✅ Gremlins MVP: unit and CLI tests with a fake claude

2026-10-16 23:33:02 +02:00
parent fd75777628
commit d662790f19
6 changed files with 493 additions and 0 deletions
@@ -0,0 +1,64 @@
+"""Fake `claude -p` for the CLI tests. $FAKE_CLAUDE_SCENARIO: ok (default), miss, api_error,
+noresult, two_models, no_cost, sleep. $FAKE_CLAUDE_LOG: one JSON line per call (argv, pid)."""
+import json
+import os
+import sys
+import time
+import uuid
+
+TRAIN_MU = {"inputTokens": 10, "outputTokens": 20, "cacheReadInputTokens": 0,
+            "cacheCreationInputTokens": 1000}
+TRAIN_COST, CALL_COST = 0.05, 0.02
+
+
+def opt(name):
+    return sys.argv[sys.argv.index(name) + 1] if name in sys.argv else None
+
+
+def emit(ev):
+    print(json.dumps(ev), flush=True)
+
+
+def main():
+    prompt = sys.stdin.buffer.read().decode("utf-8")
+    scen = os.environ.get("FAKE_CLAUDE_SCENARIO", "ok")
+    if os.environ.get("FAKE_CLAUDE_LOG"):
+        with open(os.environ["FAKE_CLAUDE_LOG"], "a", encoding="utf-8") as f:
+            f.write(json.dumps({"argv": sys.argv, "pid": os.getpid(), "prompt_chars": len(prompt)}) + "\n")
+    resume, model = opt("--resume"), opt("--model")
+    # a plain resume (no fork, no --session-id) gets a new id, as `-p` may give one
+    sid = opt("--session-id") or ("resumed-" + uuid.uuid4().hex if resume else str(uuid.uuid4()))
+    read = 1000 if resume and scen != "miss" else 0
+    created = 100 if resume else 1000
+    usage = {"input_tokens": 10, "output_tokens": 20, "cache_creation_input_tokens": created,
+             "cache_read_input_tokens": read,
+             "cache_creation": {"ephemeral_1h_input_tokens": created, "ephemeral_5m_input_tokens": 0}}
+    emit({"type": "system", "subtype": "init", "session_id": sid, "model": model})
+    emit({"type": "assistant", "session_id": sid, "message": {"id": "m1", "usage": usage}})
+    if scen == "sleep":
+        time.sleep(60)
+    if scen == "noresult":
+        sys.exit(1)
+    mu = {"inputTokens": 10, "outputTokens": 20, "cacheReadInputTokens": read,
+          "cacheCreationInputTokens": created}
+    cost = CALL_COST if resume else TRAIN_COST
+    if resume:   # the session's totals include the base's training call
+        mu = {k: v + TRAIN_MU[k] for k, v in mu.items()}
+        cost += TRAIN_COST
+    res = {"type": "result", "subtype": "success", "is_error": False, "session_id": sid,
+           "result": "done", "num_turns": 1, "usage": usage, "modelUsage": {model: mu},
+           "total_cost_usd": cost}
+    if scen == "two_models":
+        res["modelUsage"]["claude-haiku-5-5"] = {"inputTokens": 5, "outputTokens": 1,
+                                                 "cacheReadInputTokens": 0, "cacheCreationInputTokens": 0}
+    if scen == "no_cost":
+        del res["total_cost_usd"]
+    if scen == "api_error":
+        res.update(subtype="error_during_execution", is_error=True, api_error_status=429,
+                   result="API Error: 429 rate limit")
+    emit(res)
+    sys.exit(1 if scen == "api_error" else 0)
+
+
+if __name__ == "__main__":
+    main()