mirror of
https://github.com/lrnselfreliance/wrolpi.git
synced 2026-10-26 19:01:39 -04:00
c7bdedea09
Tool definitions are generated in-process from the /api/ai blueprint's own OpenAPI operations (operationId = tool name, description = tool description, dataclass bodies + declared parameters = one flat JSON schema) — the spec IS the catalog, nothing to drift. Manage endpoints never become tools. A mode is a server-enforced system prompt + tool allowlist (Help / Research / System per ai.md); the executor can only reach allowlisted /api/ai endpoints, path parameters are encoded and traversal-rejected so a crafted argument cannot escape an endpoint. POST /api/chat streams SSE (status/token/tool_call/tool_result/done/ error), starts llama-server on demand, validates tool args server-side with instructive errors the model can retry on, caps tool results with a paging hint, and bounds the loop by ai.yaml max_tool_calls plus a hard timeout. Caddy passes the stream unbuffered (flush_interval -1) in both deployments. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| ai | ||
| archive | ||
| docs | ||
| flasher | ||
| inventory | ||
| map | ||
| videos | ||
| zim | ||
| __init__.py | ||