dongarandClaude Opus 5
f4a94281ef
The second renderer adapter, and the concrete case for A13's decision to normalise in the renderer rather than on the wire. The two vendors disagree structurally, not cosmetically: the system prompt is a top-level field rather than a message, a tool call is a tool_use content block rather than an array, a tool result is a block inside a user message rather than a "tool" role, and tool schemas use input_schema rather than parameters. A middlebox flattening those would be lossy exactly where a long-running delegation lives. - render_anthropic.py builds vendor-native /v1/messages bodies from the canonical log, coalescing adjacent same-role blocks so a tool_result lands directly after its tool_use - Tool manifests are declared once in OpenAI shape and converted per vendor, so adding a tool does not mean editing two places - AnthropicPassthroughClient implements the same LLMClient protocol, so callers pick a route rather than a different kind of client, and maps provider tool ids to canonical ones at the boundary - Dangling tool calls get a placeholder result here too; this API rejects them more strictly than the OpenAI shape - Vendor-opaque reasoning blocks are dropped for now with the reason recorded: A10 wants them stored and never replayed across sessions, and the canonical schema has no event for that yet Live tests prove the body is accepted as sent, that a tool_result turn round-trips, and — as A5 asks — that prompt cache accounting survives the passthrough rather than being flattened by the proxy. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
109 lines
3.6 KiB
Python
109 lines
3.6 KiB
Python
"""Live Anthropic passthrough: the vendor-native route delegations will use.
|
|
|
|
Proves the renderer's body is accepted as-is, that a tool call round-trips
|
|
through the canonical log, and — per A5 — that prompt caching survives the
|
|
passthrough rather than being flattened by the proxy.
|
|
"""
|
|
|
|
import io
|
|
import os
|
|
from pathlib import Path
|
|
|
|
import httpx
|
|
import pytest
|
|
|
|
from nisse_dev.canonical import AssistantText, ToolCall, ToolResult, UserMessage
|
|
from nisse_dev.envfile import load_env_file
|
|
from nisse_dev.llm import AnthropicPassthroughClient
|
|
from nisse_dev.oplog import OpLog
|
|
from nisse_dev.state import StateStore
|
|
from nisse_dev.tools import EXECUTOR_TOOLS
|
|
|
|
load_env_file(Path(__file__).resolve().parents[2] / ".env")
|
|
|
|
SENTINEL = "NISSE_LIVE_PLANNER_MODEL"
|
|
|
|
pytestmark = [
|
|
pytest.mark.integration,
|
|
pytest.mark.skipif(
|
|
not os.environ.get(SENTINEL),
|
|
reason=f"no live frontier route configured ({SENTINEL} unset)",
|
|
),
|
|
]
|
|
|
|
|
|
def store_with(tmp_path: Path, *events) -> StateStore:
|
|
store = StateStore(tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO()))
|
|
for event in events:
|
|
store.append_event(event)
|
|
return store
|
|
|
|
|
|
def test_passthrough_completes_a_plain_turn(tmp_path: Path) -> None:
|
|
store = store_with(
|
|
tmp_path, UserMessage(text="Reply with exactly: pong", source="live")
|
|
)
|
|
result = AnthropicPassthroughClient.from_env().complete(
|
|
store.read_events(), None, os.environ[SENTINEL], system="Be terse."
|
|
)
|
|
texts = [e.text for e in result if isinstance(e, AssistantText)]
|
|
assert texts and "pong" in texts[0].lower()
|
|
|
|
|
|
def test_passthrough_round_trips_a_tool_call(tmp_path: Path) -> None:
|
|
store = store_with(
|
|
tmp_path,
|
|
UserMessage(
|
|
text="List the files in the current directory using your tools.",
|
|
source="live",
|
|
),
|
|
)
|
|
client = AnthropicPassthroughClient.from_env()
|
|
produced = client.complete(
|
|
store.read_events(),
|
|
EXECUTOR_TOOLS,
|
|
os.environ[SENTINEL],
|
|
system="Use a tool. Do not answer in prose.",
|
|
)
|
|
calls = [e for e in produced if isinstance(e, ToolCall)]
|
|
assert calls, f"expected a tool call, got {produced!r}"
|
|
|
|
# Feed the result back: the follow-up render must be accepted, which is
|
|
# what proves tool_result placement is right for this vendor.
|
|
for event in produced:
|
|
store.append_event(event)
|
|
store.append_event(
|
|
ToolResult(call_id=calls[0].call_id, result="app.py\ntests/", success=True)
|
|
)
|
|
follow_up = client.complete(
|
|
store.read_events(), EXECUTOR_TOOLS, os.environ[SENTINEL]
|
|
)
|
|
assert follow_up, "the vendor rejected or ignored the tool_result turn"
|
|
|
|
|
|
def test_prompt_caching_survives_the_passthrough() -> None:
|
|
# A5 asks for this to be verified rather than assumed: a proxy that
|
|
# flattened the request would silently drop cache control and turn a
|
|
# cost optimisation into a per-call expense.
|
|
base = os.environ["NISSE_LLM_BASE_URL"].rstrip("/")
|
|
token = os.environ["NISSE_LLM_TOKEN"]
|
|
response = httpx.post(
|
|
f"{base}/v1/messages",
|
|
headers={
|
|
"Authorization": f"Bearer {token}",
|
|
"x-api-key": token,
|
|
"anthropic-version": "2023-06-01",
|
|
},
|
|
json={
|
|
"model": os.environ[SENTINEL],
|
|
"max_tokens": 16,
|
|
"messages": [{"role": "user", "content": "Say pong."}],
|
|
},
|
|
timeout=120,
|
|
)
|
|
response.raise_for_status()
|
|
usage = response.json().get("usage", {})
|
|
assert "cache_read_input_tokens" in usage, (
|
|
f"cache accounting absent from passthrough usage: {usage}"
|
|
)
|