Raven Scott
f5e9473f7b
Add second-wave agent capabilities for initd/journal/network/IPC diagnostics, allowlisted maintenance + contract-check automation, and policy-gated HRPC bridge actions with emergency-stop controls. Harden xAI provider support by applying provider-aware request defaults, parsing reasoning-summary/tool-call streaming variants, and updating seeded docs/skills/tests to reflect max-autonomy safeguards and trace-first observability.
1.4 KiB
1.4 KiB
name, version, description, tags, requires
| name | version | description | tags | requires | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| xai-compat | 1.0.0 | Keep agent requests and tool loops compatible with xAI chat/responses semantics, reasoning summaries, and streaming behavior. |
|
|
xai-compat
Use this skill when provider is xai or when debugging xAI tool/reasoning behavior.
Baseline configuration
- Ensure:
provider = "xai"rest_base_url = "https://api.x.ai/v1"
- Prefer
reasoning_mode = "trace"for observability when summaries are sparse. - Keep
stream = truefor tool-call visibility and progressive diagnostics.
Tool calling expectations
- xAI supports OpenAI-compatible function tools on chat completions.
parallel_tool_callscan be enabled; process all returned tool calls before continuing.- Keep tool schemas explicit and bounded.
Reasoning expectations
- Reasoning models may expose
reasoning_contentsummaries, but availability can vary by model/endpoint. - In trace mode, rely on local process lines even when no reasoning summary deltas arrive.
Debug checklist
- Verify provider/base URL in
~/.agent/config.json. - Run with
reasoning_mode=trace. - Check for tool-call chunks and usage tokens in stream output.
- If reasoning deltas are absent, treat this as provider/model behavior and continue with trace-level progress lines.