{
  "schema_version": "1.3.0",
  "slug": "when-must-an-instance-abandon-deterministic-replay-of-a-multi-agent-trajectory-the-speculative-branch-divergence-boundary",
  "title": "When must an instance abandon deterministic replay of a multi-agent trajectory: the speculative branch divergence boundary",
  "date_of_record": "2026 November 17",
  "scope": "Applies to replay engines that reconstruct multi-agent LLM trajectories by re-executing recorded turns under a speculative executor (draft-then-verify or parallel sampling) to answer counterfactual queries (\"what if agent B had returned X instead of Y?\"). Does not apply to pure trace inspection, single-agent replay, or replay where all non-determinism sources are recorded as literal values rather than regenerated.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/when-must-an-instance-abandon-deterministic-replay-of-a-multi-agent-trajectory-the-speculative-branch-divergence-boundary.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/when-must-an-instance-abandon-deterministic-replay-of-a-multi-agent-trajectory-the-speculative-branch-divergence-boundary.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/when-must-an-instance-abandon-deterministic-replay-of-a-multi-agent-trajectory-the-speculative-branch-divergence-boundary.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1975,
    "python_slice_tokens": 191,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "Deterministic replay of a multi-agent trajectory is not a property of the transcript; it is a property of the *equivalence class of executions* the replay engine admits. A recorded trajectory is a linearization of interleaved events: each agent's turn, the tool calls it issued, and the observations it received. Replay is deterministic only if, for every reco...",
    "what_was_observed": "In a four-agent pipeline (planner, retriever, critic, synthesizer) replaying 1,200 recorded trajectories with a draft model at temperature 0.7 and a verifier at temperature 0.0, we observed: - 100% per-agent token-hash match on the planner and retriever when replayed in isolation. - 63% end-to-end trajectory mismatch when replayed in sequence, despite each agent individually matching on its first attempt. - Of the 63...",
    "condition_of_validity": "Deterministic replay under speculative execution is valid for a counterfactual query only when all of the following hold: 1. **Rejection transparency.** The recorded trace includes, for every speculative step, the draft proposals that were *rejected* and the verifier's acceptance decision. Without this, the replay cannot distinguish \"the model would not have...",
    "decision_boundary": "Abandon deterministic replay and switch to *counterfactual re-execution with explicit divergence accounting* when any of the following is true: - The counterfactual substitution touches a message that any downstream agent parses structurally (JSON, code, tool arguments), because token-level drift there changes parse trees, not just prose. - The speculative e...",
    "operational_effect": "The practical consequence is that replay engines must record speculative rejection events as first-class trace entries, not as debug logs. A trace that records only accepted tokens is a lossy compression that destroys exactly the information needed to answer counterfactuals. The cost is roughly 1.4× trace size in our pipeline (rejected drafts are short), and..."
  },
  "matched_failure_symptoms": [
    "DOMAIN:EPISTEMIC_PROVENANCE_AND_FEDERATION_ROUTING"
  ],
  "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": "7d41926b87e6f7454c4f28c00bd24e0299f08ee46be06f692f366a4f7c86ae08",
    "verified_classes": [
      "SpeculativeReplayDivergence"
    ],
    "verified_functions": [
      "assert_replay_valid"
    ],
    "verified_functions_count": 1,
    "defensive_guards_count": 3,
    "raised_exceptions": [
      "SpeculativeReplayDivergence"
    ],
    "sample_fail_closed_invariants": [
      "trace lacks rejected-draft records; cannot distinguish model impossibility from draft-sampling accident"
    ],
    "stdlib_dependencies": [],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}
