test(827): capture Gate0 runtime evidence

docs/compaction-refresh/probes/p2_provider_timing_run.py

@@ -0,0 +1,135 @@
+#!/usr/bin/env python3
+"""Force a real Pi HTTP provider response to prove response-hook timing."""
+
+from __future__ import annotations
+
+import json
+import os
+import tempfile
+import threading
+from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
+from pathlib import Path
+
+from pi_gate0_run import PiRpc, jsonl
+
+HERE = Path(__file__).resolve().parent
+
+
+class Handler(BaseHTTPRequestHandler):
+    protocol_version = "HTTP/1.1"
+
+    def log_message(self, _format: str, *_args: object) -> None:
+        return
+
+    def do_POST(self) -> None:  # noqa: N802
+        length = int(self.headers.get("content-length", "0"))
+        self.rfile.read(length)
+        chunks = [
+            {
+                "id": "gate0-response",
+                "object": "chat.completion.chunk",
+                "created": 1,
+                "model": "gate0-model",
+                "choices": [{"index": 0, "delta": {"role": "assistant"}, "finish_reason": None}],
+            },
+            {
+                "id": "gate0-response",
+                "object": "chat.completion.chunk",
+                "created": 1,
+                "model": "gate0-model",
+                "choices": [
+                    {"index": 0, "delta": {"content": "TIMING_OK"}, "finish_reason": None}
+                ],
+            },
+            {
+                "id": "gate0-response",
+                "object": "chat.completion.chunk",
+                "created": 1,
+                "model": "gate0-model",
+                "choices": [{"index": 0, "delta": {}, "finish_reason": "stop"}],
+                "usage": {"prompt_tokens": 10, "completion_tokens": 2, "total_tokens": 12},
+            },
+        ]
+        body = "".join(f"data: {json.dumps(chunk)}\n\n" for chunk in chunks) + "data: [DONE]\n\n"
+        encoded = body.encode()
+        self.send_response(200)
+        self.send_header("Content-Type", "text/event-stream")
+        self.send_header("Content-Length", str(len(encoded)))
+        self.send_header("X-Gate0-Response", "headers-before-stream")
+        self.end_headers()
+        self.wfile.write(encoded)
+        self.wfile.flush()
+
+
+def main() -> None:
+    server = ThreadingHTTPServer(("127.0.0.1", 0), Handler)
+    thread = threading.Thread(target=server.serve_forever, daemon=True)
+    thread.start()
+    port = server.server_address[1]
+
+    with tempfile.TemporaryDirectory(prefix="gate0-p2-timing-") as temp:
+        root = Path(temp)
+        workspace = root / "workspace"
+        workspace.mkdir()
+        log = root / "hooks.jsonl"
+        env = os.environ.copy()
+        env.update(
+            {
+                "GATE0_PI_LOG": str(log),
+                "GATE0_LOCAL_PROVIDER_URL": f"http://127.0.0.1:{port}/v1",
+                "MOSAIC_PI_FORCE_SKILLS": "",
+                "PI_SKIP_VERSION_CHECK": "1",
+            }
+        )
+        command = [
+            "mosaic",
+            "yolo",
+            "pi",
+            "--mode",
+            "rpc",
+            "--no-session",
+            "--no-extensions",
+            "--no-context-files",
+            "--no-prompt-templates",
+            "--provider",
+            "gate0-local",
+            "--model",
+            "gate0-model",
+            "--extension",
+            str(HERE / "pi_gate0_extension.ts"),
+        ]
+        pi = PiRpc(command, workspace, env)
+        try:
+            pi.prompt_and_settle("timing", "Reply with TIMING_OK")
+            records = jsonl(log)
+            selected = [
+                record
+                for record in records
+                if record["event"] in {"before_provider_request", "after_provider_response", "message_end"}
+                and (record["event"] != "message_end" or record.get("role") == "assistant")
+            ]
+            print("$ python3 docs/compaction-refresh/probes/p2_provider_timing_run.py")
+            print(f"local_http_endpoint=http://127.0.0.1:{port}/v1/chat/completions")
+            for record in selected:
+                print(json.dumps(record, sort_keys=True))
+            after = next(record for record in selected if record["event"] == "after_provider_response")
+            message = next(record for record in selected if record["event"] == "message_end")
+            if not (
+                after["seq"] < message["seq"]
+                and after["assistantContentAvailableAtThisHook"] is False
+                and message["assistantContentObserved"] is True
+            ):
+                raise AssertionError("provider response/content observation ordering failed")
+            print("machine_assertions=PASS")
+            print(f"after_provider_response_seq={after['seq']}")
+            print(f"message_end_seq={message['seq']}")
+            print(f"headers_hook_precedes_completed_message={after['seq'] < message['seq']}")
+        finally:
+            pi.close()
+
+    server.shutdown()
+    server.server_close()
+
+
+if __name__ == "__main__":
+    main()