Task Manifest

Task: 20260831-105429-opencode-loop-guard
Created: 2026-08-31T10:54:29Z
Orchestrator: build
Status: planned
Current owner: coder

Objective

Add a global OpenCode plugin that detects repeated tool-call cycles, blocks the call that completes a detected cycle, and provides corrective feedback to the model. The default behavior is balanced sensitivity, all models, and all tools.

Acceptance Criteria

A global TypeScript plugin is installed at ~/.config/opencode/plugins/loop-guard.ts.
No OpenCode configuration change or dependency install is required because the plugin is auto-discovered and uses only built-in APIs plus existing @opencode-ai/plugin types.
Tool-call history is tracked separately by session ID.
Detection covers cycle lengths 1 through 4.
A cycle is detected only after three complete repetitions, for a minimum of four calls in the repeating pattern.
Object argument key order does not affect signature equality; string values are preserved exactly and not normalized.
The call that completes a qualifying cycle is blocked with an error message that identifies the repeated pattern shape without leaking sensitive arguments and directs the model to reassess evidence and choose a materially different action.
Legitimate repeated calls with changed arguments are allowed.
Session state is bounded and cleared when sessions become idle or deleted.
Focused tests demonstrate cycle detection, false-positive avoidance, session isolation, key-order normalization, and history cleanup.
No secrets, credentials, or sensitive configuration values are added to the repository or artifacts.

Artifact Index

brief.md: implementation contract
implementation.md: coder report (pending)
review.md: reviewer report (pending)
iterations/: correction rounds, if needed
attachments/: raw logs and diagnostic collateral

Iteration Log

2026-08-31T10:54:29Z: Build created task workspace and brief.

Open Risks

Throwing from tool.execute.before is the intended blocking mechanism, but runtime behavior should be verified after restart.
Cycle detection may still produce false positives for genuinely repetitive workflows; thresholds are intentionally conservative.
The plugin cannot recover a model that emits no further tool calls; it can only block repeated calls and provide corrective feedback.

Final Outcome

Pending implementation and review.

2.4 KiB Raw Blame History