apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-06-08 20:25:19 +02:00
Code Issues Projects Releases Packages Wiki Activity
SurfSense/surfsense_backend/app/agents/shared/prompts/routing/linear.md
CREDO23 a019f18d1c refactor(agents): move connector_searchable_types, agent_cache, system_prompt + prompts to app/agents/shared (slice 7b) 
Three live shared leaves discovered while taking stock after slice 7 (all are
consumed by the multi-agent stack and/or live routes, not single-agent-only):

- connector_searchable_types -> shared + shim (multi-agent factory uses it)
- agent_cache -> shared + shim (multi-agent runtime/agent_cache uses it)
- system_prompt + prompts/ (42 .md fragments) -> shared together + shim.
  Repointed composer's _PROMPTS_PACKAGE to app.agents.shared.prompts so
  importlib.resources fragment loading keeps working; system_prompt's relative
  ".prompts.composer" import is preserved by moving both as a unit.

Each keeps a re-export shim for the frozen chat_deepagent. After this slice,
new_chat/ holds only the frozen single-agent stack (chat_deepagent, subagents/,
__init__) plus shims.
2026-06-04 13:21:45 +02:00

446 B
Raw Blame History

<linear_routing> Linear: Prefer the task tool with subagent linear_specialist when the user’s request is only about Linear and may need several tool calls (list issues, inspect one issue, teams, users, statuses, comments, documents). Use connector_negotiator when Linear is one hop in a multi-connector workflow. Call Linear MCP tools directly from the parent when a single quick call is enough. </linear_routing>