refactor(agent): delegate reusable harness mechanics - #5524
Conversation
Co-authored-by: Medulla <medulla@tinyhumans.ai>
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: ⛔ Files ignored due to path filters (2)
📒 Files selected for processing (4)
📝 WalkthroughWalkthroughThe change delegates queue operations and chat-template rejection detection to TinyAgents. It removes the local ChangesHost integration changes
Estimated code review effort: 3 (Moderate) | ~20 minutes Poem Poem
🚥 Pre-merge checks | ✅ 3 | ❌ 2❌ Failed checks (2 warnings)
✅ Passed checks (3 passed)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Co-authored-by: Medulla <medulla@tinyhumans.ai>
|
Note GitHub couldn't provide a complete incremental comparison for this pull request, so CodeRabbit is performing a full review instead. This review may take a little longer. |
Co-authored-by: Medulla <medulla@tinyhumans.ai>
Co-authored-by: Medulla <medulla@tinyhumans.ai>
Co-authored-by: Medulla <medulla@tinyhumans.ai>
Co-authored-by: Medulla <medulla@tinyhumans.ai>
Co-authored-by: Medulla <medulla@tinyhumans.ai>
Co-authored-by: Medulla <medulla@tinyhumans.ai>
Co-authored-by: Medulla <medulla@tinyhumans.ai>
Co-authored-by: Medulla <medulla@tinyhumans.ai>
…to-tinyagents # Conflicts: # scripts/kernel-floor.limits # src/openhuman/config/migration_helpers/ops.rs
Co-authored-by: Medulla <medulla@tinyhumans.ai>
Co-authored-by: Medulla <medulla@tinyhumans.ai>
Co-authored-by: Medulla <medulla@tinyhumans.ai>
Co-authored-by: Medulla <medulla@tinyhumans.ai>
Summary
mainProblem
OpenHuman still owned provider-neutral queue storage and local-runtime error-recognition logic. That blurred the kernel boundary and made other TinyAgents hosts duplicate harness mechanics.
Solution
The host now maps its product-specific
QueueModeandQueuedMessageinto TinyAgents' payload-generic queue. The inference compatibility module re-exports the TinyAgents classifier, while UI remediation remains in OpenHuman. The public OpenHuman behavior and wire surface are unchanged.TinyFlows 0.6.1 reached
mainas a gitlink-only change, so path-based Rust CI did not exercise its newshellcapability andNodeKind. This PR keeps shell execution disabled by wiringshell: Noneuntil OpenHuman has a policy-aware adapter, while updating workflow authoring and node-contract surfaces to recognize shell nodes. It also refreshes both Cargo locks and gives the RSS fixture's debug test an explicit worker stack so the upgraded graph is exercised reliably.Submission Checklist
Impact
No user-visible or wire-level change. Desktop, CLI, and embedded core retain the same queue semantics and error remediation. Shell workflow execution remains unavailable unless and until OpenHuman supplies an explicit policy-aware adapter. The TinyAgents dependency PR must merge before this PR.
Related
AI Authored PR Metadata
Commit & Branch
move-agent-inference-to-tinyagentsb3b23502d906952a8fb295d8ae938f56fb6c1a35Validation Run
cargo clippy --all-targets --all-features -- -D warnings;cargo build --all-targets;cargo test --all-featuresBehavior Changes