feat: validator, bundle builder and release checks for 0.1.0

- Add tools/validate.py: validates packages, and with --correction runs
  proposed corrections through the gate against a package without
  writing anything (spec/11 §11.4). The gate now refuses a proposal that
  fails the correction schema, rule correction.schema.
- tools/load.py validates every package before loading, and with
  --bundle --built-from builds a scienting-bundle/1 with the FTS5 search
  index and bundle_meta (spec/13 §13.5). Search rows are defined per
  unit (sentence, cell, equation outside a sentence, figure-text) with
  the parent kind as context.
- Roster keys carry a role, and a key with the role owner may revoke any
  receipt (spec/08 §8.7, spec/20); roster schema, store table and the
  fixture roster updated. The checker signs a trial revocation to prove
  the rule both ways.
- A qa: receipt raises the nodes it sampled except those in its errors
  (spec/08 §8.2); the example paper's fidelity counts become 27 F3,
  13 F2, 4 F1 and 1 F0.
- The destination chooses the keyed scheme, not the text policy:
  hmac-team between the team's machines, hkdf-pages outside the team
  (spec/05 §5.8, spec/12 §12.5).
- A TextQuoteSelector must repeat the anchor's plain quote and is absent
  for hashed or keyed anchors (spec/18 §18.3).
- Add fixtures/records/suspect.json, a scienting-suspect/1 record.
- Oracle: hashes are kept incrementally and checked after every
  correction against a full recomputation; load and write refuse unsafe
  manifest paths; Ed25519, HKDF and schema validation come from the
  cryptography and jsonschema packages; canonical JSON uses the built-in
  encoder with an exact RFC 8785 fallback.
- The tools need Python 3.14 with cryptography and jsonschema; the py310
  CI environment is dropped and the workflow runs the default only.
- Resolve every [CHECK] note in the docs, READMEs and context; add
  CONTRIBUTING.md; every tool answers --help and refuses unknown options.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

tools/oracle/package.py

@@ -7,6 +7,7 @@ import base64
 import json
 import os
 import posixpath
+import re
 
 from . import crypto, hashing, jcs, receipts as R
 from .anchors import ADDRESS_RE
@@ -46,8 +47,11 @@ def witness_id(sha):
     return letter_first(bytes.fromhex(sha), 7)
 
 
+SHA256_RE = re.compile(r"[0-9a-f]{64}")
+
+
 def safe_path(p):
-    if not p or p.startswith("/") or "\\" in p or "\x00" in p:
+    if not isinstance(p, str) or not p or p.startswith("/") or "\\" in p or "\x00" in p:
         return False
     parts = p.split("/")
     return all(x not in ("", ".", "..") for x in parts) and posixpath.normpath(p) == p
@@ -58,6 +62,9 @@ def write(root, files, absent=()):
 
     Returns the package hash.
     """
+    for path in list(files) + [a["path"] for a in absent]:
+        if not safe_path(path) or path == "MANIFEST.json":
+            raise Refusal("package.path.unsafe", "unsafe path %r" % path)
     os.makedirs(root, exist_ok=True)
     entries = [dict(a) for a in absent]
     for path in sorted(files, key=lambda p: p.encode("utf-8")):
@@ -374,10 +381,23 @@ def _validate(root, store, key, rep):
             if qa["sample"] != R.sample(orig, seed, qa["rate"], qa["minimum"]):
                 rep.add("doc.qa.sample", r["id"], "the sample does not follow from the seed")
     if roster and not withheld:
-        lv = R.effective_levels(nodes, vals, recs, roster)
-        if R.distribution(lv) != document["fidelity"]:
+        if R.distribution(R.effective_levels(nodes, vals, recs, roster)) != document["fidelity"]:
             rep.add("doc.fidelity.report", "document.json", "the fidelity distribution does not recompute")
 
 
+def read_state(root):
+    """The current state of the package at `root`, for the gate (spec/11 §11.4): nodes without their values,
+    the ID table and the corrections applied so far. Validate the package first."""
+    from .corrections import State
+    present = {f["path"] for f in read_json(os.path.join(root, "MANIFEST.json"))["files"]}
+
+    def jl(name):
+        return read_jsonl(os.path.join(root, name)) if name in present else []
+
+    values = ("text_hash", "match_hash", "align_key", "own_hash", "node_hash")
+    nodes = [{k: v for k, v in n.items() if k not in values} for n in jl("nodes.jsonl")]
+    return State(read_json(os.path.join(root, "document.json"))["key"], nodes, jl("ids.jsonl"), jl("corrections.jsonl"))
+
+
 def n_root_hash(nodes, doc):
     return {n["id"]: n for n in nodes}[doc.root]["node_hash"]