[P1] Add skill-aware bounded subagent delegation and reviewer roles #447

New issue

Closed

opened 2026-09-10 21:18:20 +00:00 by nsaspy · 1 comment

nsaspy commented

2026-09-10 21:18:20 +00:00

Owner

Parent: #167
Related: #117, #144, #168, #169

Goal

Compose the existing prompt compiler and bounded rlm_subagent runtime so unresolved work can be delegated to a child with the right selected skill/role context, without inventing another agent runtime.

Target flow

unresolved need
-> prompt compiler resolves applicable skill/role
-> trusted policy chooses delegation when appropriate
-> canonical rlm_subagent invocation
-> narrowed child capabilities + authority
-> bounded selected skill/context projection
-> child result/evidence/usage/trace
-> parent resume/replan

Requirements

reuse rlm_subagent and rlm_agent supervision/cancellation;
skill activation cannot grant or widen child capabilities/authority;
child context is compiled/budgeted through existing prompt/context machinery;
support generic role metadata such as reviewer/critic/researcher without hardcoding product personas;
parent/child correlation and selected-skill provenance are explicit;
propagate evidence/usage/trace references in the return envelope;
global recursion/depth/concurrency/model/token/time budgets remain authoritative;
failure/unavailable/denied/budget/cancelled states remain structured and cannot masquerade as success;
parent can consume a successful child result and continue/replan.

Acceptance

deterministic unresolved fixture selects a skill/role and delegates through canonical rlm_subagent;
child receives only selected bounded skill/context units;
capability and authority ceilings are equal-or-narrower than parent;
selected skill identity/provenance appears in delegation trace/envelope;
evidence and usage propagate back to parent;
generic reviewer/critic role can be represented without a hardcoded persona;
parent resumes/replans after child result;
recursive skill-aware delegation remains globally bounded;
denial/cancellation/budget exhaustion cannot yield false success.

Non-goals

no second subagent runtime;
no product-specific coding reviewer persona;
no skill-based authority grants;
no arbitrary callable in skill or role metadata.

Inspect current merged #144/subagent code and prompt compiler before implementation. Do as much coherent work as possible per cycle.

Parent: #167 Related: #117, #144, #168, #169 ## Goal Compose the existing prompt compiler and bounded `rlm_subagent` runtime so unresolved work can be delegated to a child with the **right selected skill/role context**, without inventing another agent runtime. ## Target flow ```text unresolved need -> prompt compiler resolves applicable skill/role -> trusted policy chooses delegation when appropriate -> canonical rlm_subagent invocation -> narrowed child capabilities + authority -> bounded selected skill/context projection -> child result/evidence/usage/trace -> parent resume/replan ``` ## Requirements - reuse `rlm_subagent` and `rlm_agent` supervision/cancellation; - skill activation cannot grant or widen child capabilities/authority; - child context is compiled/budgeted through existing prompt/context machinery; - support generic role metadata such as reviewer/critic/researcher without hardcoding product personas; - parent/child correlation and selected-skill provenance are explicit; - propagate evidence/usage/trace references in the return envelope; - global recursion/depth/concurrency/model/token/time budgets remain authoritative; - failure/unavailable/denied/budget/cancelled states remain structured and cannot masquerade as success; - parent can consume a successful child result and continue/replan. ## Acceptance - [ ] deterministic unresolved fixture selects a skill/role and delegates through canonical `rlm_subagent`; - [ ] child receives only selected bounded skill/context units; - [ ] capability and authority ceilings are equal-or-narrower than parent; - [ ] selected skill identity/provenance appears in delegation trace/envelope; - [ ] evidence and usage propagate back to parent; - [ ] generic reviewer/critic role can be represented without a hardcoded persona; - [ ] parent resumes/replans after child result; - [ ] recursive skill-aware delegation remains globally bounded; - [ ] denial/cancellation/budget exhaustion cannot yield false success. ## Non-goals - no second subagent runtime; - no product-specific coding reviewer persona; - no skill-based authority grants; - no arbitrary callable in skill or role metadata. Inspect current merged #144/subagent code and prompt compiler before implementation. Do as much coherent work as possible per cycle.

~~nsaspy referenced this issue 2026-09-10 21:20:48 +00:00~~

[P1] Add skill-aware bounded subagent delegation and reviewer roles #172

nsaspy commented

2026-09-10 21:21:33 +00:00

Author

Owner

Duplicate of #172 (pre-existing Forgejo mirror). Closing this accidental duplicate created by today's open-state sync; #172 stays canonical on Forgejo.

nsaspy closed this issue

2026-09-10 21:21:34 +00:00