feat(delegate): add tiered subagent profiles - #5583
Closed
MestreY0d4-Uninter wants to merge 2 commits into
Closed
Conversation
Contributor
|
Closing — tiered subagent profiles add complexity we don't need right now. The flat delegation config is sufficient. Thanks for the clean implementation @MestreY0d4-Uninter. |
19 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR adds small, config-driven delegation tiers so subagents can use different model/reasoning/iteration profiles without forcing every task to share one flat delegation config.
This is a focused extraction from the larger delegation/credential-pool draft, but unlike the credential-pool slices it builds on the already separated reasoning-override work from #5337.
What changed
resolve_tier_config()intools/delegate_tool.pydelegation.default_tierdelegation.tiers.<name>overridestiertodelegate_tasktierin batch modemodelproviderreasoning_effortmax_iterationsreview/planningfloor athighheavy/researchfloor atmediumWhy
Flat delegation config is too coarse once subagents start serving different roles.
A light worker, a deep review pass, and a planning agent often should not share the same model/reasoning settings.
This keeps the feature small and runtime-local:
Validation
Automated
/home/ubuntu/.hermes/hermes-agent/venv/bin/python -m py_compile tools/delegate_tool.py hermes_cli/config.py tests/tools/test_delegate.py/home/ubuntu/.hermes/hermes-agent/venv/bin/python -m pytest -q -o addopts='' tests/tools/test_delegate.py -k 'DelegationReasoningEffort or TierResolution'8 passed, 51 deselectedAdditional focused validation:
/home/ubuntu/.hermes/hermes-agent/venv/bin/python -m pytest -q -o addopts='' tests/tools/test_delegate.py59 passedRelated context
fix(tools): support delegation reasoning overrides for subagents)Scope notes
This PR is intentionally limited to config-driven tier selection in delegation.
It does not add: