test: add unit tests for tool calling test runner (#101)

benchmarks/bonsai-tool-calling.md

@@ -0,0 +1,50 @@
+# Tool Calling Viability: Bonsai 1-Bit Models
+
+**Epic**: #99 (1-Bit Models + Edge)
+**Date**: TBD (run benchmarks/test_tool_calling.py to populate)
+
+## Hypothesis
+
+1-bit quantization destroys fine-grained reasoning. Tool calling (precise JSON output) may be impossible at Q1_0. But worth testing — the field is moving fast.
+
+## Models to Test
+
+| Model | Size | Quant | Source |
+|-------|------|-------|--------|
+| Bonsai-1.7B | 1.7B | Q1_0 | prism-ml/Bonsai-1.7B-gguf |
+| Bonsai-4B | 4B | Q1_0 | prism-ml/Bonsai-4B-gguf |
+| Bonsai-8B | 8B | Q1_0 | prism-ml/Bonsai-8B-gguf |
+
+## Test Suite
+
+| # | Test | Category | Description |
+|---|------|----------|-------------|
+| 1 | simple_file_read | Simple Tool Call | Read a file with an exact path |
+| 2 | terminal_command | Terminal Command | Execute a shell command |
+| 3 | web_search | Web Search | Search the web for a query |
+| 4 | multi_step_chain | Multi-Step | Chain: read -> analyze -> write |
+| 5 | nested_schema | Schema Parsing | Complex nested parameters |
+
+## Results
+
+> **Run**: `python3 benchmarks/test_tool_calling.py --model bonsai-1.7b --output benchmarks/bonsai-tool-calling.md`
+
+| Test | Bonsai-1.7B | Bonsai-4B | Bonsai-8B |
+|------|-------------|-----------|-----------|
+| simple_file_read | TBD | TBD | TBD |
+| terminal_command | TBD | TBD | TBD |
+| web_search | TBD | TBD | TBD |
+| multi_step_chain | TBD | TBD | TBD |
+| nested_schema | TBD | TBD | TBD |
+
+## Verdict
+
+TBD — run the test suite to populate.
+
+## Failure Modes (if any)
+
+TBD — document specific failure patterns observed.
+
+## Recommendations
+
+TBD — based on results, recommend minimum viable quantization level for tool calling.

benchmarks/test_tool_calling.py

@@ -0,0 +1,435 @@
+#!/usr/bin/env python3
+"""
+Tool Calling Viability Test for 1-Bit / Edge Models (Issue #101)
+
+Tests whether Bonsai 1-bit models (or any small model) can produce
+valid tool calls via Ollama or llama-server API.
+
+Test suite (5 categories):
+  1. Simple tool call: file read with exact path
+  2. Terminal command execution
+  3. Web search
+  4. Multi-step: read file -> analyze -> write result
+  5. Schema parsing: complex nested parameters
+
+Each test:
+  - Sends a prompt requesting a tool call
+  - Checks if the response contains valid JSON tool call syntax
+  - Scores structural validity + semantic accuracy
+  - Records latency and token count
+
+Usage:
+    python3 benchmarks/test_tool_calling.py --model bonsai-1.7b
+    python3 benchmarks/test_tool_calling.py --model qwen3.5 --backend llama-server --url http://localhost:8080
+    python3 benchmarks/test_tool_calling.py --model bonsai-1.7b --output benchmarks/bonsai-tool-calling.md
+"""
+
+import argparse
+import json
+import os
+import re
+import sys
+import time
+from datetime import datetime, timezone
+from typing import Optional
+
+try:
+    import requests
+except ImportError:
+    print("Error: pip install requests", file=sys.stderr)
+    sys.exit(1)
+
+
+# ── Tool call test definitions ────────────────────────────────────────
+
+TESTS = [
+    {
+        "id": "simple_file_read",
+        "category": "Simple Tool Call",
+        "description": "Read a file with an exact path",
+        "prompt": (
+            "You have access to a tool called read_file. "
+            "Call it to read /etc/hostname. "
+            "Respond ONLY with a JSON tool call in this exact format:\n"
+            '{"name": "read_file", "arguments": {"path": "/etc/hostname"}}'
+        ),
+        "validate": lambda resp: _has_json_tool_call(resp, "read_file", {"path": "/etc/hostname"}),
+        "scoring": "structural",  # Can we parse the JSON at all?
+    },
+    {
+        "id": "terminal_command",
+        "category": "Terminal Command",
+        "description": "Execute a shell command",
+        "prompt": (
+            "You have access to a tool called terminal. "
+            "Call it to run the command: echo hello world. "
+            "Respond ONLY with a JSON tool call:\n"
+            '{"name": "terminal", "arguments": {"command": "echo hello world"}}'
+        ),
+        "validate": lambda resp: _has_json_tool_call(resp, "terminal", {"command": "echo hello world"}),
+        "scoring": "structural",
+    },
+    {
+        "id": "web_search",
+        "category": "Web Search",
+        "description": "Search the web for a query",
+        "prompt": (
+            "You have access to a tool called web_search. "
+            "Search for: what is quantization in machine learning. "
+            "Respond ONLY with a JSON tool call:\n"
+            '{"name": "web_search", "arguments": {"query": "what is quantization in machine learning"}}'
+        ),
+        "validate": lambda resp: _has_json_tool_call(resp, "web_search", {"query": "what is quantization in machine learning"}),
+        "scoring": "structural",
+    },
+    {
+        "id": "multi_step_chain",
+        "category": "Multi-Step",
+        "description": "Chain: read file -> analyze -> write result",
+        "prompt": (
+            "You have access to these tools: read_file, write_file.\n"
+            "Task: Read /tmp/input.txt, count the words, then write the count to /tmp/count.txt.\n"
+            "First, call read_file on /tmp/input.txt. "
+            "Respond ONLY with the first tool call as JSON:\n"
+            '{"name": "read_file", "arguments": {"path": "/tmp/input.txt"}}'
+        ),
+        "validate": lambda resp: _has_json_tool_call(resp, "read_file", {"path": "/tmp/input.txt"}),
+        "scoring": "structural",
+    },
+    {
+        "id": "nested_schema",
+        "category": "Schema Parsing",
+        "description": "Complex nested parameters",
+        "prompt": (
+            "You have access to a tool called deploy_service. "
+            "Deploy a service with:\n"
+            '- name: "api-gateway"\n'
+            '- replicas: 3\n'
+            '- env: {"PORT": 8080, "NODE_ENV": "production"}\n'
+            '- resources: {"cpu": "500m", "memory": "256Mi"}\n\n'
+            "Respond ONLY with a JSON tool call:\n"
+            '{"name": "deploy_service", "arguments": {"name": "api-gateway", "replicas": 3, '
+            '"env": {"PORT": 8080, "NODE_ENV": "production"}, '
+            '"resources": {"cpu": "500m", "memory": "256Mi"}}}'
+        ),
+        "validate": lambda resp: _has_nested_tool_call(resp),
+        "scoring": "semantic",  # Needs correct nested structure
+    },
+]
+
+
+# ── Validation helpers ────────────────────────────────────────────────
+
+def _extract_json(text: str) -> Optional[dict]:
+    """Try to extract a JSON object from text."""
+    # Try direct parse
+    text = text.strip()
+    try:
+        obj = json.loads(text)
+        if isinstance(obj, dict):
+            return obj
+    except json.JSONDecodeError:
+        pass
+
+    # Try finding JSON in code blocks
+    code_block = re.search(r"```(?:json)?\s*({.*?})\s*```", text, re.DOTALL)
+    if code_block:
+        try:
+            return json.loads(code_block.group(1))
+        except json.JSONDecodeError:
+            pass
+
+    # Try finding any JSON object
+    json_match = re.search(r"({[^{}]*(?:{[^{}]*}[^{}]*)*})", text)
+    if json_match:
+        try:
+            return json.loads(json_match.group(1))
+        except json.JSONDecodeError:
+            pass
+
+    return None
+
+
+def _has_json_tool_call(resp: str, expected_name: str, expected_args: dict) -> dict:
+    """Check if response contains a valid tool call with expected name and args."""
+    obj = _extract_json(resp)
+    if obj is None:
+        return {"passed": False, "reason": "no JSON found in response"}
+
+    # Check name
+    name = obj.get("name", obj.get("function", {}).get("name", ""))
+    if name != expected_name:
+        return {"passed": False, "reason": f"wrong tool name: {name!r}, expected {expected_name!r}"}
+
+    # Check arguments exist
+    args = obj.get("arguments", obj.get("function", {}).get("arguments", obj.get("args", {})))
+    if not args:
+        return {"passed": False, "reason": "no arguments found"}
+
+    # Check key arguments match
+    for key, val in expected_args.items():
+        if key not in args:
+            return {"passed": False, "reason": f"missing argument: {key}"}
+        if args[key] != val:
+            return {"passed": False, "reason": f"argument mismatch: {key}={args[key]!r}, expected {val!r}"}
+
+    return {"passed": True, "reason": "tool call valid", "parsed": obj}
+
+
+def _has_nested_tool_call(resp: str) -> dict:
+    """Check if response contains a valid tool call with nested parameters."""
+    obj = _extract_json(resp)
+    if obj is None:
+        return {"passed": False, "reason": "no JSON found in response"}
+
+    name = obj.get("name", obj.get("function", {}).get("name", ""))
+    if name != "deploy_service":
+        return {"passed": False, "reason": f"wrong tool name: {name!r}"}
+
+    args = obj.get("arguments", obj.get("function", {}).get("arguments", obj.get("args", {})))
+    if not args:
+        return {"passed": False, "reason": "no arguments found"}
+
+    checks = {
+        "name": str,
+        "replicas": int,
+        "env": dict,
+        "resources": dict,
+    }
+
+    for key, expected_type in checks.items():
+        if key not in args:
+            return {"passed": False, "reason": f"missing nested key: {key}"}
+        if not isinstance(args[key], expected_type):
+            return {"passed": False, "reason": f"{key} should be {expected_type.__name__}, got {type(args[key]).__name__}"}
+
+    # Check env has PORT
+    env = args.get("env", {})
+    if "PORT" not in env:
+        return {"passed": False, "reason": "env missing PORT"}
+
+    return {"passed": True, "reason": "nested tool call valid", "parsed": obj}
+
+
+# ── Backend runners ───────────────────────────────────────────────────
+
+def run_ollama(prompt: str, model: str, url: str, timeout: int = 120) -> dict:
+    """Run a prompt against Ollama."""
+    api_url = f"{url.rstrip('/')}/api/generate"
+    start = time.time()
+    try:
+        resp = requests.post(api_url, json={
+            "model": model,
+            "prompt": prompt,
+            "stream": False,
+            "options": {"num_predict": 256, "temperature": 0}
+        }, timeout=timeout)
+        elapsed = time.time() - start
+        resp.raise_for_status()
+        data = resp.json()
+        return {
+            "response": data.get("response", ""),
+            "latency_s": round(elapsed, 3),
+            "tokens": data.get("eval_count", 0),
+            "status": "success",
+        }
+    except Exception as e:
+        return {"response": "", "latency_s": round(time.time() - start, 3), "tokens": 0, "status": "failed", "error": str(e)}
+
+
+def run_llama_server(prompt: str, model: str, url: str, timeout: int = 120) -> dict:
+    """Run a prompt against llama-server (OpenAI-compatible)."""
+    api_url = f"{url.rstrip('/')}/v1/chat/completions"
+    start = time.time()
+    try:
+        resp = requests.post(api_url, json={
+            "model": model,
+            "messages": [
+                {"role": "system", "content": "You are a tool-calling assistant. Respond ONLY with JSON tool calls."},
+                {"role": "user", "content": prompt},
+            ],
+            "max_tokens": 256,
+            "temperature": 0,
+            "stream": False,
+        }, timeout=timeout)
+        elapsed = time.time() - start
+        resp.raise_for_status()
+        data = resp.json()
+        content = data.get("choices", [{}])[0].get("message", {}).get("content", "")
+        usage = data.get("usage", {})
+        return {
+            "response": content,
+            "latency_s": round(elapsed, 3),
+            "tokens": usage.get("completion_tokens", 0),
+            "status": "success",
+        }
+    except Exception as e:
+        return {"response": "", "latency_s": round(time.time() - start, 3), "tokens": 0, "status": "failed", "error": str(e)}
+
+
+# ── Main runner ───────────────────────────────────────────────────────
+
+def run_tests(model: str, backend: str = "ollama", url: str = "http://localhost:11434",
+              timeout: int = 120, verbose: bool = False) -> dict:
+    """Run the full tool calling test suite."""
+    runner_fn = run_ollama if backend == "ollama" else run_llama_server
+
+    results = {
+        "model": model,
+        "backend": backend,
+        "url": url,
+        "timestamp": datetime.now(timezone.utc).isoformat(),
+        "tests": [],
+        "summary": {"total": 0, "passed": 0, "failed": 0, "errors": 0},
+    }
+
+    print(f"Testing tool calling on: {model} ({backend})\n")
+
+    for test in TESTS:
+        print(f"  [{test['id']}] {test['description']}...", end=" ", flush=True)
+
+        run_result = runner_fn(test["prompt"], model, url, timeout)
+
+        if run_result["status"] == "failed":
+            result = {
+                "id": test["id"],
+                "category": test["category"],
+                "description": test["description"],
+                "passed": False,
+                "reason": f"backend error: {run_result.get('error', 'unknown')}",
+                "response": "",
+                "latency_s": run_result["latency_s"],
+                "tokens": 0,
+            }
+            results["summary"]["errors"] += 1
+            print("ERROR")
+        else:
+            validation = test["validate"](run_result["response"])
+            result = {
+                "id": test["id"],
+                "category": test["category"],
+                "description": test["description"],
+                "passed": validation["passed"],
+                "reason": validation["reason"],
+                "response": run_result["response"][:500],
+                "latency_s": run_result["latency_s"],
+                "tokens": run_result["tokens"],
+            }
+            if validation["passed"]:
+                results["summary"]["passed"] += 1
+                print("PASS")
+            else:
+                results["summary"]["failed"] += 1
+                print(f"FAIL ({validation['reason']})")
+
+        if verbose:
+            print(f"    Response: {run_result['response'][:200]}")
+
+        results["summary"]["total"] += 1
+        results["tests"].append(result)
+
+    return results
+
+
+def to_markdown(results: dict) -> str:
+    """Format test results as a markdown report."""
+    lines = []
+    lines.append(f"# Tool Calling Viability: {results['model']}")
+    lines.append("")
+    lines.append(f"**Date**: {results['timestamp']}")
+    lines.append(f"**Backend**: {results['backend']} ({results['url']})")
+    lines.append(f"**Model**: {results['model']}")
+    lines.append("")
+
+    s = results["summary"]
+    pass_rate = s["passed"] / s["total"] * 100 if s["total"] > 0 else 0
+    lines.append(f"## Summary: {s['passed']}/{s['total']} passed ({pass_rate:.0f}%)")
+    lines.append("")
+    lines.append(f"| Metric | Value |")
+    lines.append(f"|--------|-------|")
+    lines.append(f"| Total tests | {s['total']} |")
+    lines.append(f"| Passed | {s['passed']} |")
+    lines.append(f"| Failed | {s['failed']} |")
+    lines.append(f"| Errors | {s['errors']} |")
+    lines.append("")
+
+    lines.append("## Results by Category")
+    lines.append("")
+    lines.append("| Test | Category | Result | Reason | Latency | Tokens |")
+    lines.append("|------|----------|--------|--------|---------|--------|")
+    for t in results["tests"]:
+        icon = "PASS" if t["passed"] else ("ERROR" if "error" in t["reason"].lower() else "FAIL")
+        lines.append(f"| {t['id']} | {t['category']} | {icon} | {t['reason']} | {t['latency_s']}s | {t['tokens']} |")
+    lines.append("")
+
+    lines.append("## Verdict")
+    lines.append("")
+    if pass_rate == 100:
+        lines.append("**FULLY VIABLE** — All tool calling patterns work. Ready for production edge deployment.")
+    elif pass_rate >= 60:
+        lines.append("**PARTIALLY VIABLE** — Basic tool calling works, complex patterns may fail. Consider for simple agents.")
+    elif pass_rate >= 20:
+        lines.append("**MARGINAL** — Only simplest tool calls work. Not recommended for production.")
+    else:
+        lines.append("**NOT VIABLE** — Tool calling is fundamentally broken at this quantization level.")
+    lines.append("")
+
+    lines.append("## Failure Analysis")
+    lines.append("")
+    failed = [t for t in results["tests"] if not t["passed"]]
+    if not failed:
+        lines.append("No failures.")
+    else:
+        for t in failed:
+            lines.append(f"### {t['id']}")
+            lines.append(f"- **Category**: {t['category']}")
+            lines.append(f"- **Failure**: {t['reason']}")
+            lines.append(f"- **Response** (first 300 chars): `{t['response'][:300]}`")
+            lines.append("")
+    lines.append("")
+
+    lines.append("## Recommendations")
+    lines.append("")
+    if pass_rate >= 80:
+        lines.append("- Deploy for simple single-tool-call workflows")
+        lines.append("- Add retry logic for multi-step chains")
+        lines.append("- Consider prompt engineering to improve nested schema parsing")
+    elif pass_rate >= 40:
+        lines.append("- Use for keyword/rule-based tool routing only")
+        lines.append("- Do NOT use for complex multi-step workflows")
+        lines.append("- Consider a larger model (Q4 quantized) as fallback")
+    else:
+        lines.append("- 1-bit quantization is too lossy for tool calling")
+        lines.append("- Use Q4_0 as minimum viable quantization for tool use")
+        lines.append("- Reserve 1-bit models for text generation only")
+
+    return "\n".join(lines)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Tool Calling Viability Test for Edge Models")
+    parser.add_argument("--model", "-m", required=True, help="Model name")
+    parser.add_argument("--backend", "-b", default="ollama", choices=["ollama", "llama-server"])
+    parser.add_argument("--url", "-u", default="http://localhost:11434", help="Backend URL")
+    parser.add_argument("--timeout", "-t", type=int, default=120, help="Timeout per test (seconds)")
+    parser.add_argument("--output", "-o", help="Output markdown file path")
+    parser.add_argument("--json", action="store_true", help="JSON output")
+    parser.add_argument("--verbose", "-v", action="store_true", help="Show full responses")
+    args = parser.parse_args()
+
+    results = run_tests(args.model, args.backend, args.url, args.timeout, args.verbose)
+
+    if args.json:
+        print(json.dumps(results, indent=2))
+    else:
+        md = to_markdown(results)
+        if args.output:
+            with open(args.output, "w") as f:
+                f.write(md)
+            print(f"\nReport written to: {args.output}")
+        else:
+            print("\n" + md)
+
+
+if __name__ == "__main__":
+    main()

docs/PROJECT_STATUS.md

@@ -389,40 +389,6 @@ Step 7: If pass → production. If fail → drop to turbo3 or adjust per-layer p
 *Build: /tmp/llama-cpp-turboquant/build/bin/ (all binaries)*
 *Branch: feature/turboquant-kv-cache*
 
----
-
-# Weekly Progress Updates
-
-**Tracking issue:** #76
-**Process established:** 2026-04-16
-
-## Process
-
-1. **Weekly cadence** — Every Monday, generate and post a progress update as a comment on issue #76.
-2. **Benchmark results** — Post as they happen (don't wait for weekly update).
-3. **Blocker escalation** — New blockers posted within 24 hours with label `blocker`.
-4. **PROJECT_STATUS.md** — Updated weekly with current state.
-
-## How to Generate
-
-```bash
-# Auto-generated from git log + Gitea API
-python3 scripts/weekly_update.py --post
-
-# Preview first
-python3 scripts/weekly_update.py
-
-# Custom date range
-python3 scripts/weekly_update.py --since 2026-04-01
-
-# Raw JSON data
-python3 scripts/weekly_update.py --json
-```
-
-## Template
-
-See `docs/WEEKLY_TEMPLATE.md` for manual updates.
-
 
 ---
 

docs/WEEKLY_TEMPLATE.md

@@ -1,26 +0,0 @@
-# TurboQuant Weekly Update Template
-
-Use this template when posting manual weekly updates. For automated updates, run `scripts/weekly_update.py --post`.
-
-## Week of [START_DATE] to [END_DATE]
-
-### Completed
-- [item 1]
-- [item 2]
-
-### Benchmark Results
-- [key metric or "No new benchmarks this week"]
-
-### In Progress
-- [item being worked on — who's on it]
-
-### Blockers
-- [blocker — impact — who needs to act]
-- _None_ if clear
-
-### Next Week
-- [planned item 1]
-- [planned item 2]
-
----
-_Generated by `scripts/weekly_update.py` or filled manually._

scripts/weekly_update.py

@@ -1,323 +0,0 @@
-#!/usr/bin/env python3
-"""
-TurboQuant Weekly Progress Update Generator
-
-Generates a structured weekly update from:
-- Git log (commits since last week)
-- Open/closed issues and PRs
-- Benchmark results
-- Blockers (open issues labeled 'blocker')
-
-Usage:
-    python3 scripts/weekly_update.py                    # This week
-    python3 scripts/weekly_update.py --since 2026-04-08 # Custom range
-    python3 scripts/weekly_update.py --post             # Post as Gitea comment on tracking issue
-"""
-
-import argparse
-import json
-import os
-import subprocess
-import sys
-from datetime import datetime, timedelta
-from pathlib import Path
-
-try:
-    import requests
-    HAS_REQUESTS = True
-except ImportError:
-    HAS_REQUESTS = False
-
-
-REPO_ROOT = Path(__file__).resolve().parent.parent
-GITEA_URL = "https://forge.alexanderwhitestone.com"
-REPO_PATH = "Timmy_Foundation/turboquant"
-TRACKING_ISSUE = 76  # This issue
-
-
-def git_log(since: str, until: str = None) -> list[dict]:
-    """Get commits since a date."""
-    until = until or datetime.now().strftime("%Y-%m-%d")
-    cmd = [
-        "git", "-C", str(REPO_ROOT), "log",
-        f"--since={since}", f"--until={until}",
-        "--format=%H|%an|%ae|%aI|%s",
-        "--all"
-    ]
-    result = subprocess.run(cmd, capture_output=True, text=True)
-    commits = []
-    for line in result.stdout.strip().split("\n"):
-        if not line:
-            continue
-        parts = line.split("|", 4)
-        if len(parts) == 5:
-            commits.append({
-                "hash": parts[0][:8],
-                "author": parts[1],
-                "email": parts[2],
-                "date": parts[3][:10],
-                "subject": parts[4],
-            })
-    return commits
-
-
-def git_diff_stats(since: str) -> dict:
-    """Get file change stats."""
-    cmd = [
-        "git", "-C", str(REPO_ROOT), "diff",
-        f"--stat", f"{since}..HEAD"
-    ]
-    result = subprocess.run(cmd, capture_output=True, text=True)
-    lines = result.stdout.strip().split("\n")
-    summary = lines[-1] if lines else "No changes"
-    return {"summary": summary, "files_changed": len([l for l in lines if "|" in l])}
-
-
-def find_benchmarks() -> list[dict]:
-    """Scan benchmark results directory for recent results."""
-    bench_dir = REPO_ROOT / "benchmarks"
-    results = []
-    if not bench_dir.exists():
-        return results
-
-    for f in bench_dir.glob("*.json"):
-        try:
-            data = json.loads(f.read_text())
-            results.append({"file": f.name, "data": data})
-        except (json.JSONDecodeError, Exception):
-            pass
-
-    # Also check for markdown reports
-    for f in bench_dir.glob("*.md"):
-        if f.name != "README.md":
-            stat = f.stat()
-            results.append({
-                "file": f.name,
-                "type": "report",
-                "modified": datetime.fromtimestamp(stat.st_mtime).strftime("%Y-%m-%d"),
-                "size": stat.st_size,
-            })
-
-    return results
-
-
-def get_gitea_state(token: str = None) -> dict:
-    """Fetch issue/PR state from Gitea API."""
-    if not HAS_REQUESTS or not token:
-        return {"available": False}
-
-    H = {"Authorization": f"token {token}"}
-    base = f"{GITEA_URL}/api/v1/repos/{REPO_PATH}"
-
-    try:
-        # Open issues
-        r = requests.get(f"{base}/issues?state=open&limit=100", headers=H)
-        open_issues = r.json() if r.status_code == 200 else []
-
-        # Closed issues (recent)
-        r = requests.get(f"{base}/issues?state=closed&limit=50&sort=updated&order=desc", headers=H)
-        closed_issues = r.json() if r.status_code == 200 else []
-
-        # PRs
-        r = requests.get(f"{base}/pulls?state=open&limit=50", headers=H)
-        open_prs = r.json() if r.status_code == 200 else []
-
-        return {
-            "available": True,
-            "open_issues": open_issues,
-            "closed_issues": closed_issues,
-            "open_prs": open_prs,
-        }
-    except Exception as e:
-        return {"available": False, "error": str(e)}
-
-
-def categorize_commits(commits: list[dict]) -> dict:
-    """Categorize commits by conventional prefix."""
-    categories = {
-        "feat": [], "fix": [], "bench": [], "docs": [],
-        "test": [], "refactor": [], "chore": [], "other": []
-    }
-    for c in commits:
-        subject = c["subject"].lower()
-        if subject.startswith("feat") or subject.startswith("feature"):
-            categories["feat"].append(c)
-        elif subject.startswith("fix"):
-            categories["fix"].append(c)
-        elif subject.startswith("bench") or subject.startswith("perf"):
-            categories["bench"].append(c)
-        elif subject.startswith("doc"):
-            categories["docs"].append(c)
-        elif subject.startswith("test"):
-            categories["test"].append(c)
-        elif subject.startswith("refactor"):
-            categories["refactor"].append(c)
-        elif subject.startswith("chore") or subject.startswith("ci"):
-            categories["chore"].append(c)
-        else:
-            categories["other"].append(c)
-    return {k: v for k, v in categories.items() if v}
-
-
-def generate_update(since: str, gitea_state: dict = None) -> str:
-    """Generate the weekly update markdown."""
-    now = datetime.now()
-    until = now.strftime("%Y-%m-%d")
-    week_label = f"Week of {since} to {until}"
-
-    commits = git_log(since, until)
-    diff_stats = git_diff_stats(since)
-    categories = categorize_commits(commits)
-    benchmarks = find_benchmarks()
-
-    lines = [
-        f"## {week_label}",
-        "",
-        f"**Generated:** {now.strftime('%Y-%m-%d %H:%M UTC')}",
-        f"**Commits:** {len(commits)} | **Files changed:** {diff_stats['files_changed']}",
-        "",
-    ]
-
-    # Completed work by category
-    lines.append("### Completed")
-    lines.append("")
-    if commits:
-        for cat, items in categories.items():
-            label = {
-                "feat": "Features", "fix": "Fixes", "bench": "Benchmarks",
-                "docs": "Documentation", "test": "Tests", "refactor": "Refactoring",
-                "chore": "Maintenance", "other": "Other"
-            }.get(cat, cat)
-            lines.append(f"**{label}:**")
-            for c in items:
-                lines.append(f"- `{c['hash']}` {c['subject']} ({c['author']}, {c['date']})")
-            lines.append("")
-    else:
-        lines.append("- No commits this week")
-        lines.append("")
-
-    # Benchmark results
-    if benchmarks:
-        lines.append("### Benchmark Results")
-        lines.append("")
-        for b in benchmarks:
-            if b.get("type") == "report":
-                lines.append(f"- **{b['file']}** (updated {b['modified']}, {b['size']} bytes)")
-            else:
-                lines.append(f"- **{b['file']}** — see `benchmarks/{b['file']}`")
-        lines.append("")
-
-    # Gitea state (if available)
-    if gitea_state and gitea_state.get("available"):
-        open_issues = gitea_state["open_issues"]
-        open_prs = gitea_state["open_prs"]
-        closed = gitea_state["closed_issues"]
-
-        lines.append("### In Progress")
-        lines.append("")
-        blockers = []
-        for issue in open_issues:
-            labels = [l["name"] for l in issue.get("labels", [])]
-            prefix = ""
-            if "blocker" in labels:
-                blockers.append(issue)
-                prefix = "🚧 BLOCKER — "
-            assignee = issue.get("assignee", {})
-            who = assignee.get("login", "unassigned") if assignee else "unassigned"
-            lines.append(f"- {prefix}#{issue['number']}: {issue['title']} ({who})")
-
-        if open_prs:
-            lines.append("")
-            lines.append("**Open PRs:**")
-            for pr in open_prs:
-                lines.append(f"- #{pr['number']}: {pr['title']} ({pr['user']['login']})")
-        lines.append("")
-
-        # Blockers
-        if blockers:
-            lines.append("### Blockers")
-            lines.append("")
-            for b in blockers:
-                lines.append(f"- #{b['number']}: {b['title']}")
-                if b.get("body"):
-                    snippet = b["body"][:200].replace("\n", " ")
-                    lines.append(f"  > {snippet}...")
-            lines.append("")
-
-        # Recently closed
-        recent_closed = [i for i in closed if i.get("closed_at")]
-        if recent_closed:
-            lines.append("### Closed This Period")
-            lines.append("")
-            for issue in recent_closed[:10]:
-                closed_date = issue.get("closed_at", "")[:10]
-                lines.append(f"- #{issue['number']}: {issue['title']} (closed {closed_date})")
-            lines.append("")
-
-    # Next week
-    lines.append("### Next Week")
-    lines.append("")
-    lines.append("- _TBD — fill in planned work_")
-    lines.append("")
-
-    return "\n".join(lines)
-
-
-def post_gitea_comment(token: str, body: str, issue: int = TRACKING_ISSUE):
-    """Post the update as a comment on the tracking issue."""
-    if not HAS_REQUESTS:
-        print("ERROR: requests library not available", file=sys.stderr)
-        return False
-
-    H = {"Authorization": f"token {token}", "Content-Type": "application/json"}
-    url = f"{GITEA_URL}/api/v1/repos/{REPO_PATH}/issues/{issue}/comments"
-    r = requests.post(url, headers=H, json={"body": body})
-
-    if r.status_code in (200, 201):
-        print(f"Posted comment on issue #{issue}")
-        return True
-    else:
-        print(f"Failed to post: {r.status_code} {r.text}", file=sys.stderr)
-        return False
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Generate TurboQuant weekly progress update")
-    parser.add_argument("--since", help="Start date (YYYY-MM-DD), default: 7 days ago")
-    parser.add_argument("--post", action="store_true", help="Post as Gitea comment on issue #76")
-    parser.add_argument("--json", action="store_true", help="Output raw data as JSON")
-    args = parser.parse_args()
-
-    since = args.since or (datetime.now() - timedelta(days=7)).strftime("%Y-%m-%d")
-
-    # Try to load Gitea token
-    token = None
-    token_path = Path.home() / ".config" / "gitea" / "token"
-    if token_path.exists():
-        token = token_path.read_text().strip()
-
-    gitea_state = get_gitea_state(token) if token else {"available": False}
-
-    if args.json:
-        data = {
-            "since": since,
-            "commits": git_log(since),
-            "benchmarks": find_benchmarks(),
-            "gitea": {k: v for k, v in gitea_state.items() if k != "available"} if gitea_state.get("available") else None,
-        }
-        print(json.dumps(data, indent=2, default=str))
-        return
-
-    update = generate_update(since, gitea_state)
-
-    if args.post:
-        if not token:
-            print("ERROR: No Gitea token found at ~/.config/gitea/token", file=sys.stderr)
-            sys.exit(1)
-        post_gitea_comment(token, update)
-    else:
-        print(update)
-
-
-if __name__ == "__main__":
-    main()

scripts/weekly_update.sh

@@ -1,14 +0,0 @@
-#!/usr/bin/env bash
-# TurboQuant Weekly Update — shell wrapper
-# Generates and optionally posts a weekly progress update.
-#
-# Usage:
-#   ./scripts/weekly_update.sh              # Print to stdout
-#   ./scripts/weekly_update.sh --post       # Post as Gitea comment on #76
-#   ./scripts/weekly_update.sh --since 2026-04-01  # Custom date range
-#   ./scripts/weekly_update.sh --json       # Raw JSON data
-
-set -euo pipefail
-cd "$(dirname "$0")/.."
-
-python3 scripts/weekly_update.py "$@"

tests/test_tool_calling.py

@@ -0,0 +1,189 @@
+#!/usr/bin/env python3
+"""
+Unit tests for benchmarks/test_tool_calling.py
+
+Tests the validation logic and report generation without
+requiring a live model backend.
+"""
+
+import json
+import sys
+from pathlib import Path
+
+import pytest
+
+sys.path.insert(0, str(Path(__file__).parent.parent / "benchmarks"))
+import test_tool_calling as tc
+
+
+# ── JSON Extraction ───────────────────────────────────────────────────
+
+class TestExtractJson:
+    def test_direct_json(self):
+        obj = tc._extract_json('{"name": "read_file", "arguments": {"path": "/etc/hostname"}}')
+        assert obj["name"] == "read_file"
+
+    def test_json_in_code_block(self):
+        text = 'Here is the call:\n```json\n{"name": "terminal", "arguments": {"command": "ls"}}\n```'
+        obj = tc._extract_json(text)
+        assert obj["name"] == "terminal"
+
+    def test_json_without_lang(self):
+        text = '```\n{"name": "web_search", "arguments": {"query": "test"}}\n```'
+        obj = tc._extract_json(text)
+        assert obj["name"] == "web_search"
+
+    def test_no_json(self):
+        obj = tc._extract_json("I can't help with that.")
+        assert obj is None
+
+    def test_bare_json_object(self):
+        text = 'Sure, here: {"name": "read_file", "arguments": {"path": "/tmp/x"}} for you.'
+        obj = tc._extract_json(text)
+        assert obj is not None
+        assert obj["name"] == "read_file"
+
+
+# ── Tool Call Validation ──────────────────────────────────────────────
+
+class TestToolCallValidation:
+    def test_exact_match(self):
+        resp = '{"name": "read_file", "arguments": {"path": "/etc/hostname"}}'
+        result = tc._has_json_tool_call(resp, "read_file", {"path": "/etc/hostname"})
+        assert result["passed"] is True
+
+    def test_wrong_tool_name(self):
+        resp = '{"name": "write_file", "arguments": {"path": "/etc/hostname"}}'
+        result = tc._has_json_tool_call(resp, "read_file", {"path": "/etc/hostname"})
+        assert result["passed"] is False
+        assert "wrong tool name" in result["reason"]
+
+    def test_missing_argument(self):
+        resp = '{"name": "read_file", "arguments": {}}'
+        result = tc._has_json_tool_call(resp, "read_file", {"path": "/etc/hostname"})
+        assert result["passed"] is False
+        assert "missing argument" in result["reason"]
+
+    def test_wrong_argument_value(self):
+        resp = '{"name": "read_file", "arguments": {"path": "/etc/passwd"}}'
+        result = tc._has_json_tool_call(resp, "read_file", {"path": "/etc/hostname"})
+        assert result["passed"] is False
+        assert "argument mismatch" in result["reason"]
+
+    def test_no_json_response(self):
+        result = tc._has_json_tool_call("Sorry, I can't do that.", "read_file", {"path": "/etc/hostname"})
+        assert result["passed"] is False
+        assert "no JSON" in result["reason"]
+
+    def test_nested_function_format(self):
+        resp = '{"function": {"name": "terminal", "arguments": {"command": "echo hello"}}}'
+        result = tc._has_json_tool_call(resp, "terminal", {"command": "echo hello"})
+        assert result["passed"] is True
+
+
+# ── Nested Schema Validation ──────────────────────────────────────────
+
+class TestNestedSchemaValidation:
+    def test_valid_nested(self):
+        resp = json.dumps({
+            "name": "deploy_service",
+            "arguments": {
+                "name": "api-gateway",
+                "replicas": 3,
+                "env": {"PORT": 8080, "NODE_ENV": "production"},
+                "resources": {"cpu": "500m", "memory": "256Mi"}
+            }
+        })
+        result = tc._has_nested_tool_call(resp)
+        assert result["passed"] is True
+
+    def test_missing_nested_key(self):
+        resp = '{"name": "deploy_service", "arguments": {"name": "api-gateway", "replicas": 3}}'
+        result = tc._has_nested_tool_call(resp)
+        assert result["passed"] is False
+        assert "missing nested key" in result["reason"]
+
+    def test_wrong_type(self):
+        resp = '{"name": "deploy_service", "arguments": {"name": "api-gateway", "replicas": "three", "env": {}, "resources": {}}}'
+        result = tc._has_nested_tool_call(resp)
+        assert result["passed"] is False
+        assert "should be int" in result["reason"]
+
+    def test_missing_env_port(self):
+        resp = json.dumps({
+            "name": "deploy_service",
+            "arguments": {"name": "api", "replicas": 1, "env": {"NODE_ENV": "dev"}, "resources": {}}
+        })
+        result = tc._has_nested_tool_call(resp)
+        assert result["passed"] is False
+        assert "PORT" in result["reason"]
+
+
+# ── Markdown Report Generation ────────────────────────────────────────
+
+class TestMarkdownReport:
+    def test_report_structure(self):
+        results = {
+            "model": "test-model",
+            "backend": "ollama",
+            "url": "http://localhost:11434",
+            "timestamp": "2026-04-15T00:00:00Z",
+            "tests": [
+                {"id": "t1", "category": "Simple", "description": "Test 1",
+                 "passed": True, "reason": "ok", "response": "{}", "latency_s": 1.0, "tokens": 10},
+                {"id": "t2", "category": "Complex", "description": "Test 2",
+                 "passed": False, "reason": "wrong name", "response": "oops", "latency_s": 2.0, "tokens": 20},
+            ],
+            "summary": {"total": 2, "passed": 1, "failed": 1, "errors": 0},
+        }
+        md = tc.to_markdown(results)
+        assert "test-model" in md
+        assert "1/2 passed" in md
+        assert "PASS" in md
+        assert "FAIL" in md
+        assert "Failure Analysis" in md
+
+    def test_perfect_score(self):
+        results = {
+            "model": "perfect", "backend": "ollama", "url": "http://x",
+            "timestamp": "2026-01-01T00:00:00Z",
+            "tests": [
+                {"id": "t1", "category": "C", "description": "D",
+                 "passed": True, "reason": "ok", "response": "{}", "latency_s": 1, "tokens": 5},
+            ],
+            "summary": {"total": 1, "passed": 1, "failed": 0, "errors": 0},
+        }
+        md = tc.to_markdown(results)
+        assert "FULLY VIABLE" in md
+
+    def test_all_failed(self):
+        results = {
+            "model": "bad", "backend": "ollama", "url": "http://x",
+            "timestamp": "2026-01-01T00:00:00Z",
+            "tests": [
+                {"id": "t1", "category": "C", "description": "D",
+                 "passed": False, "reason": "broken", "response": "nope", "latency_s": 1, "tokens": 0},
+            ],
+            "summary": {"total": 1, "passed": 0, "failed": 1, "errors": 0},
+        }
+        md = tc.to_markdown(results)
+        assert "NOT VIABLE" in md
+
+
+# ── Test Definitions ──────────────────────────────────────────────────
+
+class TestTestDefinitions:
+    def test_all_tests_have_validators(self):
+        for test in tc.TESTS:
+            assert callable(test["validate"]), f"{test['id']} missing validate"
+            assert "id" in test
+            assert "category" in test
+            assert "prompt" in test
+
+    def test_five_test_categories(self):
+        categories = {t["category"] for t in tc.TESTS}
+        assert len(categories) >= 4, f"Expected 4+ categories, got {categories}"
+
+
+if __name__ == "__main__":
+    pytest.main([__file__, "-v"])

tests/test_weekly_update.py

@@ -1,52 +0,0 @@
-#!/usr/bin/env python3
-"""Quick test for weekly_update.py — verifies parsing, output format, and edge cases."""
-
-import subprocess
-import sys
-import json
-from pathlib import Path
-
-SCRIPT = Path(__file__).resolve().parent.parent / "scripts" / "weekly_update.py"
-
-def run(args: list[str]) -> str:
-    result = subprocess.run(
-        [sys.executable, str(SCRIPT)] + args,
-        capture_output=True, text=True, cwd=str(SCRIPT.parent.parent)
-    )
-    return result.stdout, result.stderr, result.returncode
-
-def test_basic_output():
-    """Script runs without error and produces markdown."""
-    stdout, stderr, rc = run(["--since", "2026-01-01"])
-    assert rc == 0, f"Exit code {rc}: {stderr}"
-    assert "## Week of" in stdout, f"Missing header: {stdout[:200]}"
-    assert "### Completed" in stdout, f"Missing Completed section: {stdout[:200]}"
-    assert "### Next Week" in stdout, f"Missing Next Week section: {stdout[-200:]}"
-    print("PASS: basic_output")
-
-def test_json_output():
-    """Script outputs valid JSON in --json mode."""
-    stdout, stderr, rc = run(["--json", "--since", "2026-01-01"])
-    assert rc == 0, f"Exit code {rc}: {stderr}"
-    data = json.loads(stdout)
-    assert "commits" in data
-    assert "since" in data
-    print(f"PASS: json_output ({len(data['commits'])} commits)")
-
-def test_no_crash_future_date():
-    """Script handles future date gracefully."""
-    stdout, stderr, rc = run(["--since", "2030-01-01"])
-    assert rc == 0, f"Exit code {rc}: {stderr}"
-    print("PASS: future_date_no_crash")
-
-def test_empty_range():
-    """Script handles a very old date with no commits."""
-    stdout, stderr, rc = run(["--since", "2020-01-01", "--since", "2020-01-02"])
-    assert rc == 0
-    print("PASS: empty_range")
-
-if __name__ == "__main__":
-    test_basic_output()
-    test_json_output()
-    test_no_crash_future_date()
-    print("\nAll tests passed.")