Renn F ff8867dd1f fix(grok): stop opencode subagent-stream hang at the config layer ...

The Grok pr_reviewer wedged in_progress forever: opencode's default agent ran
with the subagent `task` tool enabled, spawned an Explore subagent on
grok-build-0.1 whose model call opened an SSE stream that went idle, and the
run hung with no timeout.

- Hard-disable opencode's subagent `task` tool in the generated opencode.json.
  No RoboCo role uses opencode-internal subagents — work flows through the
  gateway verbs — so removing the tool kills the hang trigger outright.
- Set provider.xai.options.timeout + chunkTimeout (operator-tunable via
  ROBOCO_GROK_REQUEST_TIMEOUT_MS / ROBOCO_GROK_CHUNK_TIMEOUT_MS) as the
  defence-in-depth backstop; chunkTimeout aborts an idle stream.
- Bundle the permission + timeout + subagent knobs into an OpencodeGuards
  dataclass (keeps the builder under the arg-count gate).
- Drop the dead ROBOCO_AGENT_TOOLS spawn env (it had no consumer); opencode
  tool restriction lives in the rendered config now.

2026-06-18 11:31:13 +02:00

..

test_metrics_holder.py

100% Coverage

2026-05-06 21:02:31 +02:00

test_opencode_config.py

fix(grok): stop opencode subagent-stream hang at the config layer

2026-06-18 11:31:13 +02:00

test_opencode_usage.py

fix(grok): correct opencode provider (Responses API), stdin, reasoning cost

2026-06-18 09:57:20 +02:00

test_probe_ollama_tags.py

[3cc1729c] Add self-hosted LLM provider with dynamic model discovery (#128)

2026-06-13 08:38:31 +02:00

test_providers.py

fix(grok): stop opencode subagent-stream hang at the config layer

2026-06-18 11:31:13 +02:00

test_toon_adapter.py

100% Coverage

2026-05-06 21:02:31 +02:00