Roland 84883c36f6 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>		2026-09-13 20:10:16 -06:00
..
test	ai: the /api/chat agent loop — SSE streaming, modes, tool execution	2026-09-13 20:10:16 -06:00
__init__.py	ai: package llama-server for all three deployments, with idle unload	2026-09-13 20:10:16 -06:00
agent.py	ai: the /api/chat agent loop — SSE streaming, modes, tool execution	2026-09-13 20:10:16 -06:00
api.py	ai: the /api/chat agent loop — SSE streaming, modes, tool execution	2026-09-13 20:10:16 -06:00
catalog.py	ai: ai.yaml config, model catalog, and the GGUF downloader	2026-09-13 20:10:15 -06:00
chat.py	ai: the /api/chat agent loop — SSE streaming, modes, tool execution	2026-09-13 20:10:16 -06:00
config.py	ai: ai.yaml config, model catalog, and the GGUF downloader	2026-09-13 20:10:15 -06:00
conftest.py	ai: ai.yaml config, model catalog, and the GGUF downloader	2026-09-13 20:10:15 -06:00
controller_client.py	ai: package llama-server for all three deployments, with idle unload	2026-09-13 20:10:16 -06:00
downloader.py	ai: ai.yaml config, model catalog, and the GGUF downloader	2026-09-13 20:10:15 -06:00
errors.py	ai: system endpoints — aggregate status, services, logs, disks	2026-09-13 20:10:15 -06:00
help_docs.py	ai: help-docs search — Help mode tools	2026-09-13 20:10:15 -06:00
lib.py	ai: add the /api/ai blueprint, the read-only LLM tool catalog	2026-09-13 20:10:15 -06:00
modes.py	ai: the /api/chat agent loop — SSE streaming, modes, tool execution	2026-09-13 20:10:16 -06:00
schema.py	ai: the /api/chat agent loop — SSE streaming, modes, tool execution	2026-09-13 20:10:16 -06:00
service.py	ai: package llama-server for all three deployments, with idle unload	2026-09-13 20:10:16 -06:00