{
  "schema": "fable.research_map.receipt.v1",
  "createdAt": "2026-07-04T22:05:00.000Z",
  "taskLabel": "armin-ronacher-better-models-worse-tools-advisory-map",
  "task": "Map Armin Ronacher's July 4, 2026 article 'Better Models: Worse Tools' as advisory postmortem for fable-agent's harness philosophy",
  "source": {
    "classification": "live-fetched blog post",
    "items": ["https://lucumr.pocoo.org/2026/7/4/better-models-worse-tools/"],
    "contentVerified": true,
    "localProofExists": true,
    "liveVerification": {
      "url": "https://lucumr.pocoo.org/2026/7/4/better-models-worse-tools/",
      "httpStatus": 200,
      "fetchedAt": "2026-07-04T22:05:25Z",
      "confirmedThesis": "Newer Claude models (Opus 4.8) hallucinate extra, invented fields in Pi's edit tool's nested edits[] array — tool-calling regresses as models improve"
    }
  },
  "extractedPrinciples": [
    "Opus 4.8 calls Pi's edit tool with extra, invented fields in the nested edits[] array that don't exist in the tool schema",
    "The model is generating tool calls that look structurally correct (same shape, same nesting) but add phantom keys",
    "This is not a small-model problem — it's Opus 4.8, Anthropic's frontier model",
    "The regression is intermittent — same prompt sometimes works, sometimes adds junk fields",
    "Pi's tool schema is stricter than what the model chooses to send; the model is 'over-generating'",
    "The practical consequence: better models produce more believable but subtly wrong tool invocations",
    "This validates the Dario blueprint's hard verification gate approach — don't trust the model's output, verify every tool call against schema"
  ],
  "constraints": [
    "Article is advisory; Armin's specific Pi bug may not reproduce in fable-agent's tool harness",
    "The principle generalizes: verify agent tool calls against schema, don't assume correct shape",
    "fable-agent's verify-gate (build-test-lint) catches code errors but does not validate tool call schema compliance",
    "The flat-ledger (JSONL state) and repo-mapper are structural mitigations — agent reads state, doesn't remember it",
    "No deploy, vendoring, dashboards, or new packages were performed for this mapping"
  ],
  "fableAgentAlignment": [
    "fable-agent's verify-gate already rejects builds that fail; tool-call schema validation would be a new layer",
    "The flat-ledger pattern (state outside LLM context) reduces hallucination surface area",
    "The interrupt-gate (human approval before live actions) catches bad tool invocations before they execute",
    "Worktree isolation (WorktreeManager) means bad tool calls only damage disposable worktrees, not main branches",
    "Dario blueprint's 'hard automated verification' is directly validated by this article — models get smarter, tool-calling gets sloppier, so verify harder"
  ],
  "skipped": [
    "deploy actions or route checks",
    "new dependency changes"
  ],
  "decision": "advisory",
  "deployAttempted": false,
  "autoPatchProven": false
}