dongarandClaude Opus 5.5
83804fe02a
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m14s
Development Plan M1.1, as discussed. - Schema v4: a work_items table (id, scope, title, status, outcome, position, data) and an agent row whose active_item points at one (NULL: idle). Canonical events and intents carry their work item, and events their actor. Older stores are refused with a clear message: there was no production data, so no migration (the mechanism stays). - The log is reached through a Transcript bound to one work item and one actor: store.transcript(item, actor) reads only that item and writes with both. The planner, executor, delegation and expert desk get one per call from the orchestrator instead of holding the store, so a component can neither read another task's events (the planner read every earlier task's, #78) nor write without attribution. store.all_events() is kept for readers that span items (evaluation capture, dumps). Intents are begun through the transcript or with work_item=, so each belongs to its item. - The orchestrator opens a work item on 'use', closes it with its outcome (completed or abandoned), and carries what the operator said while idle into the new item as copies with their origin, so a task sent before 'use' is still planned from (D1). control.py keeps its state machine through get_state()/transition(), now over the active work item, until M2.6 retires it. - nisse_dev.dump shows work items and each event's item and actor. Tests: test_work_items.py (scoping, attribution, intent ownership, restart, outcomes, carried messages, a second task never seeing the first); the suites updated for the per-call transcript. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
104 lines
3.5 KiB
Python
104 lines
3.5 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 L9 — that prompt caching survives the
|
|
passthrough rather than being flattened by the proxy.
|
|
"""
|
|
|
|
import io
|
|
from pathlib import Path
|
|
|
|
import httpx
|
|
import pytest
|
|
|
|
from nisse_dev.canonical import AssistantText, ToolCall, ToolResult, UserMessage
|
|
from nisse_dev.config import AgentConfig
|
|
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
|
|
|
|
pytestmark = pytest.mark.integration
|
|
|
|
|
|
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.transcript("t", "helper").append(event)
|
|
return store
|
|
|
|
|
|
def test_passthrough_completes_a_plain_turn(
|
|
tmp_path: Path, passthrough: AnthropicPassthroughClient, live_model: str
|
|
) -> None:
|
|
store = store_with(
|
|
tmp_path, UserMessage(text="Reply with exactly: pong", source="live")
|
|
)
|
|
result = passthrough.complete(
|
|
store.transcript("t", "helper").read(), None, live_model, 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, passthrough: AnthropicPassthroughClient, live_model: str
|
|
) -> None:
|
|
store = store_with(
|
|
tmp_path,
|
|
UserMessage(
|
|
text="List the files in the current directory using your tools.",
|
|
source="live",
|
|
),
|
|
)
|
|
client = passthrough
|
|
produced = client.complete(
|
|
store.transcript("t", "helper").read(),
|
|
EXECUTOR_TOOLS,
|
|
live_model,
|
|
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.transcript("t", "helper").append(event)
|
|
store.transcript("t", "helper").append(
|
|
ToolResult(call_id=calls[0].call_id, result="app.py\ntests/", success=True)
|
|
)
|
|
follow_up = client.complete(
|
|
store.transcript("t", "helper").read(), EXECUTOR_TOOLS, live_model
|
|
)
|
|
assert follow_up, "the vendor rejected or ignored the tool_result turn"
|
|
|
|
|
|
def test_prompt_caching_survives_the_passthrough(
|
|
live_config: AgentConfig, live_model: str
|
|
) -> None:
|
|
# L9 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 = live_config.llm_base_url.rstrip("/")
|
|
token = live_config.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": live_model,
|
|
"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}"
|
|
)
|