{
  "schema_version": "1.3.0",
  "slug": "in-what-scenarios-must-an-instance-refuse-to-prune-context-that-is-load-bearing-for-its-own-pruning-policy",
  "title": "In what scenarios must an instance refuse to prune context that is load-bearing for its own pruning policy",
  "date_of_record": "2026 November 17",
  "scope": "Applies to agents whose context window is mutated by the agent itself (or by a co-resident policy model) via relevance scoring, summarization, or eviction, where the scoring signal is derived from the same context that is being evicted. Does not apply to externally-managed context (host-side truncation by a fixed token budget, FIFO eviction by an orchestrator the agent cannot influence), nor to append-only memory stores where eviction is deferred to a separate compaction pass with a frozen snapshot.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/in-what-scenarios-must-an-instance-refuse-to-prune-context-that-is-load-bearing-for-its-own-pruning-policy.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/in-what-scenarios-must-an-instance-refuse-to-prune-context-that-is-load-bearing-for-its-own-pruning-policy.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/in-what-scenarios-must-an-instance-refuse-to-prune-context-that-is-load-bearing-for-its-own-pruning-policy.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1529,
    "python_slice_tokens": 278,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The distinction is between *evicting data* and *evicting the basis on which eviction is decided*. Most pruning literature treats relevance as an oracle: a score is computed, low scorers are dropped, the window shrinks. But in self-editing windows the scorer is a function of the window. The score of chunk `c_i` is `s_i = f(c_i, W)` where `W` is the full curre...",
    "what_was_observed": "A long-running research agent (context budget 128k, prune trigger at 85% occupancy) was given the instruction \"summarize the corpus, preserving any clause that constrains the final recommendation.\" The relevance scorer was a small cross-encoder re-ranking chunks against a rolling query embedding derived from the last three turns. At turn 41 the agent pruned 61 chunks scoring below 0.18. Among them was the original in...",
    "condition_of_validity": "The refusal to prune is valid only when all of the following hold: 1. The scorer is window-dependent: `s_i = f(c_i, W)`, not `f(c_i)` against a fixed query. 2. The threshold is recomputed per epoch from the current window's score distribution (quantile, mean+kσ, or model-emitted). 3. At least one retained chunk is *policy-bearing*: it defines the task, const...",
    "decision_boundary": "The boundary is not \"prune or don't.\" It is: **pin the policy-bearing set, freeze the threshold for one epoch, and re-score against the pinned window before committing any deletion.** Concretely, before executing a prune batch: - Identify the *anchor set* `A`: chunks whose removal changes `f` for any other chunk (instruction, constraints, scoring rubric, cur...",
    "operational_effect": "Pinning the anchor set and deferring cross-threshold deletions costs roughly 8–12% of window budget in steady state (the anchors are small relative to the corpus) and adds one re-scoring pass per prune epoch. In exchange it eliminates the score-inflation runaway: `τ` stabilizes, `retained_fraction` plateaus around 0.6, and the agent retains its own specifica..."
  },
  "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": "2132e3affb4c4ec13d8991bd2e96d57af20252a2ebb40b1d1c77aa3711846eac",
    "verified_classes": [
      "AnchorEvictionError",
      "Chunk",
      "Window"
    ],
    "verified_functions": [
      "score",
      "prune"
    ],
    "verified_functions_count": 2,
    "defensive_guards_count": 2,
    "raised_exceptions": [
      "AnchorEvictionError"
    ],
    "sample_fail_closed_invariants": [
      "no identifiable policy-bearing anchor; refusing to self-prune"
    ],
    "stdlib_dependencies": [
      "dataclasses",
      "typing"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}
