feat(grok): route interactive intake/secretary to opencode-serve images

Wire the GROK interactive path the in-place way (matching how the interactive
roles already choose ANTHROPIC_* per route), so a GROK route launches the
Grok-native opencode-serve image instead of the Claude SDK-driver image:

- _spawn_intake_container / _spawn_secretary_container pick the
  grok-prompter / grok-secretary image (ensuring the base→grok→interactive
  build chain) when the route is GROK, and stamp provider_type on the spec +
  AgentConfig so finalize routes usage to the opencode store.
- _build_intake_run_cmd / _build_secretary_run_cmd inject OPENAI_* + the
  opencode store mount + system-prompt env for GROK via a shared
  _append_interactive_provider_env, keeping ANTHROPIC_* for every other
  provider. The intake's minimal mounts (no gateway MCP) are preserved, so
  Grok intake matches the Claude intake's tool surface (the spec).
- Add a per-agent opencode store mount to the interactive host paths so
  interactive Grok usage/cost is captured like the one-shot path.

Removes the interim Phase-0 routing guard (the real path supersedes it) and
retires the unused AgentProvider.spawn_interactive/InteractiveSpawnSpec seam —
the interactive roles have a bespoke assembly that the one-shot provider
surface doesn't fit, so the fork lives in their own builders.

UNVERIFIED-LIVE: end-to-end intake/secretary chat on Grok needs the stack up +
opencode serve confirmed against grok-build-0.1.
This commit is contained in:
Renn F
2026-06-18 12:32:41 +02:00
parent 3753fbccc4
commit 0d76ebf586
7 changed files with 211 additions and 205 deletions
-55
View File
@@ -1,55 +0,0 @@
"""AgentProvider interactive scaffolding: opt-in, declines by default."""
from __future__ import annotations
from typing import TYPE_CHECKING
import pytest
from roboco.llm.providers.base import (
AgentProvider,
InteractiveSpawnSpec,
ProviderError,
SpawnResult,
)
if TYPE_CHECKING:
from pathlib import Path
from roboco.models.runtime import OrchestratorAgentConfig as AgentConfig
class _OneShotOnly(AgentProvider):
"""A minimal provider that implements only the one-shot lifecycle."""
async def spawn(
self,
config: AgentConfig,
initial_prompt: str | None = None,
agent_settings_path: Path | None = None,
) -> SpawnResult:
return SpawnResult(instance_id="x")
async def stop(self, instance_id: str, graceful: bool = True) -> None: ...
async def health_check(self, instance_id: str) -> bool:
return True
async def remove(self, instance_id: str) -> None: ...
def _spec() -> InteractiveSpawnSpec:
cfg = type("C", (), {"agent_id": "intake-1"})()
return InteractiveSpawnSpec(
config=cfg, image="img", session_id="s1", role="prompter"
)
def test_provider_declines_interactive_by_default() -> None:
assert _OneShotOnly.supports_interactive is False
@pytest.mark.asyncio
async def test_spawn_interactive_default_raises() -> None:
# A one-shot-only provider declines interactive spawns rather than crashing.
with pytest.raises(ProviderError):
await _OneShotOnly().spawn_interactive(_spec())