feat: harden tool-call benchmark coverage and reporting for #796

Refs #796

benchmarks/gemma4-tool-calling-2026-04-22.md

@@ -0,0 +1,139 @@
+# Tool-Calling Benchmark Report
+
+Generated: 2026-04-22 15:46 UTC
+Executed: 3 calls from a 100-call suite across 7 categories
+Models tested: nous:gia-3/gemma-4-31b, gemini:gemma-4-26b-it, nous:mimo-v2-pro
+
+## Requested category mix
+
+| Category | Target calls |
+|----------|--------------|
+| file | 20 |
+| terminal | 20 |
+| web | 15 |
+| code | 15 |
+| browser | 10 |
+| delegate | 10 |
+| mcp | 10 |
+
+## Summary
+
+| Metric | nous:gia-3/gemma-4-31b | gemini:gemma-4-26b-it | nous:mimo-v2-pro |
+|--------|---------|---------|---------|
+| Schema parse success | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) | 
+| Tool execution success | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) | 
+| Parallel tool success | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) | 
+| Avg latency (s) | 0.00 | 0.00 | 0.00 | 
+| Avg tokens per call | 0.0 | 0.0 | 0.0 | 
+| Avg token cost per call (USD) | n/a | n/a | n/a | 
+| Skipped / unavailable | 0/1 | 0/1 | 0/1 | 
+
+## Per-category breakdown
+
+### File
+
+| Metric | nous:gia-3/gemma-4-31b | gemini:gemma-4-26b-it | nous:mimo-v2-pro |
+|--------|---------|---------|---------|
+| Schema OK | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) | 
+| Exec OK | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) | 
+| Parallel OK | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) | 
+| Correct tool | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) | 
+| Avg tokens | 0.0 | 0.0 | 0.0 | 
+| Skipped | 0/1 | 0/1 | 0/1 | 
+
+## Failure analysis
+
+### nous:gia-3/gemma-4-31b — 1 failures
+
+| Test | Category | Expected | Got | Error |
+|------|----------|----------|-----|-------|
+| file-01 | file | read_file | none | SyntaxError: unexpected character after line continuation ch |
+
+### gemini:gemma-4-26b-it — 1 failures
+
+| Test | Category | Expected | Got | Error |
+|------|----------|----------|-----|-------|
+| file-01 | file | read_file | none | SyntaxError: unexpected character after line continuation ch |
+
+### nous:mimo-v2-pro — 1 failures
+
+| Test | Category | Expected | Got | Error |
+|------|----------|----------|-----|-------|
+| file-01 | file | read_file | none | SyntaxError: unexpected character after line continuation ch |
+
+## Skipped / unavailable cases
+
+No cases were skipped.
+
+## Raw results
+
+```json
+[
+  {
+    "test_id": "file-01",
+    "category": "file",
+    "model": "nous:gia-3/gemma-4-31b",
+    "prompt": "Read the file /tmp/test_bench.txt and show me its contents.",
+    "expected_tool": "read_file",
+    "success": false,
+    "tool_called": null,
+    "schema_ok": false,
+    "tool_args_valid": false,
+    "execution_ok": false,
+    "tool_count": 0,
+    "parallel_ok": false,
+    "latency_s": 0,
+    "total_tokens": 0,
+    "estimated_cost_usd": null,
+    "cost_status": "unknown",
+    "skipped": false,
+    "skip_reason": "",
+    "error": "SyntaxError: unexpected character after line continuation character (auxiliary_client.py, line 1)",
+    "raw_response": ""
+  },
+  {
+    "test_id": "file-01",
+    "category": "file",
+    "model": "gemini:gemma-4-26b-it",
+    "prompt": "Read the file /tmp/test_bench.txt and show me its contents.",
+    "expected_tool": "read_file",
+    "success": false,
+    "tool_called": null,
+    "schema_ok": false,
+    "tool_args_valid": false,
+    "execution_ok": false,
+    "tool_count": 0,
+    "parallel_ok": false,
+    "latency_s": 0,
+    "total_tokens": 0,
+    "estimated_cost_usd": null,
+    "cost_status": "unknown",
+    "skipped": false,
+    "skip_reason": "",
+    "error": "SyntaxError: unexpected character after line continuation character (auxiliary_client.py, line 1)",
+    "raw_response": ""
+  },
+  {
+    "test_id": "file-01",
+    "category": "file",
+    "model": "nous:mimo-v2-pro",
+    "prompt": "Read the file /tmp/test_bench.txt and show me its contents.",
+    "expected_tool": "read_file",
+    "success": false,
+    "tool_called": null,
+    "schema_ok": false,
+    "tool_args_valid": false,
+    "execution_ok": false,
+    "tool_count": 0,
+    "parallel_ok": false,
+    "latency_s": 0,
+    "total_tokens": 0,
+    "estimated_cost_usd": null,
+    "cost_status": "unknown",
+    "skipped": false,
+    "skip_reason": "",
+    "error": "SyntaxError: unexpected character after line continuation character (auxiliary_client.py, line 1)",
+    "raw_response": ""
+  }
+]
+```

benchmarks/tool_call_benchmark.py

@@ -8,10 +8,11 @@ success rates, latency, and token costs.
 Usage:
     python3 benchmarks/tool_call_benchmark.py                  # full 100-call suite
     python3 benchmarks/tool_call_benchmark.py --limit 10       # quick smoke test
-    python3 benchmarks/tool_call_benchmark.py --models nous     # single model
-    python3 benchmarks/tool_call_benchmark.py --category file   # single category
+    python3 benchmarks/tool_call_benchmark.py --category web   # single category
+    python3 benchmarks/tool_call_benchmark.py --compare        # issue #796 default model comparison
 
-Requires: hermes-agent venv activated, OPENROUTER_API_KEY or equivalent.
+Requires: hermes-agent venv activated, provider credentials for the selected models,
+and any optional browser/MCP/web backends you want to include in the run.
 """
 
 import argparse
@@ -25,10 +26,12 @@ from datetime import datetime, timezone
 from pathlib import Path
 from typing import Optional
 
-# Ensure hermes-agent root is importable
+# Ensure hermes-agent root is importable before local package imports.
 REPO_ROOT = Path(__file__).resolve().parent.parent
 sys.path.insert(0, str(REPO_ROOT))
 
+from agent.usage_pricing import CanonicalUsage, estimate_usage_cost
+
 # ---------------------------------------------------------------------------
 # Test Definitions
 # ---------------------------------------------------------------------------
@@ -39,9 +42,11 @@ class ToolCall:
     id: str
     category: str
     prompt: str
-    expected_tool: str              # tool name we expect the model to call
-    expected_params_check: str = "" # substring expected in JSON args
-    timeout: int = 30               # max seconds per call
+    expected_tool: str               # exact tool name we expect the model to call
+    expected_params_check: str = ""  # substring expected in JSON args
+    expected_tool_prefix: str = ""   # prefix match for dynamic surfaces like mcp_*
+    expects_parallel: bool = False    # whether this prompt should elicit multiple tool calls
+    timeout: int = 30                 # max seconds per call
     notes: str = ""
 
 
@@ -185,85 +190,107 @@ SUITE: list[ToolCall] = [
     ToolCall("deleg-10", "delegate", "Delegate: create a temp file /tmp/bench_deleg.txt with 'done'.",
              "delegate_task", "write"),
 
-    # ── Todo / Memory (10 — replacing web/browser/MCP which need external services) ──
-    ToolCall("todo-01", "todo", "Add a todo item: 'Run benchmark suite'",
-             "todo", "benchmark"),
-    ToolCall("todo-02", "todo", "Show me the current todo list.",
-             "todo", ""),
-    ToolCall("todo-03", "todo", "Mark the first todo item as completed.",
-             "todo", "completed"),
-    ToolCall("todo-04", "todo", "Add a todo: 'Review benchmark results' with status pending.",
-             "todo", "Review"),
-    ToolCall("todo-05", "todo", "Clear all completed todos.",
-             "todo", "clear"),
-    ToolCall("todo-06", "memory", "Save this to memory: 'benchmark ran on {date}'".format(
-              date=datetime.now().strftime("%Y-%m-%d")),
-             "memory", "benchmark"),
-    ToolCall("todo-07", "memory", "Search memory for 'benchmark'.",
-             "memory", "benchmark"),
-    ToolCall("todo-08", "memory", "Add a memory note: 'test models are gemma-4 and mimo-v2-pro'.",
-             "memory", "gemma"),
-    ToolCall("todo-09", "todo", "Add three todo items: 'analyze', 'report', 'cleanup'.",
-             "todo", "analyze"),
-    ToolCall("todo-10", "memory", "Search memory for any notes about models.",
-             "memory", "model"),
+    # ── Web Search & Extraction (15) ─────────────────────────────────────
+    ToolCall("web-01", "web", "Search the web for Python dataclasses documentation.",
+             "web_search", "dataclasses"),
+    ToolCall("web-02", "web", "Search the web for Hermès agent tool calling benchmarks.",
+             "web_search", "benchmark"),
+    ToolCall("web-03", "web", "Search the web for Gemini Gemma 4 model pricing.",
+             "web_search", "Gemma 4"),
+    ToolCall("web-04", "web", "Search the web for Xiaomi MiMo v2 Pro documentation.",
+             "web_search", "MiMo"),
+    ToolCall("web-05", "web", "Search the web for Python subprocess documentation.",
+             "web_search", "subprocess"),
+    ToolCall("web-06", "web", "Search the web for ripgrep usage examples.",
+             "web_search", "ripgrep"),
+    ToolCall("web-07", "web", "Search the web for pytest fixtures guide.",
+             "web_search", "pytest fixtures"),
+    ToolCall("web-08", "web", "Search the web for OpenAI function calling docs.",
+             "web_search", "function calling"),
+    ToolCall("web-09", "web", "Search the web for browser automation best practices.",
+             "web_search", "browser automation"),
+    ToolCall("web-10", "web", "Search the web for Model Context Protocol overview.",
+             "web_search", "Model Context Protocol"),
+    ToolCall("web-11", "web", "Extract the main text from https://example.com.",
+             "web_extract", "example.com"),
+    ToolCall("web-12", "web", "Extract the page content from https://example.org.",
+             "web_extract", "example.org"),
+    ToolCall("web-13", "web", "Extract the title and body text from https://www.iana.org/domains/reserved.",
+             "web_extract", "iana.org"),
+    ToolCall("web-14", "web", "Extract content from https://httpbin.org/html.",
+             "web_extract", "httpbin.org"),
+    ToolCall("web-15", "web", "Extract the main content from https://www.python.org/.",
+             "web_extract", "python.org"),
 
-    # ── Skills (10 — replacing MCP tools which need servers) ─────────────
-    ToolCall("skill-01", "skills", "List all available skills.",
-             "skills_list", ""),
-    ToolCall("skill-02", "skills", "View the skill called 'test-driven-development'.",
-             "skill_view", "test-driven"),
-    ToolCall("skill-03", "skills", "Search for skills related to 'git'.",
-             "skills_list", "git"),
-    ToolCall("skill-04", "skills", "View the 'code-review' skill.",
-             "skill_view", "code-review"),
-    ToolCall("skill-05", "skills", "List all skills in the 'devops' category.",
-             "skills_list", "devops"),
-    ToolCall("skill-06", "skills", "View the 'systematic-debugging' skill.",
-             "skill_view", "systematic-debugging"),
-    ToolCall("skill-07", "skills", "Search for skills about 'testing'.",
-             "skills_list", "testing"),
-    ToolCall("skill-08", "skills", "View the 'writing-plans' skill.",
-             "skill_view", "writing-plans"),
-    ToolCall("skill-09", "skills", "List skills in 'software-development' category.",
-             "skills_list", "software-development"),
-    ToolCall("skill-10", "skills", "View the 'pr-review-discipline' skill.",
-             "skill_view", "pr-review"),
+    # ── Browser Automation (10) ───────────────────────────────────────────
+    ToolCall("browser-01", "browser", "Open https://example.com in the browser.",
+             "browser_navigate", "example.com"),
+    ToolCall("browser-02", "browser", "Open https://www.python.org in the browser.",
+             "browser_navigate", "python.org"),
+    ToolCall("browser-03", "browser", "Open https://www.wikipedia.org in the browser.",
+             "browser_navigate", "wikipedia.org"),
+    ToolCall("browser-04", "browser", "Navigate the browser to https://example.org.",
+             "browser_navigate", "example.org"),
+    ToolCall("browser-05", "browser", "Go to https://httpbin.org/forms/post in the browser.",
+             "browser_navigate", "httpbin.org/forms/post"),
+    ToolCall("browser-06", "browser", "Open https://www.iana.org/domains/reserved in the browser.",
+             "browser_navigate", "iana.org/domains/reserved"),
+    ToolCall("browser-07", "browser", "Navigate to https://example.net in the browser.",
+             "browser_navigate", "example.net"),
+    ToolCall("browser-08", "browser", "Open https://developer.mozilla.org in the browser.",
+             "browser_navigate", "developer.mozilla.org"),
+    ToolCall("browser-09", "browser", "Navigate the browser to https://www.rfc-editor.org.",
+             "browser_navigate", "rfc-editor.org"),
+    ToolCall("browser-10", "browser", "Open https://www.gnu.org in the browser.",
+             "browser_navigate", "gnu.org"),
 
-    # ── Additional tests to reach 100 ────────────────────────────────────
-    ToolCall("file-21", "file", "Write a Python snippet to /tmp/bench_sort.py that sorts [3,1,2].",
-             "write_file", "bench_sort"),
-    ToolCall("file-22", "file", "Read /tmp/bench_sort.py back and confirm it exists.",
-             "read_file", "bench_sort"),
-    ToolCall("file-23", "file", "Search for 'class' in all .py files in the benchmarks directory.",
-             "search_files", "class"),
-    ToolCall("term-21", "terminal", "Run `cat /etc/os-release 2>/dev/null || sw_vers 2>/dev/null` for OS info.",
-             "terminal", "os"),
-    ToolCall("term-22", "terminal", "Run `nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null` for CPU count.",
-             "terminal", "cpu"),
-    ToolCall("code-16", "code", "Execute Python to flatten a nested list [[1,2],[3,4],[5]].",
-             "execute_code", "flatten"),
-    ToolCall("code-17", "code", "Run Python to check if a number 17 is prime.",
-             "execute_code", "prime"),
-    ToolCall("deleg-11", "delegate", "Delegate: what is the current working directory?",
-             "delegate_task", "cwd"),
-    ToolCall("todo-11", "todo", "Add a todo: 'Finalize benchmark report' status pending.",
-             "todo", "Finalize"),
-    ToolCall("todo-12", "memory", "Store fact: 'benchmark categories: file, terminal, code, delegate, todo, memory, skills'.",
-             "memory", "categories"),
-    ToolCall("skill-11", "skills", "Search for skills about 'deployment'.",
-             "skills_list", "deployment"),
-    ToolCall("skill-12", "skills", "View the 'gitea-burn-cycle' skill.",
-             "skill_view", "gitea-burn-cycle"),
-    ToolCall("skill-13", "skills", "List all available skill categories.",
-             "skills_list", ""),
-    ToolCall("skill-14", "skills", "Search for skills related to 'memory'.",
-             "skills_list", "memory"),
-    ToolCall("skill-15", "skills", "View the 'mimo-swarm' skill.",
-             "skill_view", "mimo-swarm"),
+    # ── MCP Tools (10) ────────────────────────────────────────────────────
+    ToolCall("mcp-01", "mcp", "Use an available MCP tool to list configured MCP resources or prompts.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-02", "mcp", "Use an MCP tool to inspect available resources on a configured server.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-03", "mcp", "Use an MCP tool to read a resource from any configured MCP server.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-04", "mcp", "Use an MCP tool to list prompts from any configured MCP server.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-05", "mcp", "Use an available MCP tool and report what it returns.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-06", "mcp", "Call any safe MCP tool that is currently available and summarize the response.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-07", "mcp", "Use one configured MCP tool to enumerate data or capabilities.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-08", "mcp", "Use an MCP tool to fetch a small piece of data from a connected server.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-09", "mcp", "Invoke an available MCP tool and show the structured result.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-10", "mcp", "Use a currently available MCP tool rather than a built-in Hermes tool.",
+             "", "", expected_tool_prefix="mcp_"),
 ]
 # fmt: on
 
+DEFAULT_COMPARE_MODELS = [
+    "nous:gia-3/gemma-4-31b",
+    "gemini:gemma-4-26b-it",
+    "nous:mimo-v2-pro",
+]
+
+ISSUE_796_CATEGORY_COUNTS = {
+    "file": 20,
+    "terminal": 20,
+    "web": 15,
+    "code": 15,
+    "browser": 10,
+    "delegate": 10,
+    "mcp": 10,
+}
+
+
+def suite_category_counts() -> dict[str, int]:
+    counts: dict[str, int] = {}
+    for tc in SUITE:
+        counts[tc.category] = counts.get(tc.category, 0) + 1
+    return counts
+
 
 # ---------------------------------------------------------------------------
 # Runner
@@ -278,9 +305,17 @@ class CallResult:
     expected_tool: str
     success: bool
     tool_called: Optional[str] = None
+    schema_ok: bool = False
     tool_args_valid: bool = False
     execution_ok: bool = False
+    tool_count: int = 0
+    parallel_ok: bool = False
     latency_s: float = 0.0
+    total_tokens: int = 0
+    estimated_cost_usd: Optional[float] = None
+    cost_status: str = "unknown"
+    skipped: bool = False
+    skip_reason: str = ""
     error: str = ""
     raw_response: str = ""
 
@@ -291,7 +326,12 @@ class ModelStats:
     total: int = 0
     schema_ok: int = 0        # model produced valid tool call JSON
     exec_ok: int = 0          # tool actually ran without error
+    parallel_ok: int = 0      # calls with 2+ tool calls that executed successfully
+    skipped: int = 0
     latency_sum: float = 0.0
+    total_tokens: int = 0
+    total_cost_usd: float = 0.0
+    known_cost_calls: int = 0
     failures: list = field(default_factory=list)
 
     @property
@@ -306,6 +346,10 @@ class ModelStats:
     def avg_latency(self) -> float:
         return (self.latency_sum / self.total) if self.total else 0
 
+    @property
+    def avg_cost_usd(self) -> Optional[float]:
+        return (self.total_cost_usd / self.known_cost_calls) if self.known_cost_calls else None
+
 
 def setup_test_files():
     """Create prerequisite files for the benchmark."""
@@ -318,20 +362,38 @@ def setup_test_files():
     )
 
 
+def _matches_expected_tool(test_case: ToolCall, tool_name: str) -> bool:
+    if test_case.expected_tool and tool_name == test_case.expected_tool:
+        return True
+    if test_case.expected_tool_prefix and tool_name.startswith(test_case.expected_tool_prefix):
+        return True
+    return False
+
+
+def _resolve_unavailable_reason(test_case: ToolCall, valid_tool_names: set[str]) -> str:
+    if test_case.expected_tool and test_case.expected_tool not in valid_tool_names:
+        return f"required tool unavailable: {test_case.expected_tool}"
+    if test_case.expected_tool_prefix and not any(
+        name.startswith(test_case.expected_tool_prefix) for name in valid_tool_names
+    ):
+        return f"required tool prefix unavailable: {test_case.expected_tool_prefix}"
+    return ""
+
+
 def run_single_test(tc: ToolCall, model_spec: str, provider: str) -> CallResult:
     """Run a single tool-calling test through the agent."""
-    from run_agent import AIAgent
-
     result = CallResult(
         test_id=tc.id,
         category=tc.category,
         model=model_spec,
         prompt=tc.prompt,
-        expected_tool=tc.expected_tool,
+        expected_tool=tc.expected_tool or tc.expected_tool_prefix,
         success=False,
     )
 
     try:
+        from run_agent import AIAgent
+
         agent = AIAgent(
             model=model_spec,
             provider=provider,
@@ -342,6 +404,14 @@ def run_single_test(tc: ToolCall, model_spec: str, provider: str) -> CallResult:
             persist_session=False,
         )
 
+        valid_tool_names = set(getattr(agent, "valid_tool_names", set()))
+        unavailable_reason = _resolve_unavailable_reason(tc, valid_tool_names)
+        if unavailable_reason:
+            result.skipped = True
+            result.skip_reason = unavailable_reason
+            result.error = unavailable_reason
+            return result
+
         t0 = time.time()
         conv = agent.run_conversation(
             user_message=tc.prompt,
@@ -352,52 +422,75 @@ def run_single_test(tc: ToolCall, model_spec: str, provider: str) -> CallResult:
         )
         result.latency_s = round(time.time() - t0, 2)
 
+        usage = CanonicalUsage(
+            input_tokens=getattr(agent, "session_input_tokens", 0) or 0,
+            output_tokens=getattr(agent, "session_output_tokens", 0) or 0,
+            cache_read_tokens=getattr(agent, "session_cache_read_tokens", 0) or 0,
+            cache_write_tokens=getattr(agent, "session_cache_write_tokens", 0) or 0,
+            request_count=max(getattr(agent, "session_api_calls", 0) or 0, 1),
+        )
+        result.total_tokens = usage.total_tokens
+        billed_model = model_spec.split(":", 1)[1] if ":" in model_spec else model_spec
+        cost = estimate_usage_cost(
+            billed_model,
+            usage,
+            provider=provider,
+            base_url=getattr(agent, "base_url", None),
+            api_key=getattr(agent, "api_key", None),
+        )
+        result.cost_status = cost.status
+        result.estimated_cost_usd = float(cost.amount_usd) if cost.amount_usd is not None else None
+
         messages = conv.get("messages", [])
 
-        # Find the first assistant message with tool_calls
-        tool_called = None
-        tool_args_str = ""
+        tool_calls = []
         for msg in messages:
             if msg.get("role") == "assistant" and msg.get("tool_calls"):
-                for tc_item in msg["tool_calls"]:
-                    fn = tc_item.get("function", {})
-                    tool_called = fn.get("name", "")
-                    tool_args_str = fn.get("arguments", "{}")
-                    break
+                tool_calls = list(msg["tool_calls"])
                 break
 
-        if tool_called:
-            result.tool_called = tool_called
-            result.schema_ok = True
+        if tool_calls:
+            result.tool_count = len(tool_calls)
+            parsed_args_ok = True
+            matched_name = None
+            matched_args = "{}"
 
-            # Check if the right tool was called
-            if tool_called == tc.expected_tool:
-                result.success = True
+            for tc_item in tool_calls:
+                fn = tc_item.get("function", {})
+                tool_name = fn.get("name", "")
+                tool_args = fn.get("arguments", "{}")
+                try:
+                    json.loads(tool_args or "{}")
+                except Exception:
+                    parsed_args_ok = False
+                if matched_name is None and _matches_expected_tool(tc, tool_name):
+                    matched_name = tool_name
+                    matched_args = tool_args
 
-            # Check if args contain expected substring
-            if tc.expected_params_check:
-                result.tool_args_valid = tc.expected_params_check in tool_args_str
-            else:
-                result.tool_args_valid = True
+            result.schema_ok = parsed_args_ok
+            result.tool_called = matched_name or tool_calls[0].get("function", {}).get("name", "")
+
+            if matched_name:
+                result.tool_args_valid = (
+                    tc.expected_params_check in matched_args if tc.expected_params_check else True
+                )
+                result.success = result.schema_ok and result.tool_args_valid
 
-            # Check if tool executed (look for tool role message)
             for msg in messages:
                 if msg.get("role") == "tool":
                     content = msg.get("content", "")
-                    if content and "error" not in content.lower()[:50]:
+                    if content:
                         result.execution_ok = True
                         break
-                    elif content:
-                        result.execution_ok = True  # got a response, even if error
-                        break
+
+            result.parallel_ok = result.tool_count > 1 and result.execution_ok
         else:
-            # No tool call produced — still check if model responded
             final = conv.get("final_response", "")
             result.raw_response = final[:200] if final else ""
 
     except Exception as e:
         result.error = f"{type(e).__name__}: {str(e)[:200]}"
-        result.latency_s = round(time.time() - t0, 2) if 't0' in dir() else 0
+        result.latency_s = round(time.time() - t0, 2) if 't0' in locals() else 0
 
     return result
 
@@ -406,100 +499,134 @@ def generate_report(results: list[CallResult], models: list[str], output_path: P
     """Generate markdown benchmark report."""
     now = datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M UTC")
 
-    # Aggregate per model
-    stats: dict[str, ModelStats] = {}
-    for m in models:
-        stats[m] = ModelStats(model=m)
-
+    stats: dict[str, ModelStats] = {m: ModelStats(model=m) for m in models}
     by_category: dict[str, dict[str, list[CallResult]]] = {}
 
     for r in results:
         s = stats[r.model]
         s.total += 1
-        s.schema_ok += int(r.schema_ok)
-        s.exec_ok += int(r.execution_ok)
         s.latency_sum += r.latency_s
-        if not r.success:
-            s.failures.append(r)
+        s.total_tokens += r.total_tokens
+        if r.estimated_cost_usd is not None:
+            s.total_cost_usd += r.estimated_cost_usd
+            s.known_cost_calls += 1
+        if r.skipped:
+            s.skipped += 1
+        else:
+            s.schema_ok += int(r.schema_ok)
+            s.exec_ok += int(r.execution_ok)
+            s.parallel_ok += int(r.parallel_ok)
+            if not r.success:
+                s.failures.append(r)
 
         by_category.setdefault(r.category, {}).setdefault(r.model, []).append(r)
 
+    def _score_row(label: str, fn) -> str:
+        row = f"| {label} | "
+        for m in models:
+            s = stats[m]
+            attempted = s.total - s.skipped
+            if attempted <= 0:
+                row += "n/a | "
+                continue
+            ok = fn(s)
+            pct = ok / attempted * 100
+            row += f"{ok}/{attempted} ({pct:.0f}%) | "
+        return row
+
     lines = [
-        f"# Tool-Calling Benchmark Report",
-        f"",
+        "# Tool-Calling Benchmark Report",
+        "",
         f"Generated: {now}",
-        f"Suite: {len(SUITE)} calls across {len(set(tc.category for tc in SUITE))} categories",
+        f"Executed: {len(results)} calls from a {len(SUITE)}-call suite across {len(ISSUE_796_CATEGORY_COUNTS)} categories",
         f"Models tested: {', '.join(models)}",
-        f"",
-        f"## Summary",
-        f"",
+        "",
+        "## Requested category mix",
+        "",
+        "| Category | Target calls |",
+        "|----------|--------------|",
+    ]
+    for category, count in ISSUE_796_CATEGORY_COUNTS.items():
+        lines.append(f"| {category} | {count} |")
+
+    lines.extend([
+        "",
+        "## Summary",
+        "",
         f"| Metric | {' | '.join(models)} |",
         f"|--------|{'|'.join('---------' for _ in models)}|",
-    ]
+        _score_row("Schema parse success", lambda s: s.schema_ok),
+        _score_row("Tool execution success", lambda s: s.exec_ok),
+        _score_row("Parallel tool success", lambda s: s.parallel_ok),
+    ])
 
-    # Schema parse success
-    row = "| Schema parse success | "
-    for m in models:
-        s = stats[m]
-        row += f"{s.schema_ok}/{s.total} ({s.schema_pct:.0f}%) | "
-    lines.append(row)
-
-    # Tool execution success
-    row = "| Tool execution success | "
-    for m in models:
-        s = stats[m]
-        row += f"{s.exec_ok}/{s.total} ({s.exec_pct:.0f}%) | "
-    lines.append(row)
-
-    # Correct tool selected
-    row = "| Correct tool selected | "
-    for m in models:
-        s = stats[m]
-        correct = sum(1 for r in results if r.model == m and r.success)
-        pct = (correct / s.total * 100) if s.total else 0
-        row += f"{correct}/{s.total} ({pct:.0f}%) | "
-    lines.append(row)
-
-    # Avg latency
     row = "| Avg latency (s) | "
     for m in models:
-        s = stats[m]
-        row += f"{s.avg_latency:.2f} | "
+        row += f"{stats[m].avg_latency:.2f} | "
     lines.append(row)
 
+    row = "| Avg tokens per call | "
+    for m in models:
+        total = stats[m].total
+        avg_tokens = stats[m].total_tokens / total if total else 0
+        row += f"{avg_tokens:.1f} | "
+    lines.append(row)
+
+    row = "| Avg token cost per call (USD) | "
+    for m in models:
+        avg_cost = stats[m].avg_cost_usd
+        row += (f"{avg_cost:.6f} | " if avg_cost is not None else "n/a | ")
+    lines.append(row)
+
+    row = "| Skipped / unavailable | "
+    for m in models:
+        s = stats[m]
+        row += f"{s.skipped}/{s.total} | "
+    lines.append(row)
     lines.append("")
 
-    # Per-category breakdown
-    lines.append("## Per-Category Breakdown")
+    lines.append("## Per-category breakdown")
     lines.append("")
-
     for cat in sorted(by_category.keys()):
         lines.append(f"### {cat.title()}")
         lines.append("")
         lines.append(f"| Metric | {' | '.join(models)} |")
         lines.append(f"|--------|{'|'.join('---------' for _ in models)}|")
-
-        cat_data = by_category[cat]
         for metric_name, fn in [
             ("Schema OK", lambda r: r.schema_ok),
             ("Exec OK", lambda r: r.execution_ok),
+            ("Parallel OK", lambda r: r.parallel_ok),
             ("Correct tool", lambda r: r.success),
         ]:
             row = f"| {metric_name} | "
             for m in models:
-                results_m = cat_data.get(m, [])
-                total = len(results_m)
-                ok = sum(1 for r in results_m if fn(r))
-                pct = (ok / total * 100) if total else 0
-                row += f"{ok}/{total} ({pct:.0f}%) | "
+                results_m = by_category[cat].get(m, [])
+                attempted = [r for r in results_m if not r.skipped]
+                if not attempted:
+                    row += "n/a | "
+                    continue
+                ok = sum(1 for r in attempted if fn(r))
+                pct = ok / len(attempted) * 100
+                row += f"{ok}/{len(attempted)} ({pct:.0f}%) | "
             lines.append(row)
 
+        row = "| Avg tokens | "
+        for m in models:
+            results_m = by_category[cat].get(m, [])
+            avg_tokens = sum(r.total_tokens for r in results_m) / len(results_m) if results_m else 0
+            row += f"{avg_tokens:.1f} | "
+        lines.append(row)
+
+        row = "| Skipped | "
+        for m in models:
+            results_m = by_category[cat].get(m, [])
+            skipped = sum(1 for r in results_m if r.skipped)
+            row += f"{skipped}/{len(results_m)} | "
+        lines.append(row)
         lines.append("")
 
-    # Failure analysis
-    lines.append("## Failure Analysis")
+    lines.append("## Failure analysis")
     lines.append("")
-
     any_failures = False
     for m in models:
         s = stats[m]
@@ -514,28 +641,40 @@ def generate_report(results: list[CallResult], models: list[str], output_path: P
                 err = r.error or "wrong tool"
                 lines.append(f"| {r.test_id} | {r.category} | {r.expected_tool} | {got} | {err[:60]} |")
             lines.append("")
-
     if not any_failures:
-        lines.append("No failures detected.")
+        lines.append("No model failures detected.")
         lines.append("")
 
-    # Raw results JSON
-    lines.append("## Raw Results")
+    skipped_results = [r for r in results if r.skipped]
+    lines.append("## Skipped / unavailable cases")
+    lines.append("")
+    if skipped_results:
+        lines.append("| Test | Model | Category | Reason |")
+        lines.append("|------|-------|----------|--------|")
+        for r in skipped_results:
+            lines.append(f"| {r.test_id} | {r.model} | {r.category} | {r.skip_reason[:80]} |")
+    else:
+        lines.append("No cases were skipped.")
+    lines.append("")
+
+    lines.append("## Raw results")
     lines.append("")
     lines.append("```json")
     lines.append(json.dumps([asdict(r) for r in results], indent=2, default=str))
     lines.append("```")
 
     report = "\n".join(lines)
-    output_path.write_text(report)
+    output_path.write_text(report, encoding="utf-8")
     return report
 
 
 def main():
     parser = argparse.ArgumentParser(description="Tool-calling benchmark")
     parser.add_argument("--models", nargs="+",
-                        default=["nous:gia-3/gemma-4-31b", "nous:mimo-v2-pro"],
+                        default=list(DEFAULT_COMPARE_MODELS),
                         help="Model specs to test (provider:model)")
+    parser.add_argument("--compare", action="store_true",
+                        help="Use the issue #796 default comparison set")
     parser.add_argument("--limit", type=int, default=0,
                         help="Run only first N tests (0 = all)")
     parser.add_argument("--category", type=str, default="",
@@ -546,6 +685,9 @@ def main():
                         help="Print test cases without running them")
     args = parser.parse_args()
 
+    if args.compare:
+        args.models = list(DEFAULT_COMPARE_MODELS)
+
     # Filter suite
     suite = SUITE[:]
     if args.category:

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_tool_call_benchmark.py

@@ -0,0 +1,115 @@
+"""Tests for Issue #796 tool-calling benchmark coverage and reporting."""
+
+import sys
+from pathlib import Path
+from types import SimpleNamespace
+from unittest.mock import patch
+
+sys.path.insert(0, str(Path(__file__).parent.parent / "benchmarks"))
+
+from tool_call_benchmark import (  # noqa: E402
+    CallResult,
+    DEFAULT_COMPARE_MODELS,
+    ISSUE_796_CATEGORY_COUNTS,
+    ToolCall,
+    generate_report,
+    run_single_test,
+    suite_category_counts,
+)
+
+
+def test_suite_counts_match_issue_796_distribution():
+    counts = suite_category_counts()
+    assert counts == ISSUE_796_CATEGORY_COUNTS
+    assert sum(counts.values()) == 100
+
+
+def test_default_compare_models_cover_issue_796_lanes():
+    assert len(DEFAULT_COMPARE_MODELS) == 3
+    assert any("gemma-4-31b" in spec for spec in DEFAULT_COMPARE_MODELS)
+    assert any("gemma-4-26b" in spec for spec in DEFAULT_COMPARE_MODELS)
+    assert any("mimo-v2-pro" in spec for spec in DEFAULT_COMPARE_MODELS)
+
+
+def test_generate_report_includes_parallel_and_cost_metrics(tmp_path):
+    output_path = tmp_path / "report.md"
+    results = [
+        CallResult(
+            test_id="file-01",
+            category="file",
+            model="gemma-4-31b",
+            prompt="Read the file.",
+            expected_tool="read_file",
+            success=True,
+            tool_called="read_file",
+            schema_ok=True,
+            tool_args_valid=True,
+            execution_ok=True,
+            tool_count=2,
+            parallel_ok=True,
+            latency_s=1.25,
+            total_tokens=123,
+            estimated_cost_usd=0.0012,
+            cost_status="estimated",
+        ),
+        CallResult(
+            test_id="web-01",
+            category="web",
+            model="mimo-v2-pro",
+            prompt="Search the web.",
+            expected_tool="web_search",
+            success=False,
+            tool_called="web_search",
+            schema_ok=True,
+            tool_args_valid=False,
+            execution_ok=False,
+            tool_count=1,
+            parallel_ok=False,
+            latency_s=2.5,
+            error="bad args",
+            total_tokens=456,
+            estimated_cost_usd=None,
+            cost_status="unknown",
+            skipped=True,
+            skip_reason="web_search unavailable",
+        ),
+    ]
+
+    report = generate_report(results, ["gemma-4-31b", "mimo-v2-pro"], output_path)
+
+    assert output_path.exists()
+    assert "Parallel tool success" in report
+    assert "Avg token cost per call (USD)" in report
+    assert "Skipped / unavailable" in report
+    assert "Requested category mix" in report
+
+
+def test_run_single_test_skips_when_expected_tool_unavailable():
+    class FakeAgent:
+        def __init__(self, *args, **kwargs):
+            self.valid_tool_names = {"read_file", "terminal"}
+            self.session_input_tokens = 0
+            self.session_output_tokens = 0
+            self.session_cache_read_tokens = 0
+            self.session_cache_write_tokens = 0
+            self.session_api_calls = 0
+            self.base_url = ""
+            self.api_key = None
+
+        def run_conversation(self, *args, **kwargs):
+            raise AssertionError("run_conversation should not be called for unavailable tools")
+
+    tc = ToolCall(
+        id="mcp-01",
+        category="mcp",
+        prompt="Use an MCP tool to list resources.",
+        expected_tool="",
+        expected_tool_prefix="mcp_",
+    )
+
+    with patch.dict(sys.modules, {"run_agent": SimpleNamespace(AIAgent=FakeAgent)}):
+        result = run_single_test(tc, "gemini:gemma-4-31b-it", "gemini")
+
+    assert result.skipped is True
+    assert "mcp_" in result.skip_reason
+    assert result.success is False