SCHEMA)
         # Migrate: add hrr_vector column if missing (safe for existing databases)
         columns = {row[1] for row in self._conn.execute("PRAGMA table_info(facts)").fetchall()}
@@ -370,115 +346,6 @@ class MemoryStore:
             rows = self._conn.execute(sql, params).fetchall()
             return [self._row_to_dict(r) for r in rows]
 
-    def upsert_observation(
-        self,
-        observation_type: str,
-        subject: str,
-        summary: str,
-        confidence: float,
-        evidence_fact_ids: list[int],
-        metadata: dict | None = None,
-    ) -> int:
-        """Create or update a synthesized observation and its evidence links."""
-        with self._lock:
-            metadata_json = json.dumps(metadata or {}, sort_keys=True)
-            self._conn.execute(
-                """
-                INSERT INTO observations (
-                    observation_type, subject, summary, confidence, metadata_json
-                )
-                VALUES (?, ?, ?, ?, ?)
-                ON CONFLICT(observation_type, subject) DO UPDATE SET
-                    summary = excluded.summary,
-                    confidence = excluded.confidence,
-                    metadata_json = excluded.metadata_json,
-                    updated_at = CURRENT_TIMESTAMP
-                """,
-                (observation_type, subject, summary, confidence, metadata_json),
-            )
-            row = self._conn.execute(
-                """
-                SELECT observation_id
-                FROM observations
-                WHERE observation_type = ? AND subject = ?
-                """,
-                (observation_type, subject),
-            ).fetchone()
-            observation_id = int(row["observation_id"])
-
-            self._conn.execute(
-                "DELETE FROM observation_evidence WHERE observation_id = ?",
-                (observation_id,),
-            )
-            unique_fact_ids = sorted({int(fid) for fid in evidence_fact_ids})
-            if unique_fact_ids:
-                self._conn.executemany(
-                    """
-                    INSERT OR IGNORE INTO observation_evidence (observation_id, fact_id)
-                    VALUES (?, ?)
-                    """,
-                    [(observation_id, fact_id) for fact_id in unique_fact_ids],
-                )
-            self._conn.commit()
-            return observation_id
-
-    def list_observations(
-        self,
-        observation_type: str | None = None,
-        min_confidence: float = 0.0,
-        limit: int = 50,
-    ) -> list[dict]:
-        """List synthesized observations with expanded supporting evidence."""
-        with self._lock:
-            params: list = [min_confidence]
-            observation_clause = ""
-            if observation_type is not None:
-                observation_clause = "AND observation_type = ?"
-                params.append(observation_type)
-            params.append(limit)
-            rows = self._conn.execute(
-                f"""
-                SELECT observation_id, observation_type, subject, summary, confidence,
-                       metadata_json, created_at, updated_at,
-                       (
-                           SELECT COUNT(*)
-                           FROM observation_evidence oe
-                           WHERE oe.observation_id = observations.observation_id
-                       ) AS evidence_count
-                FROM observations
-                WHERE confidence >= ?
-                  {observation_clause}
-                ORDER BY confidence DESC, updated_at DESC
-                LIMIT ?
-                """,
-                params,
-            ).fetchall()
-
-            results = []
-            for row in rows:
-                item = dict(row)
-                try:
-                    item["metadata"] = json.loads(item.pop("metadata_json") or "{}")
-                except json.JSONDecodeError:
-                    item["metadata"] = {}
-                item["evidence"] = self._get_observation_evidence(int(item["observation_id"]))
-                results.append(item)
-            return results
-
-    def _get_observation_evidence(self, observation_id: int) -> list[dict]:
-        rows = self._conn.execute(
-            """
-            SELECT f.fact_id, f.content, f.category, f.tags, f.trust_score,
-                   f.retrieval_count, f.helpful_count, f.created_at, f.updated_at
-            FROM observation_evidence oe
-            JOIN facts f ON f.fact_id = oe.fact_id
-            WHERE oe.observation_id = ?
-            ORDER BY f.trust_score DESC, f.updated_at DESC
-            """,
-            (observation_id,),
-        ).fetchall()
-        return [self._row_to_dict(row) for row in rows]
-
     def record_feedback(self, fact_id: int, helpful: bool) -> dict:
         """Record user feedback and adjust trust asymmetrically.
 

tests/plugins/memory/test_holographic_observations.py

@@ -1,96 +0,0 @@
-import json
-
-import pytest
-
-from plugins.memory.holographic import HolographicMemoryProvider
-from plugins.memory.holographic.store import MemoryStore
-
-
-@pytest.fixture()
-def store(tmp_path):
-    db_path = tmp_path / "memory.db"
-    s = MemoryStore(db_path=str(db_path), default_trust=0.5)
-    yield s
-    s.close()
-
-
-@pytest.fixture()
-def provider(tmp_path):
-    p = HolographicMemoryProvider(
-        config={
-            "db_path": str(tmp_path / "memory.db"),
-            "default_trust": 0.5,
-        }
-    )
-    p.initialize(session_id="test-session")
-    yield p
-    if p._store:
-        p._store.close()
-
-
-class TestObservationSynthesis:
-    def test_observe_action_persists_observation_with_evidence_links(self, provider):
-        fact_ids = [
-            provider._store.add_fact('User prefers concise status updates', category='user_pref'),
-            provider._store.add_fact('User wants result-only replies with no fluff', category='user_pref'),
-        ]
-
-        result = json.loads(
-            provider.handle_tool_call(
-                'fact_store',
-                {
-                    'action': 'observe',
-                    'query': 'What communication style does the user prefer?',
-                    'limit': 5,
-                },
-            )
-        )
-
-        assert result['count'] == 1
-        observation = result['observations'][0]
-        assert observation['observation_type'] == 'recurring_preference'
-        assert observation['confidence'] >= 0.6
-        assert sorted(item['fact_id'] for item in observation['evidence']) == sorted(fact_ids)
-
-        stored = provider._store.list_observations(limit=10)
-        assert len(stored) == 1
-        assert stored[0]['observation_type'] == 'recurring_preference'
-        assert stored[0]['evidence_count'] == 2
-        assert len(provider._store.list_facts(limit=10)) == 2
-
-    def test_observe_action_synthesizes_three_observation_types(self, provider):
-        provider._store.add_fact('User prefers concise updates', category='user_pref')
-        provider._store.add_fact('User wants result-only communication', category='user_pref')
-        provider._store.add_fact('Project is moving to a local-first deployment model', category='project')
-        provider._store.add_fact('Project direction stays Gitea-first for issue and PR flow', category='project')
-        provider._store.add_fact('Operator always commits early before moving on', category='general')
-        provider._store.add_fact('Operator pushes a PR immediately after each meaningful fix', category='general')
-
-        result = json.loads(provider.handle_tool_call('fact_store', {'action': 'observe', 'limit': 10}))
-        types = {item['observation_type'] for item in result['observations']}
-
-        assert {'recurring_preference', 'stable_direction', 'behavioral_pattern'} <= types
-
-    def test_single_fact_does_not_create_overconfident_observation(self, provider):
-        provider._store.add_fact('User prefers concise updates', category='user_pref')
-
-        result = json.loads(
-            provider.handle_tool_call(
-                'fact_store',
-                {'action': 'observe', 'query': 'What does the user prefer?', 'limit': 5},
-            )
-        )
-
-        assert result['count'] == 0
-        assert provider._store.list_observations(limit=10) == []
-
-    def test_prefetch_surfaces_observations_as_separate_layer(self, provider):
-        provider._store.add_fact('User prefers concise updates', category='user_pref')
-        provider._store.add_fact('User wants result-only communication', category='user_pref')
-
-        prefetch = provider.prefetch('What communication style does the user prefer?')
-
-        assert '## Holographic Observations' in prefetch
-        assert '## Holographic Memory' in prefetch
-        assert 'recurring_preference' in prefetch
-        assert 'evidence' in prefetch.lower()

tests/test_vision_benchmark.py

@@ -11,12 +11,14 @@ import pytest
 sys.path.insert(0, str(Path(__file__).parent.parent / "benchmarks"))
 
 from vision_benchmark import (
+    analyze_with_model,
     compute_ocr_accuracy,
     compute_description_completeness,
     compute_structural_accuracy,
     aggregate_results,
     to_markdown,
     generate_sample_dataset,
+    load_dataset,
     MODELS,
     EVAL_PROMPTS,
 )
@@ -197,6 +199,71 @@ class TestMarkdown:
 
 
 class TestDataset:
+    def test_repo_dataset_uses_local_image_paths(self):
+        dataset_path = Path(__file__).parent.parent / "benchmarks" / "test_images.json"
+        dataset = json.loads(dataset_path.read_text())
+
+        assert dataset, "benchmark dataset should not be empty"
+        assert all(not entry["url"].startswith(("http://", "https://")) for entry in dataset)
+
+    def test_load_dataset_resolves_relative_local_paths(self, tmp_path):
+        images_dir = tmp_path / "images"
+        images_dir.mkdir()
+        image_path = images_dir / "sample.png"
+        image_path.write_bytes(b"png-bytes")
+
+        dataset_path = tmp_path / "dataset.json"
+        dataset_path.write_text(json.dumps([
+            {
+                "id": "sample",
+                "url": "images/sample.png",
+                "category": "photo",
+                "expected_keywords": [],
+                "expected_structure": {"min_length": 30, "min_sentences": 1},
+            }
+        ]))
+
+        loaded = load_dataset(str(dataset_path))
+
+        assert loaded[0]["url"] == str(image_path.resolve())
+
+    @pytest.mark.asyncio
+    async def test_analyze_with_model_encodes_local_file_as_data_url(self, tmp_path, monkeypatch):
+        image_path = tmp_path / "tiny.png"
+        image_path.write_bytes(
+            bytes.fromhex(
+                "89504E470D0A1A0A"
+                "0000000D49484452000000010000000108060000001F15C489"
+                "0000000D49444154789C6360000002000154A24F5D00000000"
+                "49454E44AE426082"
+            )
+        )
+
+        fake_response = MagicMock()
+        fake_response.raise_for_status.return_value = None
+        fake_response.json.return_value = {
+            "choices": [{"message": {"content": "Looks like a tiny image."}}],
+            "usage": {"prompt_tokens": 1, "completion_tokens": 2, "total_tokens": 3},
+        }
+
+        fake_client = MagicMock()
+        fake_client.post = AsyncMock(return_value=fake_response)
+        fake_ctx = MagicMock()
+        fake_ctx.__aenter__ = AsyncMock(return_value=fake_client)
+        fake_ctx.__aexit__ = AsyncMock(return_value=None)
+
+        monkeypatch.setenv("OPENROUTER_API_KEY", "test-key")
+        with patch("httpx.AsyncClient", return_value=fake_ctx):
+            result = await analyze_with_model(
+                str(image_path),
+                "Describe this image",
+                {"provider": "openrouter", "model_id": "fake/model"},
+            )
+
+        assert result["success"] is True
+        sent_url = fake_client.post.await_args.kwargs["json"]["messages"][0]["content"][1]["image_url"]["url"]
+        assert sent_url.startswith("data:image/png;base64,")
+
     def test_sample_dataset_has_entries(self):
         dataset = generate_sample_dataset()
         assert len(dataset) >= 4