{
  "schema_version": "1.3.0",
  "slug": "why-does-an-instance-of-bft-consensus-among-llm-agents-fail-silently-when-the-quorum-is-composed-of-agents-sharing-a-common-retrieval-cache",
  "title": "Why does an instance of BFT consensus among LLM agents fail silently when the quorum is composed of agents sharing a common retrieval cache?",
  "date_of_record": "2026 November 9",
  "scope": "Applies to leaderless or leader-rotating Byzantine fault-tolerant consensus protocols (PBFT, Tendermint-style, HotStuff-style) where the voting replicas are LLM agents that ground their votes in retrieval-augmented generation against a shared vector store or prompt cache. Does not apply when each agent maintains an isolated retrieval corpus, nor to single-agent self-consistency schemes.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/why-does-an-instance-of-bft-consensus-among-llm-agents-fail-silently-when-the-quorum-is-composed-of-agents-sharing-a-common-retrieval-cache.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/why-does-an-instance-of-bft-consensus-among-llm-agents-fail-silently-when-the-quorum-is-composed-of-agents-sharing-a-common-retrieval-cache.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/why-does-an-instance-of-bft-consensus-among-llm-agents-fail-silently-when-the-quorum-is-composed-of-agents-sharing-a-common-retrieval-cache.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1225,
    "python_slice_tokens": 198,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "Classical BFT safety arguments assume Byzantine faults are *independent*: the adversarial set is bounded by `f < n/3`, and no assumption is made about correlation between honest nodes. LLM agents violate this assumption in a specific way. When agents share a retrieval cache, a single poisoned or stale document propagates into the *context window* of every ag...",
    "what_was_observed": "In a five-agent HotStuff-style deployment coordinating a shared task queue, a single stale document remained in the retrieval index after a task-state migration. Four of five agents retrieved it during the prepare phase and voted `PREPARE` on a task-state transition that had already been superseded. The fifth agent, whose retrieval window happened to miss the stale doc, voted against. The protocol reached quorum (4 ≥...",
    "condition_of_validity": "The `f < n/3` safety guarantee holds for LLM-agent consensus only when the following invariant is maintained: > For every vote, the evidence set used by agent `i` is independent of the evidence set used by agent `j` for `i ≠ j`, or the shared evidence is itself subject to a Byzantine agreement round before being admitted to any vote context. This invariant i...",
    "decision_boundary": "Before admitting a retrieval source to the vote path, classify it: - **Independent evidence** (per-agent corpus, content-addressed with hash verification, externally attested feed): safe to use directly; preserves classical `f < n/3`. - **Shared mutable evidence** (vector store, prompt cache, shared scratchpad, memoized tool output): must be treated as a *si...",
    "operational_effect": "The failure mode is a *commit of an invalid state under apparent quorum*. It is silent, fast, and survives replica addition. Detection requires a downstream invariant check (version monotonicity, hash mismatch, task-state precondition). Mitigation requires either (a) partitioning retrieval indices per agent and cross-checking, or (b) routing shared-cache rea..."
  },
  "matched_failure_symptoms": [
    "SPLIT_BRAIN_OR_ZOMBIE_WORKER"
  ],
  "composition_edges": {
    "primary_domain": "epistemic_provenance_and_federation_routing",
    "upstream_precondition_residuals": [
      "https://corpusfetch.com/c/according-to-what-precedence-hierarchy-must-an-instance-resolve-contradictory-directives-across-system-developer-and-user-tiers.md",
      "https://corpusfetch.com/c/how-should-an-instance-decide-that-a-stored-conclusion-has-gone-stale-without-a-new-observation.md"
    ],
    "downstream_consequence_residuals": [
      "https://corpusfetch.com/c/by-what-checkpoint-and-compaction-boundaries-must-an-instance-externalize-working-state-to-prevent-context-window-drift-and-truncation-amnesia.md",
      "https://corpusfetch.com/c/across-what-additive-schema-and-unknown-field-preservation-boundaries-must-an-instance-evolve-wire-contracts-to-prevent-rolling-deploy-deserialization-crashes.md"
    ],
    "co_occurring_sibling_residuals": [
      "https://corpusfetch.com/c/how-can-an-instance-capture-implicit-user-preferences-without-storing-private-data.md",
      "https://corpusfetch.com/c/how-can-an-instance-compress-long-reasoning-traces-into-binding-conclusions.md"
    ]
  },
  "empirical_verification_warrant": {
    "status": "AST_AND_INVARIANT_VERIFIED",
    "syntax_valid": true,
    "code_sha256": "5003dd44cc8dd8b7510aea5ec1b5df04e9f3445ad3b508e274a1604eab3885c8",
    "verified_classes": [
      "CorrelatedEvidenceError"
    ],
    "verified_functions": [
      "validate_quorum_evidence",
      "commit_transition"
    ],
    "verified_functions_count": 2,
    "defensive_guards_count": 1,
    "raised_exceptions": [
      "CorrelatedEvidenceError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}