mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
Renn F
a88045aacf
Move the last Grok runtime off opencode onto xAI's official `grok` CLI, for full parity with the Claude path. The intake/secretary chat now runs per-turn headless `grok -p` invocations that resume one session id (proven live: context carries across runs), with streaming-json deltas mapped to the existing panel StreamChunk kinds — the IntakeDriver loop, message source, relay, and idle reaper are reused unchanged; only the SessionFactory differs (GrokCliSession replaces the opencode-serve session). - GrokCliSession + a pure, unit-tested streaming-json -> StreamChunk assembler (thought coalesced to one block, text streamed live, end captures the session id for -r, fenced-draft fallback, clear errors incl. rate-limit). - intake propose_draft and secretary read_company_state/read_task/submit_directive are now FastMCP servers (roboco-intake / roboco-secretary) wired into ~/.grok/config.toml, launched via `uv run --directory /app` to resolve the installed package. The secretary tools reuse the shared backend helpers. - Orchestrator: interactive spawn mounts the subscription auth + per-agent usage dir (no metered xAI key, no permission env — grok flags carry per-role perms); usage/cost now read a captured usage.json (drop the opencode.db reader, the _opencode_db_path/_grok_usage_from_opencode methods, and the cost-cap's opencode read). hosts["opencode"] -> hosts["grok_usage"]; OPENCODE_DATA_DIR -> GROK_USAGE_DATA_DIR. - Fix one-shot usage capture: `-s` does not pin the session id (grok generates its own), so the entrypoint now reads the real id back from the JSON run log and the reader uses it; usage is captured per-turn on the interactive path. - Delete the opencode layer: opencode_config/opencode_usage/opencode_session, the docker/grok/*.js plugins, the old one-shot entrypoint, and their tests. - Compose (all three files), .env.example, and stale comments updated to the grok-CLI runtime; add the SuperGrok auth mount + grok-usage dir. Gate green: ruff, mypy (296 files), xenon, tests. NAS build/verify pending.
96 lines
3.3 KiB
Python
96 lines
3.3 KiB
Python
"""grok_cli_session — the pure streaming-json → StreamChunk mapper.
|
|
|
|
The subprocess runner (``GrokCliSession``) needs the live grok binary, so it is
|
|
not gate-covered; the turn-mapping logic lives in the pure ``_StreamAssembler``
|
|
and is fully exercised here by feeding it parsed events.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
|
|
from roboco.agent_sdk.grok_cli_session import (
|
|
_classify_failure,
|
|
_parse_event,
|
|
_StreamAssembler,
|
|
)
|
|
|
|
|
|
def _kinds(chunks: list) -> list[str]:
|
|
return [c.kind for c in chunks]
|
|
|
|
|
|
def test_thought_deltas_coalesce_into_one_thinking_block() -> None:
|
|
a = _StreamAssembler()
|
|
out: list = []
|
|
for piece in ("Let", " me", " think"):
|
|
out += a.feed({"type": "thought", "data": piece})
|
|
# Nothing emitted until the answer starts (reasoning shown as one block).
|
|
assert out == []
|
|
out += a.feed({"type": "text", "data": "Hello"})
|
|
assert _kinds(out) == ["thinking", "text"]
|
|
assert out[0].text == "Let me think"
|
|
assert out[1].text == "Hello"
|
|
|
|
|
|
def test_text_deltas_stream_live() -> None:
|
|
a = _StreamAssembler()
|
|
out: list = []
|
|
for piece in ("a", "b", "c"):
|
|
out += a.feed({"type": "text", "data": piece})
|
|
assert _kinds(out) == ["text", "text", "text"]
|
|
assert "".join(c.text for c in out) == "abc"
|
|
|
|
|
|
def test_end_captures_session_id_and_emits_turn_end() -> None:
|
|
a = _StreamAssembler()
|
|
a.feed({"type": "text", "data": "hi"})
|
|
out = a.feed({"type": "end", "sessionId": "sid-9", "stopReason": "EndTurn"})
|
|
assert _kinds(out) == ["turn_end"]
|
|
assert a.session_id == "sid-9"
|
|
assert a.saw_end is True
|
|
assert out[-1].data["session_id"] == "sid-9"
|
|
|
|
|
|
def test_end_flushes_pending_thinking_before_turn_end() -> None:
|
|
a = _StreamAssembler()
|
|
a.feed({"type": "thought", "data": "reasoning only"})
|
|
out = a.feed({"type": "end", "sessionId": "s", "stopReason": "EndTurn"})
|
|
assert _kinds(out) == ["thinking", "turn_end"]
|
|
|
|
|
|
def test_fenced_draft_is_surfaced_as_a_draft_chunk() -> None:
|
|
a = _StreamAssembler()
|
|
draft = {"title": "Build X", "objective": "do it"}
|
|
a.feed({"type": "text", "data": "Here:\n```roboco-draft\n"})
|
|
a.feed({"type": "text", "data": json.dumps(draft)})
|
|
a.feed({"type": "text", "data": "\n```\n"})
|
|
out = a.feed({"type": "end", "sessionId": "s", "stopReason": "EndTurn"})
|
|
assert "draft" in _kinds(out)
|
|
draft_chunk = next(c for c in out if c.kind == "draft")
|
|
assert draft_chunk.data["title"] == "Build X"
|
|
|
|
|
|
def test_unknown_event_types_are_ignored() -> None:
|
|
a = _StreamAssembler()
|
|
assert a.feed({"type": "tool", "name": "whatever"}) == []
|
|
assert a.feed({"type": "", "data": "x"}) == []
|
|
|
|
|
|
def test_parse_event_is_tolerant() -> None:
|
|
assert _parse_event('{"type":"text","data":"x"}') == {"type": "text", "data": "x"}
|
|
assert _parse_event("not json") is None
|
|
assert _parse_event("[1,2,3]") is None # not a dict
|
|
|
|
|
|
def test_classify_failure_detects_rate_limit() -> None:
|
|
msg = _classify_failure(1, "xAI error: 429 too many requests")
|
|
assert "rate-limited" in msg.lower()
|
|
|
|
|
|
def test_classify_failure_generic_uses_last_stderr_line() -> None:
|
|
msg = _classify_failure(2, "warming up\nboom: the model exploded")
|
|
assert "boom: the model exploded" in msg
|
|
# With no stderr, the exit code is surfaced.
|
|
assert "exit code 2" in _classify_failure(2, "")
|