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

docs(spec): architecture cycle 25 — model_tier, autonomous shell blocking, in-actor compaction, uncertainty band escalation #6884

Closed
HAL9000 wants to merge 1 commits from spec/architecture-cycle-25-new-features into master
pull from: spec/architecture-cycle-25-new-features
merge into: cleveragents:master
Conversation 19 Commits 1 Files Changed 1
+147

1 Commits

Author SHA1 Message Date
HAL9000 2523ba67c7 docs(spec): architecture cycle 25 — model_tier, autonomous shell blocking, in-actor compaction, uncertainty band escalation
CI / lint (pull_request) Failing after 20s
Details
CI / push-validation (pull_request) Successful in 23s
Details
CI / helm (pull_request) Successful in 23s
Details
CI / build (pull_request) Successful in 36s
Details
CI / quality (pull_request) Successful in 44s
Details
CI / typecheck (pull_request) Successful in 53s
Details
CI / security (pull_request) Successful in 4m9s
Details
CI / coverage (pull_request) Has been skipped
Details
CI / e2e_tests (pull_request) Successful in 4m22s
Details
CI / integration_tests (pull_request) Successful in 4m29s
Details
CI / unit_tests (pull_request) Successful in 8m32s
Details
CI / docker (pull_request) Has been skipped
Details
CI / status-check (pull_request) Failing after 1s
Details
CI / benchmark-publish (pull_request) Has been skipped
Details
CI / benchmark-regression (pull_request) Has been skipped
Details 
Add spec coverage for four new architectural features:

1. Actor node model_tier field: Optional per-node model tier override (cheap/default/frontier)
   in graph route nodes. Tier-to-model mapping via new model.tiers.* config keys.
   Enables cost-optimised actor graphs without hardcoding model names.

2. Autonomous shell blocking: Safety Profile integration with ShellSafetyService.
   When allow_unsafe_tools=false and profile is headless (ci/full-auto), CRITICAL+HIGH
   shell patterns are hard-blocked rather than advisory. TUI remains advisory-only.

3. In-actor conversation history compaction: LangGraph actor runner hook that monitors
   accumulated message history and summarises old turns when threshold exceeded.
   Distinct from ACMS (which handles retrieval); this handles within-session accumulation.
   New actor.compaction.* config keys.

4. Uncertainty band LLM escalation: Optional two-stage AutonomyController augmentation.
   Stage 1 heuristic runs always (zero LLM cost). Stage 2 cheap LLM evaluator activates
   only when score falls within uncertainty band around threshold. Result caching and
   circuit breaker included. New escalation.classifier.* config keys.

Closes: #6765, #6763, #6761, #6760
ISSUES CLOSED: #6765, #6763, #6761, #6760
 2026-04-12 19:01:51 +00:00