cleveragents/cleveragents-core
4
0
Fork 3
Code Issues 6.0k Pull Requests 115 Actions Packages Projects Releases Wiki Activity

docs(spec): clarify ACMS context tier hydration vs full indexing #7376

Closed
HAL9000 wants to merge 1 commits from spec/arch-acms-tier-hydration into master
pull from: spec/arch-acms-tier-hydration
merge into: cleveragents:master
Conversation 9 Commits 1 Files Changed 1
+24

1 Commits

Author SHA1 Message Date
HAL9000 d8c02ca1f1 docs(spec): clarify ACMS context tier hydration vs full indexing
CI / lint (pull_request) Successful in 36s
Details
CI / build (pull_request) Successful in 23s
Details
CI / push-validation (pull_request) Successful in 29s
Details
CI / helm (pull_request) Successful in 32s
Details
CI / quality (pull_request) Successful in 3m43s
Details
CI / typecheck (pull_request) Successful in 4m24s
Details
CI / security (pull_request) Successful in 4m17s
Details
CI / e2e_tests (pull_request) Successful in 6m11s
Details
CI / integration_tests (pull_request) Successful in 6m39s
Details
CI / unit_tests (pull_request) Successful in 8m20s
Details
CI / docker (pull_request) Successful in 11s
Details
CI / coverage (pull_request) Successful in 10m22s
Details
CI / status-check (pull_request) Successful in 1s
Details
CI / benchmark-publish (pull_request) Has been skipped
Details
CI / benchmark-regression (pull_request) Successful in 57m23s
Details 
The spec's 'Critical Design Decision' stated 'no on-demand indexing during
agent execution', but PR #4219 introduced context_tier_hydrator.py which
does exactly that — populating the in-memory ContextTierService from linked
project resources at the start of each plan execution.

This is a spec-implementation divergence that needed clarification:

- Context tier hydration is a lightweight file-read bridge (not full ACMS
  indexing). It populates the HOT tier with raw file content so the LLM
  has file context during plan execution.
- Full ACMS indexing (UKO ontology graphs, embeddings, persistent index)
  is what the 'no on-demand' principle applies to.
- When the full ACMS pipeline is implemented with persistent index state,
  hydration will be replaced by reading from the persisted index.

Added a note block under the Critical Design Decision explaining the
distinction, the hydration algorithm, and the relationship to the principle.

Refs: issue #7365 (spec update proposal from spec-updater agent),
      PR #4219 (fix(acms): wire ACMS indexing pipeline into CLI)
 2026-04-12 16:43:52 +00:00