CREDO23 2b7d91aa03 feat(automations): add create_automation HITL tool (NL → draft → approve → save) ... Single tool exposed to the main agent. The main agent passes a natural-language `intent`; a focused drafter sub-LLM turns it into a full AutomationCreate JSON; that JSON is surfaced via request_approval (action_type "automation_create") so the user can edit/approve it on a frontend card; on approval the tool persists via AutomationService. Three phases, one tool call. Scope split: - main agent sees only `intent: str` (no schema knowledge leaks into the calling graph) — prompt fragments scoped accordingly. - drafter sub-LLM owns the schema + few-shot intent→JSON examples — lives in the generating graph's prompt (tools/automation/prompt.py). Files: - main_agent/tools/automation/{create.py, prompt.py, __init__.py}: new tool + drafter system prompt with two few-shot intent→JSON examples. - system_prompt/prompts/tools/create_automation/{description.md, example.md}: intent-only guidance for the main agent. - main_agent/tools/index.py: add create_automation to the main-agent allowlist. - new_chat/tools/registry.py: deferred-import factory to break the multi_agent_chat ↔ registry cycle; one ToolDefinition entry.		2026-05-28 00:12:02 +02:00
..
main_agent	feat(automations): add create_automation HITL tool (NL → draft → approve → save)	2026-05-28 00:12:02 +02:00
middleware	feat(agents): track subagent invocation telemetry	2026-05-22 13:48:57 +05:30
subagents	fix: resolve desktop KB prompt self-contradiction on chunk_ids	2026-05-22 17:24:57 +02:00
__init__.py	fix(stream): route every agent (re)build through one helper to prevent factory drift	2026-05-05 23:35:23 +02:00
constants.py	multi_agent_chat/subagents: dict-keyed middleware_stack + always-on KB	2026-05-12 18:04:54 +02:00