@dogfood-lab/study-swarm 1.3.0 → 2.0.0

package/examples/study-swarm-lock.dispatch.md

@@ -120,14 +120,14 @@ Each choice traces to findings by number. The shape:
 }
 ```
 
-- **L1 — One lock per dispatch; the lock IS the dispatch's content-address.** `lock_sha256` binds every per-step record and the verifier block together, so a replay cannot stitch a step from one dispatch onto another. (findings 4, 13, 17, 18)
+- **L1 — One lock per dispatch; the lock IS the dispatch's content-address.** `lock_sha256` binds every per-step record and the verifier block together, so a replay cannot stitch a step from one dispatch onto another — the per-step record carries exactly PROV's minimal lineage quadruple (input hashes, output hashes, actor, rollup link). (findings 4, 13, 17, 18, 25)
 - **L2 — The harness emits the record; the CLI canonicalizes + hashes + validates it.** This producer/verifier split is universal across the provenance literature, and it is what keeps the CLI zero-dependency, network-free, and deterministic — it never calls a model. (findings 17, 19, 21, 22)
 - **L3 — Hash the prompt as normalized text, not JCS-restructured JSON.** The prompt is the literal string the model conditioned on, so it is hashed directly rather than canonicalized as JSON (the JWS/DSSE hash-known-bytes rule) — under one necessary text normalization (BOM strip + CRLF→LF + NFC), without which the same prompt hashes differently across platforms. (findings 12, 23; 10, 11)
 - **L4 — Normalize every text input before hashing (BOM strip + CRLF→LF + NFC), and JCS-canonicalize the structured JSON (tool surface, lock body).** This is the only way the same dispatch hashes identically on Windows, macOS, and Linux — the prompt, the dispatch text, `PROTOCOL.md`, and every JSON string value all pass through it. (findings 9, 10, 11) *(CI caught a real CRLF drift here when an early build hashed raw `PROTOCOL.md` bytes — the fix is exactly this normalization, and a line-ending-invariance test now guards it.)*
-- **L5 — Capture the tool surface as the canonicalized array `{name, description, inputSchema, outputSchema}` plus the effective JSON Schema dialect.** Neither MCP nor the provider APIs ship a per-tool version or hash, so the lock's content hash is the missing drift detector, and the dialect is part of the contract. (findings 7, 33, 34, 35, 37)
+- **L5 — Capture the tool surface as the canonicalized array `{name, description, inputSchema, outputSchema}` plus the effective JSON Schema dialect.** Neither MCP nor the provider APIs ship a per-tool version or hash, so the lock's content hash is the missing drift detector, and the dialect is part of the contract; each captured schema is validated well-formed before hashing, so the lock pins a schema the run could actually have used. (findings 7, 33, 34, 35, 36, 37)
 - **L6 — Pin the RESOLVED model id, never an alias.** A named model can be re-tuned server-side; the concrete platform identity is what makes a step replayable. (findings 19, 29)
 - **L7 — `output_sha256` records outputs for DRIFT DETECTION, not determinism.** Pinning model + prompt + temperature does not yield bit-identical outputs (batch-invariance, FP non-associativity, MoE routing, provider drift), so the honest claim is **"replayable inputs + drift-detectable outputs,"** never "deterministic replay." (findings 8, 19, 26, 27, 28, 30, 31, 32)
-- **L8 — `lock --verify` is fail-closed strict-match.** Re-derive every deterministic hash and assert equality; any mismatch — and any unrecognized field — exits non-zero, never auto-heals. (findings 5, 6, 20, 38)
+- **L8 — `lock --verify` is fail-closed strict-match.** Re-derive every deterministic hash and assert equality; any mismatch — and any unrecognized field — exits non-zero, never auto-heals — the cache-invalidation rule that any change to a folded input re-executes rather than serving a stale hit. (findings 2, 5, 6, 20, 38)
 - **L9 — Self-describing digests + domain separation in the rollup, hashed as one flat canonical array.** Digests carry their algorithm prefix; the canonical JSON object's distinct keys and the array's explicit length supply domain separation and sidestep the odd-leaf-duplication collision class. (findings 14, 15, 24, 38)
 - **L10 — Pin the verifier receipt offline-verifiably.** Store `receipt_id` + `receipt_chain_sha256`; `lock --verify` confirms the verification happened without re-contacting the verifier. The Ed25519 receipt is a stable pin; the ephemeral key buys verifiability, not anti-forgery — stated, not oversold. (findings 16, 21, 22)
 - **L11 — Pin content, not mtimes.** The lock is robust to file-touch noise by construction. (findings 1, 3)

package/examples/study-swarm-lock.lock.json

@@ -1,46 +1,46 @@
 {
-  "schema": "dispatch.lock/v1",
-  "study_swarm_version": "1.3.0",
-  "protocol_sha256": "sha256-seELxwXtj+xVxa3mas2cP0J0iMTTpq4vHqFMiUGqmuU=",
-  "dispatch_sha256": "sha256-mPdwnlPuRlCtky20zG6l5AFJ8iRAZjHISnoGDUuGSOo=",
+  "schema": "dispatch.lock/v2",
+  "study_swarm_version": "2.0.0",
+  "protocol_sha256": "sha256-9tVI9RrD1qKHB/j/Ec9+//Q6y5coRtOvVcfDyiH46eQ=",
+  "dispatch_sha256": "sha256-W4v3ZnQx66bIfL2eCCTdIEgOkcWOw7oMg13rxlbEXuE=",
   "steps": [
     {
       "question_id": "Q1-replay-manifest",
       "resolved_model": "claude-opus-4-8",
-      "prompt_sha256": "sha256-hcdcTxvqJNij0z9ItUPIzQhBWbrVZy3VvY4umPHaM5I=",
-      "tool_schema_sha256": "sha256-kUC7s+wAFV4lzwrFKYp36khxCRQZWlWeFDOwhPIqGCk=",
+      "prompt_sha256": "sha256-S/YE49Ry8VUND0oyNE2ls9NQ8prCfASakEn4VPAE/Yc=",
+      "tool_schema_sha256": "sha256-x6ygSP9mm+7sp06lFaxpe5W3RsNc0h57hz6aHoXPYXo=",
       "schema_dialect": "https://json-schema.org/draft/2020-12/schema",
       "output_sha256": "sha256-k5rkOOyAHGBCVacEk8LPULp+s5YHVzaUyCHJY4tD5jE="
     },
     {
       "question_id": "Q2-canonicalization",
       "resolved_model": "claude-opus-4-8",
-      "prompt_sha256": "sha256-Gj+ri3gWVWxP7M9fv50c0xsgiZ2j3T6kn3A3c3EhSos=",
-      "tool_schema_sha256": "sha256-kUC7s+wAFV4lzwrFKYp36khxCRQZWlWeFDOwhPIqGCk=",
+      "prompt_sha256": "sha256-9ZbmzzaBscf6H4AUj/BRIA8UjG65KtFuMHdkqjucjhA=",
+      "tool_schema_sha256": "sha256-x6ygSP9mm+7sp06lFaxpe5W3RsNc0h57hz6aHoXPYXo=",
       "schema_dialect": "https://json-schema.org/draft/2020-12/schema",
       "output_sha256": "sha256-ymPE5lJqoygN0MpzqftgE1tYlyp7z+poCK2Z1Zj3mi8="
     },
     {
       "question_id": "Q3-provenance-attestation",
       "resolved_model": "claude-opus-4-8",
-      "prompt_sha256": "sha256-g5/dW+zJvMObKyqnAdy70pUPtJcGD0DrsjkeEx/AcIY=",
-      "tool_schema_sha256": "sha256-kUC7s+wAFV4lzwrFKYp36khxCRQZWlWeFDOwhPIqGCk=",
+      "prompt_sha256": "sha256-yUGaXe7X4bRhFHSKtDjxHh3xuPtg1+BmLV6jza4C0fo=",
+      "tool_schema_sha256": "sha256-x6ygSP9mm+7sp06lFaxpe5W3RsNc0h57hz6aHoXPYXo=",
       "schema_dialect": "https://json-schema.org/draft/2020-12/schema",
       "output_sha256": "sha256-OSUAIhytytKihfFM1Y+p1BllUSTC+KEfb/NX86X+Kc0="
     },
     {
       "question_id": "Q4-llm-determinism",
       "resolved_model": "claude-opus-4-8",
-      "prompt_sha256": "sha256-OfQ00IyAulvEOnZ/UpiLp+JTwF4jYUzQRaqCp3zgIbE=",
-      "tool_schema_sha256": "sha256-kUC7s+wAFV4lzwrFKYp36khxCRQZWlWeFDOwhPIqGCk=",
+      "prompt_sha256": "sha256-Pq1qlM2d+twv0Bpj9oKai/wqDgprgbgrX82++lwL01A=",
+      "tool_schema_sha256": "sha256-x6ygSP9mm+7sp06lFaxpe5W3RsNc0h57hz6aHoXPYXo=",
       "schema_dialect": "https://json-schema.org/draft/2020-12/schema",
       "output_sha256": "sha256-aFDm9p4/94p97NJg/vWKbYXchv6N1b0swpIfYoep1iw="
     },
     {
       "question_id": "Q5-tool-schema-drift",
       "resolved_model": "claude-opus-4-8",
-      "prompt_sha256": "sha256-qIr9Dl8GmGeikUrgCJ62QQh8FvTNUhvdxL0Ivk/Di3M=",
-      "tool_schema_sha256": "sha256-kUC7s+wAFV4lzwrFKYp36khxCRQZWlWeFDOwhPIqGCk=",
+      "prompt_sha256": "sha256-M/W3TeerL+sC7rgduBkXme0awKZIGWc12h82tMe22UM=",
+      "tool_schema_sha256": "sha256-x6ygSP9mm+7sp06lFaxpe5W3RsNc0h57hz6aHoXPYXo=",
       "schema_dialect": "https://json-schema.org/draft/2020-12/schema",
       "output_sha256": "sha256-Y1lsUdKoplgdos0r4faN6UgxXX74D/Se0AVHCiUA9dM="
     }
@@ -58,5 +58,5 @@
     "receipt_signature": "272c892124e3bc13a76b2674fa361b1d65aee6a588c74604cf4ae4e7c9440a8ba7888175b9ec1286fe87490121f694f64cd30adc3ffc0e1b31cd3365b7b38901",
     "receipt_chain_sha256": "499b63905064a5e25fd1801c5530504c94742f2183c4d3c8eb545a20cfbb112e"
   },
-  "lock_sha256": "sha256-AOzuFtiRt4iXnsVqEvcB5hms1oO1LcjRrin96aQnUHE="
+  "lock_sha256": "sha256-oNSayaGGWFonFxzME+D1nwB14GsXitSWL7CLD6R9zwM="
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@dogfood-lab/study-swarm",
-  "version": "1.3.0",
+  "version": "2.0.0",
   "description": "Ground design decisions in cited research, then verify every citation with a different model family before it becomes canon — a research-grounded design protocol, with a thin CLI.",
   "keywords": [
     "methodology",