feat(loop-context): implement semantic frustration circuit breaker

[THRISHAL12345]

Summary

Introduces a semantic "frustration" circuit breaker to loop-context that detects when an agent loops repeatedly on the same semantic action (even if yielding different errors) and escalates before draining the token budget.

Changes

• New pattern or starter (followed templates/pattern-template.md + updated registry.yaml)
• Doc / example improvement
• Tool change (loop-context)
• Story (includes real failure or surprise + lesson)

Checklist (from CONTRIBUTING)

• All required sections present for patterns
• Links work from README, patterns/README, starters/README, docs/index
• No secrets, tokens, internal company URLs
• STATE.md* examples use .example suffix
• Safety-related content references docs/safety.md
• Ran node tools/loop-audit/dist/cli.js . (or on the starter) and addressed findings

Testing / Dogfood

• loop-audit passes on affected starters or this repo
• Manual review of generated state / skill output
• Added rigorous unit tests in loop-context/test/context-manager.test.mjs verifying semantic similarity triggers.

Screenshots / Examples (if UI or command output)

When an agent repeats semantically similar actions without success, the circuit breaker now outputs:

{
  "shouldContinue": false,
  "escalate": true,
  "trigger": "frustration",
  "reason": "Semantic looping detected: agent repeated highly similar action 3× in a row (threshold 3): \"Try to fix the syntax error\". Escalating.",
  "iterations": 3,
  "tokensUsed": 15000
}

---

[cobusgreyling]

Thanks @THRISHAL12345 — merged; published as loop-context@1.4.0.