Commit graph

2 commits

Author SHA1 Message Date
Roland
f49ae3aee5
ai: live-chat fixes from first real-model run
Three findings from running Qwen3-1.7B against the docker stack:
the llm image lost libgomp when the build tools were removed
(llama-server needs the OpenMP runtime); the Help prompt let the
small model answer from memory instead of the docs, so it now
requires search_help before any answer; and help search results
called the slug "doc" while get_help_doc's argument is "slug", so
the model invented slugs — the names now match.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-09-24 18:23:23 -06:00
Roland
c7bdedea09
ai: the /api/chat agent loop — SSE streaming, modes, tool execution
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>
2026-09-24 18:23:21 -06:00