540b4f5b01
First-PR scope from #1. Single-process Python daemon that relays between Claude Code instances and chat-Claude (Anthropic API). Components: * relay.config — .env + config.yaml loader. Auto-generates ntfy topic on first run and persists it back to .env. * relay.state — atomic file I/O via tempfile + rename, advisory flock at state/.lock to enforce single-instance. * relay.conversation — append-only history with summarization. Triggers a summarize call when total chars exceed HISTORY_CHAR_CAP (default 400k); replaces history with the summary plus the most recent 10 turns. * relay.anthropic_client — SDK wrapper. Marks the system prompt cacheable (5-min ephemeral cache); concatenates text blocks; estimates per-call cost from the Anthropic price table with cache-write/read accounted for. * relay.queue — JSON envelope intake; oldest-by-mtime; malformed envelopes moved to queue/.rejected/. * relay.dispatch — one-input-at-a-time per session (dispatch/<session_id>/input.txt). Won't overwrite a pending dispatch; queues internally and waits for CC to delete. * relay.ntfy — best-effort POST to https://ntfy.sh/<topic>; failures logged but never block the main loop. * relay.daemon — main loop. Polls jc_input.txt (priority) then queue/. Detects [NEEDS-JC] in the first 200 chars of any response and pauses dispatch until JC writes jc_input.txt. JC override supports @session-N: prefix for direct dispatch without an API call. * relay.__main__ — CLI: relay run / relay status / relay topic. Tests: 57 unit tests pass (config, state, conversation, queue, dispatch, anthropic_client, ntfy, full daemon loop with a fake client). One real-API smoke test marked real_api, opt-in via pytest -m real_api; skips cleanly on credit-balance errors. Out of scope for this PR (deferred to follow-ups): Flask status endpoint, multi-session config in production, exponential backoff, systemd unit, cost-tracking aggregation. Closes #1. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
68 lines
2.4 KiB
Python
68 lines
2.4 KiB
Python
from __future__ import annotations
|
|
|
|
import json
|
|
from pathlib import Path
|
|
|
|
from relay.conversation import RECENT_TURNS_KEPT, Conversation, render_for_log
|
|
|
|
|
|
def test_append_and_read_back(tmp_path: Path) -> None:
|
|
convo = Conversation(tmp_path / "c.json")
|
|
convo.append("user", "hello", session_id="session-1")
|
|
convo.append("assistant", "hi back")
|
|
assert [t.role for t in convo.turns] == ["user", "assistant"]
|
|
persisted = json.loads((tmp_path / "c.json").read_text())
|
|
assert persisted[0]["session_id"] == "session-1"
|
|
|
|
|
|
def test_total_chars_sums_content(tmp_path: Path) -> None:
|
|
convo = Conversation(tmp_path / "c.json")
|
|
convo.append("user", "abc")
|
|
convo.append("assistant", "defg")
|
|
assert convo.total_chars() == 7
|
|
|
|
|
|
def test_needs_summarization_threshold(tmp_path: Path) -> None:
|
|
convo = Conversation(tmp_path / "c.json")
|
|
convo.append("user", "x" * 100)
|
|
assert not convo.needs_summarization(200)
|
|
assert convo.needs_summarization(50)
|
|
|
|
|
|
def test_replace_with_summary_keeps_recent_turns(tmp_path: Path) -> None:
|
|
convo = Conversation(tmp_path / "c.json")
|
|
for i in range(RECENT_TURNS_KEPT + 5):
|
|
convo.append("user", f"u{i}")
|
|
convo.append("assistant", f"a{i}")
|
|
convo.replace_with_summary("SUMMARY")
|
|
assert convo.turns[0].role == "assistant"
|
|
assert convo.turns[0].content == "SUMMARY"
|
|
assert convo.turns[0].meta == "summary"
|
|
# 1 summary + RECENT_TURNS_KEPT verbatim
|
|
assert len(convo.turns) == 1 + RECENT_TURNS_KEPT
|
|
|
|
|
|
def test_replace_with_summary_persists(tmp_path: Path) -> None:
|
|
convo = Conversation(tmp_path / "c.json")
|
|
for i in range(20):
|
|
convo.append("user", f"u{i}")
|
|
convo.replace_with_summary("S")
|
|
reloaded = Conversation(tmp_path / "c.json")
|
|
assert reloaded.turns[0].content == "S"
|
|
|
|
|
|
def test_to_api_messages_strips_metadata(tmp_path: Path) -> None:
|
|
convo = Conversation(tmp_path / "c.json")
|
|
convo.append("user", "x", session_id="s1")
|
|
convo.append("assistant", "y")
|
|
msgs = convo.to_api_messages()
|
|
assert msgs == [{"role": "user", "content": "x"}, {"role": "assistant", "content": "y"}]
|
|
|
|
|
|
def test_render_for_log_truncates_long_content(tmp_path: Path) -> None:
|
|
convo = Conversation(tmp_path / "c.json")
|
|
convo.append("user", "a" * 1000)
|
|
rendered = render_for_log(convo.turns[0], max_chars=50)
|
|
assert len(rendered["content"]) < 100
|
|
assert "more chars" in rendered["content"]
|