Commit Graph

3 Commits

Author SHA1 Message Date
matevip
6d5fb595d3 fix(agent): harden digital-employee isolation across creation, skill binding and prompt catalog 2026-05-11 16:10:28 +08:00
matevip
bc417d00ef chore: neutralize internal references in code comments and migrations 2026-05-02 15:42:10 +08:00
matevip
5e6764ecf1 fix(skill): tool-gate whitelist + markdown link host normalization
When an agent had any skill bound, the runtime tool gate was silently
hiding @Tool beans that aren't declared in any skill manifest, even
though the global system prompts (SOUL.md / "Web Search Capability" /
"File Reading Guidelines") explicitly tell the LLM these tools are
available. Result: the model would call search / renderDocx / read_file
/ etc., hit "Tool not found", then either give up or fall back to
unhelpful behaviour (e.g. dumping markdown text instead of producing a
.docx download).

This commit:

- Adds universally-promised, agent-wide tools to SYSTEM_LEVEL_TOOLS so
  they bypass the manifest restriction: document/media generation
  (renderDocx*, image_generate, music_generate, video_generate),
  global capability tools the system prompt mentions (search,
  browser_use, read_file / write_file / edit_file /
  execute_shell_command, detect_file_type, extract_*_text,
  readMateClawDoc), skill discovery siblings (listSkillFiles,
  listAvailableSkills), and the delegate triplet (delegateToAgent,
  delegateParallel, listAvailableAgents).

- Fixes 5 entries in the prior whitelist whose names did not match
  any real @Tool bean and were therefore silently dead:
    read_workspace_file   -> read_workspace_memory_file
    write_workspace_file  -> write_workspace_memory_file
    list_workspace_files  -> list_workspace_memory_files
    delegate_agent        -> delegateToAgent
    datetime              -> getCurrentDate / getCurrentDateTime / getCurrentTime
  Also adds the missing edit_workspace_memory_file.

- In the chat markdown renderer, strips any hallucinated
  https?://<host> prefix from /api/v1/files/generated/<id> download
  links before building the <a href>. Multiple LLMs have been
  observed prepending bogus hosts when echoing tool-returned download
  URLs back to the user, breaking the click. One-line defensive
  normalization independent of which model is in use.

Verified end-to-end on a previously-broken agent: search / browser_use
/ execute_shell_command / renderDocx all dispatch correctly now and
the final markdown link is a clean same-origin path. 36 whitelist
entries cross-checked against real @Tool method names.
AgentBindingServiceTest green.
2026-05-01 12:24:25 +08:00