Add CSV export support for SuiteResultAdd csv reports (#62)

* Add basic evaluation example script

* Fix typos and improve clarity in docstrings across core modules

* Add Google-style docstrings to BaseAdapter methods

* Format base adapter using ruff

* docs: add instructions for running CI checks locally

* Remove example file unrelated to CI documentation

* Add py.typed marker for type checker support

* Add test for markdown emoji encoding

* Fix test_reporting: correct class usage, fields, and Windows-safe to_markdown

* All tests passing: fixed dependencies and formatting

* Update dependencies / poetry config

* Fix emoji markdown test and align ScenarioRun signature

* Fix reporting tests and update dependencies

* Fix missing required dependencies (jsonschema, scipy)

* Update all files

* Add CSV export support for SuiteResult

* Fix SIM118 linter issue in SuiteResult.to_csv

* Fix Ruff formatting issues in SuiteResult.to_csv

* Fix CSV export: iterate over dict keys correctly and pass Ruff lint

---------

Signed-off-by: Jagriti-student <jagriti7989@gmail.com>

Author: Jagriti-student

src/agentunit/reporting/results.py

@@ -2,11 +2,12 @@
 
 from __future__ import annotations
 
+import csv
 import json
 import statistics
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, Any
 from xml.etree import ElementTree as ET
 
 from agentunit.reporting.html import render_html_report
@@ -19,6 +20,11 @@
     from agentunit.core.trace import TraceLog
 
 
+# -------------------------
+# Data Models
+# -------------------------
+
+
 @dataclass(slots=True)
 class ScenarioRun:
     scenario_name: str
@@ -68,6 +74,29 @@ def to_dict(self) -> dict[str, object]:
         }
 
 
+# -------------------------
+# Helpers
+# -------------------------
+
+
+def _flatten_metrics(metrics: dict[str, Any], prefix: str = "metric") -> dict[str, Any]:
+    flat: dict[str, Any] = {}
+
+    for key, value in metrics.items():
+        if isinstance(value, dict):
+            for inner_key, inner_value in value.items():
+                flat[f"{prefix}_{key}_{inner_key}"] = inner_value
+        else:
+            flat[f"{prefix}_{key}"] = value
+
+    return flat
+
+
+# -------------------------
+# Suite Result
+# -------------------------
+
+
 @dataclass(slots=True)
 class SuiteResult:
     scenarios: list[ScenarioResult]
@@ -84,7 +113,10 @@ def to_dict(self) -> dict[str, object]:
     def to_json(self, path: str | Path) -> Path:
         target = Path(path)
         target.parent.mkdir(parents=True, exist_ok=True)
-        target.write_text(json.dumps(self.to_dict(), indent=2), encoding="utf-8")
+        target.write_text(
+            json.dumps(self.to_dict(), indent=2),
+            encoding="utf-8",
+        )
         return target
 
     def to_markdown(self, path: str | Path) -> Path:
@@ -99,7 +131,8 @@ def to_markdown(self, path: str | Path) -> Path:
     def to_junit(self, path: str | Path) -> Path:
         target = Path(path)
         target.parent.mkdir(parents=True, exist_ok=True)
-        testsuites = ET.Element(
+
+        testsuite = ET.Element(
             "testsuite",
             attrib={
                 "name": "agentunit",
@@ -108,10 +141,11 @@ def to_junit(self, path: str | Path) -> Path:
                 "time": f"{(self.finished_at - self.started_at).total_seconds():.4f}",
             },
         )
+
         for scenario in self.scenarios:
             for run in scenario.runs:
                 testcase = ET.SubElement(
-                    testsuites,
+                    testsuite,
                     "testcase",
                     attrib={
                         "classname": scenario.name,
@@ -126,7 +160,8 @@ def to_junit(self, path: str | Path) -> Path:
                         attrib={"message": run.error or "Scenario failed"},
                     )
                     failure.text = json.dumps(run.metrics)
-        tree = ET.ElementTree(testsuites)
+
+        tree = ET.ElementTree(testsuite)
         tree.write(target, encoding="utf-8", xml_declaration=True)
         return target
 
@@ -140,22 +175,78 @@ def to_html(self, path: str | Path) -> Path:
         target.write_text(html, encoding="utf-8")
         return target
 
+    def to_csv(self, path: str | Path) -> Path:
+        """
+        Export suite results to CSV.
+        One row per scenario run.
+        """
+        target = Path(path)
+        target.parent.mkdir(parents=True, exist_ok=True)
+
+        rows: list[dict[str, Any]] = []
+
+        for scenario in self.scenarios:
+            for run in scenario.runs:
+                row: dict[str, Any] = {
+                    "scenario_name": scenario.name,
+                    "case_id": run.case_id,
+                    "success": run.success,
+                    "duration_ms": run.duration_ms,
+                    "error": run.error,
+                }
+
+                if run.metrics:
+                    row.update(_flatten_metrics(run.metrics))
+
+                rows.append(row)
+
+        if not rows:
+            return target
+
+        fieldnames = sorted({key for row in rows for key in row})
+
+        with target.open("w", newline="", encoding="utf-8") as f:
+            writer = csv.DictWriter(f, fieldnames=fieldnames)
+            writer.writeheader()
+            writer.writerows(rows)
+
+        return target
+
+
+# -------------------------
+# Utilities
+# -------------------------
+
 
 def merge_results(results: Iterable[SuiteResult]) -> SuiteResult:
     results = list(results)
     scenarios: dict[str, ScenarioResult] = {}
+
     for result in results:
         for scenario in result.scenarios:
             existing = scenarios.setdefault(scenario.name, ScenarioResult(name=scenario.name))
             for run in scenario.runs:
                 existing.add_run(run)
+
     started = min(result.started_at for result in results)
     finished = max(result.finished_at for result in results)
-    return SuiteResult(scenarios=list(scenarios.values()), started_at=started, finished_at=finished)
+
+    return SuiteResult(
+        scenarios=list(scenarios.values()),
+        started_at=started,
+        finished_at=finished,
+    )
 
 
-def _render_markdown_scenario(scenario: ScenarioResult) -> list[str]:
-    lines = [f"## {scenario.name}", f"Success rate: {scenario.success_rate:.2%}", ""]
+def _render_markdown_scenario(
+    scenario: ScenarioResult,
+) -> list[str]:
+    lines = [
+        f"## {scenario.name}",
+        f"Success rate: {scenario.success_rate:.2%}",
+        "",
+    ]
+
     for run in scenario.runs:
         lines.append(f"- **{run.case_id}**: {'✅' if run.success else '❌'}")
         metrics_repr = ", ".join(
@@ -165,5 +256,6 @@ def _render_markdown_scenario(scenario: ScenarioResult) -> list[str]:
             lines.append(f"  - Metrics: {metrics_repr}")
         if run.error:
             lines.append(f"  - Error: {run.error}")
+
     lines.append("")
     return lines