present-day 0.14.0__tar.gz

present_day-0.14.0/LICENSE

@@ -0,0 +1,177 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS

present_day-0.14.0/PKG-INFO

@@ -0,0 +1,52 @@
+Metadata-Version: 2.4
+Name: present-day
+Version: 0.14.0
+Summary: Tamper-evident signed memory, provenance and trust for AI agents
+Author: Ruslan Tiahniienko
+License-Expression: Apache-2.0
+Keywords: ai-agents,memory,provenance,ed25519,merkle,mcp
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Security :: Cryptography
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: cryptography>=42
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.2; extra == "mcp"
+Provides-Extra: web
+Requires-Dist: fastapi>=0.110; extra == "web"
+Requires-Dist: uvicorn>=0.27; extra == "web"
+Provides-Extra: saml
+Requires-Dist: python3-saml>=1.16; extra == "saml"
+Provides-Extra: postgres
+Requires-Dist: psycopg[binary]>=3.2; extra == "postgres"
+Requires-Dist: psycopg-pool>=3.2; extra == "postgres"
+Provides-Extra: langchain
+Requires-Dist: langchain-core>=0.3; extra == "langchain"
+Provides-Extra: llamaindex
+Requires-Dist: llama-index-core>=0.12; extra == "llamaindex"
+Provides-Extra: openai-agents
+Requires-Dist: openai-agents>=0.2; extra == "openai-agents"
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == "dev"
+Requires-Dist: httpx>=0.27; extra == "dev"
+Requires-Dist: build; extra == "dev"
+Requires-Dist: twine; extra == "dev"
+Requires-Dist: pip-audit; extra == "dev"
+Requires-Dist: cyclonedx-bom; extra == "dev"
+Dynamic: license-file
+
+# Present Day
+
+Tamper-evident, signed memory for AI agents: a hash-chained Ed25519 ledger, a trust graph with quorum and anti-Sybil rules,
+drift and injection detection, offline-verifiable evidence bundles, a local node, a hosted cabinet, a CLI and an MCP server.
+
+```
+pip install present-day            # core, CLI
+pip install "present-day[mcp]"     # MCP server for Claude Desktop, Cursor, ...
+pip install "present-day[web]"     # hosted cabinet
+present-day init && present-day redteam
+```
+
+Licensed under Apache-2.0.

present_day-0.14.0/PYPI.md

@@ -0,0 +1,13 @@
+# Present Day
+
+Tamper-evident, signed memory for AI agents: a hash-chained Ed25519 ledger, a trust graph with quorum and anti-Sybil rules,
+drift and injection detection, offline-verifiable evidence bundles, a local node, a hosted cabinet, a CLI and an MCP server.
+
+```
+pip install present-day            # core, CLI
+pip install "present-day[mcp]"     # MCP server for Claude Desktop, Cursor, ...
+pip install "present-day[web]"     # hosted cabinet
+present-day init && present-day redteam
+```
+
+Licensed under Apache-2.0.

present_day-0.14.0/pyproject.toml

@@ -0,0 +1,40 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "present-day"
+version = "0.14.0"
+description = "Tamper-evident signed memory, provenance and trust for AI agents"
+requires-python = ">=3.10"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+authors = [{name = "Ruslan Tiahniienko"}]
+readme = "PYPI.md"
+keywords = ["ai-agents", "memory", "provenance", "ed25519", "merkle", "mcp"]
+classifiers = ["Development Status :: 4 - Beta", "Intended Audience :: Developers", "Topic :: Security :: Cryptography"]
+
+dependencies = ["cryptography>=42"]
+
+[project.optional-dependencies]
+mcp = ["mcp>=1.2"]
+web = ["fastapi>=0.110", "uvicorn>=0.27"]
+saml = ["python3-saml>=1.16"]
+postgres = ["psycopg[binary]>=3.2", "psycopg-pool>=3.2"]
+langchain = ["langchain-core>=0.3"]
+llamaindex = ["llama-index-core>=0.12"]
+openai-agents = ["openai-agents>=0.2"]
+dev = ["pytest>=8", "httpx>=0.27", "build", "twine", "pip-audit", "cyclonedx-bom"]
+
+[project.scripts]
+present-day = "present_day.cli:main"
+p7 = "present_day.cli:main"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+present_day = ["web/*", "cloud/web/*"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

present_day-0.14.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

present_day-0.14.0/src/present_day/__init__.py

@@ -0,0 +1,4 @@
+"""Present Day: tamper-evident signed memory and provenance for AI agents (protocol P7)."""
+
+__version__ = "0.14.0"
+PROTOCOL = "P7/1"

present_day-0.14.0/src/present_day/agent.py

@@ -0,0 +1,58 @@
+"""Agent home: the agent's own signing key plus the cabinet connection it should use.
+
+The private key never leaves this directory; the cabinet only ever sees signed entries.
+"""
+
+from __future__ import annotations
+
+import json
+import os
+from pathlib import Path
+
+from .client import CloudClient
+from .crypto import NAME_RE, Identity
+
+
+class AgentError(Exception):
+    pass
+
+
+def default_path() -> Path:
+    return Path(os.environ.get("P7_AGENT_HOME") or Path.home() / ".present-day-agent")
+
+
+class AgentHome:
+    def __init__(self, path: str | Path | None = None):
+        self.path = Path(path) if path else default_path()
+        self.cfg_path = self.path / "agent.json"
+
+    def exists(self) -> bool:
+        return self.cfg_path.exists()
+
+    def init(self, name: str, url: str, token: str, workspace: str) -> Identity:
+        if not NAME_RE.match(name):
+            raise AgentError("name must match [A-Za-z0-9_-]{1,32}")
+        if self.exists():
+            raise AgentError(f"{self.path} is already initialised")
+        self.path.mkdir(parents=True, exist_ok=True, mode=0o700)
+        os.chmod(self.path, 0o700)
+        ident = Identity.generate()
+        ident.save(self.path / "agent.pem", os.environ.get("P7_PASSPHRASE") or None)
+        cfg = {"name": name, "url": url.rstrip("/"), "workspace": workspace, "token": token}
+        fd = os.open(self.cfg_path, os.O_WRONLY | os.O_CREAT | os.O_EXCL, 0o600)
+        with os.fdopen(fd, "w") as f:
+            json.dump(cfg, f, indent=2)
+        return ident
+
+    def config(self) -> dict:
+        try:
+            return json.loads(self.cfg_path.read_text())
+        except (OSError, ValueError) as e:
+            raise AgentError(f"agent not initialised in {self.path}: run `present-day agent init`") from e
+
+    def identity(self) -> Identity:
+        return Identity.load(self.path / "agent.pem", os.environ.get("P7_PASSPHRASE") or None)
+
+    def client(self) -> CloudClient:
+        c = self.config()
+        return CloudClient(c["url"], c["token"], c["workspace"], self.identity())

present_day-0.14.0/src/present_day/backends.py

@@ -0,0 +1,87 @@
+"""Memory backends shared by the MCP server and the framework integrations (no optional dependencies).
+
+* local : a node home on this machine (PRESENT_DAY_HOME, key P7_IDENTITY, default "agent")
+* cloud : a hosted workspace; the agent signs with its own key and authenticates with an API key
+          (P7_AGENT_HOME, created by `present-day agent init`)
+"""
+
+from __future__ import annotations
+
+from .agent import AgentHome
+from .home import Home
+
+
+class LocalBackend:
+    def __init__(self, home: Home, identity_name: str):
+        self.engine, self._home, self._name = home.engine(), home, identity_name
+
+    def _me(self):
+        return self._home.identity(self._name)
+
+    def remember(self, subject, predicate, obj, confidence, source_uri, supersedes) -> dict:
+        e = self.engine.claim(self._me(), subject, predicate, obj, confidence=confidence,
+                              sources=[{"uri": source_uri}] if source_uri else None,
+                              supersedes=[supersedes] if supersedes else None)
+        return {"entry": e.entry_hash, "seq": e.seq}
+
+    def recall(self, subject, predicate, status, limit) -> list[dict]:
+        return self.engine.query(subject=subject or None, predicate=predicate or None,
+                                 status=status or None, limit=limit)
+
+    def attest(self, target, stance, note) -> dict:
+        e = self.engine.attest(self._me(), target, stance, note)
+        return {"entry": e.entry_hash, "seq": e.seq}
+
+    def history(self, subject, predicate) -> list[dict]:
+        return self.engine.history(subject, predicate)
+
+    def provenance(self, entry) -> dict:
+        return self.engine.provenance(entry)
+
+    def verify(self) -> dict:
+        return self.engine.verify()
+
+    def alerts(self) -> list[dict]:
+        return [a.to_dict() for a in self.engine.alerts()]
+
+    def receipt(self, subject, predicate, question, answer) -> dict:
+        return self.engine.answer_receipt(subject, predicate, question, answer, self._me())
+
+    def evidence(self, subject, predicate) -> dict:
+        return self.engine.evidence_for(subject, predicate)
+
+
+class CloudBackend:
+    def __init__(self, agent: AgentHome):
+        self.c = agent.client()
+
+    def remember(self, subject, predicate, obj, confidence, source_uri, supersedes) -> dict:
+        r = self.c.claim(subject, predicate, obj, confidence=confidence,
+                         sources=[{"uri": source_uri}] if source_uri else None,
+                         supersedes=[supersedes] if supersedes else None)
+        return {"entry": r["entry_hash"], "seq": r["seq"]}
+
+    def recall(self, subject, predicate, status, limit) -> list[dict]:
+        return self.c.recall(subject=subject, predicate=predicate, status=status, limit=str(limit))
+
+    def attest(self, target, stance, note) -> dict:
+        r = self.c.attest(target, stance, note)  # signed locally; needs the full 64-hex hash
+        return {"entry": r["entry_hash"], "seq": r["seq"]}
+
+    def history(self, subject, predicate) -> list[dict]:
+        return self.c.history(subject, predicate)
+
+    def provenance(self, entry) -> dict:
+        return self.c.provenance(entry)
+
+    def verify(self) -> dict:
+        return self.c.verify()
+
+    def alerts(self) -> list[dict]:
+        return self.c.alerts()
+
+    def receipt(self, subject, predicate, question, answer) -> dict:
+        return self.c.answer_receipt(subject, predicate, question, answer)
+
+    def evidence(self, subject, predicate) -> dict:
+        return self.c.evidence(subject, predicate)

present_day-0.14.0/src/present_day/canon.py

@@ -0,0 +1,52 @@
+"""Canonical JSON (P7-canon-1): sorted keys, no whitespace, UTF-8, no floats.
+
+Floats are rejected on purpose: their text form is not stable across runtimes,
+which would break signatures. Confidence and similar values are integers.
+"""
+
+from __future__ import annotations
+
+import json
+from typing import Any
+
+
+class CanonError(ValueError):
+    pass
+
+
+_MAX_DEPTH = 32
+_MAX_INT = 2**53
+
+
+def _check(o: Any, depth: int = 0) -> None:
+    if depth > _MAX_DEPTH:
+        raise CanonError("structure too deep")
+    if o is None or isinstance(o, (bool, str)):
+        return
+    if isinstance(o, int):
+        if not -_MAX_INT < o < _MAX_INT:
+            raise CanonError("integer out of range")
+        return
+    if isinstance(o, float):
+        raise CanonError("floats are not allowed; use integers")
+    if isinstance(o, (list, tuple)):
+        for x in o:
+            _check(x, depth + 1)
+        return
+    if isinstance(o, dict):
+        for k, v in o.items():
+            if not isinstance(k, str):
+                raise CanonError("object keys must be strings")
+            _check(v, depth + 1)
+        return
+    raise CanonError(f"unsupported type: {type(o).__name__}")
+
+
+def canonical(o: Any) -> bytes:
+    _check(o)
+    try:
+        return json.dumps(
+            o, sort_keys=True, separators=(",", ":"), ensure_ascii=False, allow_nan=False
+        ).encode("utf-8")
+    except UnicodeEncodeError as e:
+        raise CanonError("invalid unicode (lone surrogate)") from e

present_day-0.14.0/src/present_day/claims.py

@@ -0,0 +1,148 @@
+"""P7 entry types and strict payload validation (unknown fields are rejected)."""
+
+from __future__ import annotations
+
+import re
+from typing import Any, Callable
+
+HEX64 = re.compile(r"^[0-9a-f]{64}$")
+CTRL = re.compile(r"[\x00-\x08\x0b\x0c\x0e-\x1f\x7f]")  # control chars except \t \n \r
+
+GOVERNANCE_TYPES = {"genesis", "identity", "vouch", "revoke"}
+CONTENT_TYPES = {"claim", "attest", "observation", "retract", "rollback"}
+ALL_TYPES = GOVERNANCE_TYPES | CONTENT_TYPES
+ROLES = {"agent", "source", "human", "node"}
+STANCES = {"support", "dispute"}
+
+
+class SchemaError(ValueError):
+    pass
+
+
+def _s(maxlen: int, *, oneline: bool = False, minlen: int = 0) -> Callable[[Any], str]:
+    def check(v: Any) -> str:
+        if not isinstance(v, str):
+            raise SchemaError("must be a string")
+        if not minlen <= len(v) <= maxlen:
+            raise SchemaError(f"length must be {minlen}..{maxlen}")
+        if CTRL.search(v) or (oneline and ("\n" in v or "\r" in v)):
+            raise SchemaError("contains control characters")
+        return v
+    return check
+
+
+def _hex64(v: Any) -> str:
+    if not isinstance(v, str) or not HEX64.match(v):
+        raise SchemaError("must be 64 lowercase hex chars")
+    return v
+
+
+def _int(lo: int, hi: int) -> Callable[[Any], int]:
+    def check(v: Any) -> int:
+        if isinstance(v, bool) or not isinstance(v, int) or not lo <= v <= hi:
+            raise SchemaError(f"must be an integer {lo}..{hi}")
+        return v
+    return check
+
+
+def _enum(options: set[str]) -> Callable[[Any], str]:
+    def check(v: Any) -> str:
+        if v not in options:
+            raise SchemaError(f"must be one of {sorted(options)}")
+        return v
+    return check
+
+
+def _list(item: Callable[[Any], Any], maxn: int) -> Callable[[Any], list]:
+    def check(v: Any) -> list:
+        if not isinstance(v, list) or len(v) > maxn:
+            raise SchemaError(f"must be a list of at most {maxn} items")
+        return [item(x) for x in v]
+    return check
+
+
+def _source(v: Any) -> dict:
+    if not isinstance(v, dict):
+        raise SchemaError("source must be an object")
+    return _validate(v, {
+        "uri": (_s(2048, oneline=True, minlen=1), False),
+        "entry": (_hex64, False),
+        "content_hash": (_hex64, False),
+    }, require_any=("uri", "entry"))
+
+
+# field -> (validator, required)
+SCHEMAS: dict[str, dict[str, tuple[Callable[[Any], Any], bool]]] = {
+    "genesis": {"name": (_s(64, oneline=True, minlen=1), True)},
+    "identity": {
+        "role": (_enum(ROLES), True),
+        "name": (_s(64, oneline=True, minlen=1), True),
+    },
+    "vouch": {"target": (_hex64, True), "weight": (_int(1, 100), False)},
+    "revoke": {"target": (_hex64, True), "reason": (_s(256), False)},
+    "claim": {
+        "subject": (_s(256, oneline=True, minlen=1), True),
+        "predicate": (_s(128, oneline=True, minlen=1), True),
+        "object": (_s(4096), True),
+        "confidence": (_int(0, 100), False),
+        "sources": (_list(_source, 20), False),
+        "supersedes": (_list(_hex64, 20), False),
+        "tags": (_list(_s(32, oneline=True, minlen=1), 10), False),
+        "text": (_s(8192), False),
+    },
+    "attest": {
+        "target": (_hex64, True),
+        "stance": (_enum(STANCES), True),
+        "note": (_s(512), False),
+    },
+    "retract": {"targets": (_list(_hex64, 50), True), "reason": (_s(256), False)},
+    "rollback": {"from_seq": (_int(2, 2**40), True), "reason": (_s(256), False)},
+    "observation": {
+        "source": (_s(2048, oneline=True, minlen=1), True),
+        "content_hash": (_hex64, True),
+        "size": (_int(0, 2**40), True),
+        "note": (_s(512), False),
+    },
+}
+
+
+def _validate(p: dict, spec: dict, require_any: tuple[str, ...] = ()) -> dict:
+    if not isinstance(p, dict):
+        raise SchemaError("payload must be an object")
+    unknown = set(p) - set(spec)
+    if unknown:
+        raise SchemaError(f"unknown fields: {sorted(unknown)}")
+    out: dict[str, Any] = {}
+    for name, (check, required) in spec.items():
+        if name not in p:
+            if required:
+                raise SchemaError(f"missing field: {name}")
+            continue
+        try:
+            out[name] = check(p[name])
+        except SchemaError as e:
+            raise SchemaError(f"{name}: {e}") from e
+    if require_any and not any(k in out for k in require_any):
+        raise SchemaError(f"one of {list(require_any)} is required")
+    return out
+
+
+def validate_payload(type_: str, payload: dict) -> dict:
+    spec = SCHEMAS.get(type_)
+    if spec is None:
+        raise SchemaError(f"unknown entry type: {type_}")
+    return _validate(payload, spec)
+
+
+def text_fields(type_: str, payload: dict) -> list[tuple[str, str]]:
+    """Free-text fields an LLM could later read; used by the injection scanner."""
+    names = {
+        "claim": ("subject", "predicate", "object", "text"),
+        "attest": ("note",),
+        "observation": ("source", "note"),
+        "identity": ("name",),
+        "retract": ("reason",),
+        "rollback": ("reason",),
+        "revoke": ("reason",),
+    }.get(type_, ())
+    return [(n, payload[n]) for n in names if isinstance(payload.get(n), str)]