sum-engine 0.5.0__tar.gz → 0.6.0__tar.gz

{sum_engine-0.5.0 → sum_engine-0.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sum-engine
-Version: 0.5.0
+Version: 0.6.0
 Summary: SUM — bidirectional knowledge distillation with optional cryptographic attestation. Pipe prose, get a CanonicalBundle (HMAC / Ed25519 / W3C VC 2.0), verify anywhere.
 Author: ototao
 License: Apache-2.0
@@ -25,9 +25,11 @@ Requires-Dist: cryptography>=41.0.0
 Requires-Dist: sympy>=1.12
 Provides-Extra: sieve
 Requires-Dist: spacy>=3.7.0; extra == "sieve"
+Provides-Extra: openai
+Requires-Dist: openai<3.0.0,>=1.40.0; extra == "openai"
+Requires-Dist: pydantic>=2.0.0; extra == "openai"
 Provides-Extra: llm
-Requires-Dist: openai<3.0.0,>=1.40.0; extra == "llm"
-Requires-Dist: pydantic>=2.0.0; extra == "llm"
+Requires-Dist: sum-engine[openai]; extra == "llm"
 Provides-Extra: anthropic
 Requires-Dist: anthropic>=0.97.0; extra == "anthropic"
 Requires-Dist: pydantic>=2.0.0; extra == "anthropic"
@@ -51,7 +53,7 @@ Requires-Dist: build>=1.0.0; extra == "dev"
 Requires-Dist: hypothesis>=6.0.0; extra == "dev"
 Provides-Extra: all
 Requires-Dist: sum-engine[sieve]; extra == "all"
-Requires-Dist: sum-engine[llm]; extra == "all"
+Requires-Dist: sum-engine[openai]; extra == "all"
 Requires-Dist: sum-engine[anthropic]; extra == "all"
 Requires-Dist: sum-engine[receipt-verify]; extra == "all"
 Requires-Dist: sum-engine[mcp]; extra == "all"
@@ -165,7 +167,7 @@ The reverse direction also runs under explicit slider control. The local path ac
 sum render --density 0.5 < bundle.json
 # → keeps the lex-prefix half of the axioms; @sliders header records what was requested
 
-sum render --length 0.9 --use-worker https://sum.ototao.com --json < bundle.json
+sum render --length 0.9 --use-worker https://sum-demo.ototao.workers.dev --json < bundle.json
 # → LLM-conditioned tome + signed render_receipt (sum.render_receipt.v1) on stdout
 ```
 
@@ -192,7 +194,7 @@ pip install 'sum-engine[mcp,sieve]'
 
 ### Calling SUM over HTTP
 
-The hosted Worker at `https://sum.ototao.com` exposes `/api/render`, `/api/complete`, `/api/qid`, and the `/.well-known/{jwks,revoked-kids}.json` verification surfaces. [`docs/API_REFERENCE.md`](docs/API_REFERENCE.md) is the wire spec — request/response shapes, error codes, the six-step receipt-verification flow, working Node + Python examples. Use this when the caller is a web app, mobile app, or server-side service; use the MCP server when the caller is a local LLM client.
+The hosted Worker at `https://sum-demo.ototao.workers.dev` exposes `/api/render`, `/api/complete`, `/api/qid`, and the `/.well-known/{jwks,revoked-kids}.json` verification surfaces. [`docs/API_REFERENCE.md`](docs/API_REFERENCE.md) is the wire spec — request/response shapes, error codes, the six-step receipt-verification flow, working Node + Python examples. Use this when the caller is a web app, mobile app, or server-side service; use the MCP server when the caller is a local LLM client.
 
 ---
 

{sum_engine-0.5.0 → sum_engine-0.6.0}/README.md

@@ -104,7 +104,7 @@ The reverse direction also runs under explicit slider control. The local path ac
 sum render --density 0.5 < bundle.json
 # → keeps the lex-prefix half of the axioms; @sliders header records what was requested
 
-sum render --length 0.9 --use-worker https://sum.ototao.com --json < bundle.json
+sum render --length 0.9 --use-worker https://sum-demo.ototao.workers.dev --json < bundle.json
 # → LLM-conditioned tome + signed render_receipt (sum.render_receipt.v1) on stdout
 ```
 
@@ -131,7 +131,7 @@ pip install 'sum-engine[mcp,sieve]'
 
 ### Calling SUM over HTTP
 
-The hosted Worker at `https://sum.ototao.com` exposes `/api/render`, `/api/complete`, `/api/qid`, and the `/.well-known/{jwks,revoked-kids}.json` verification surfaces. [`docs/API_REFERENCE.md`](docs/API_REFERENCE.md) is the wire spec — request/response shapes, error codes, the six-step receipt-verification flow, working Node + Python examples. Use this when the caller is a web app, mobile app, or server-side service; use the MCP server when the caller is a local LLM client.
+The hosted Worker at `https://sum-demo.ototao.workers.dev` exposes `/api/render`, `/api/complete`, `/api/qid`, and the `/.well-known/{jwks,revoked-kids}.json` verification surfaces. [`docs/API_REFERENCE.md`](docs/API_REFERENCE.md) is the wire spec — request/response shapes, error codes, the six-step receipt-verification flow, working Node + Python examples. Use this when the caller is a web app, mobile app, or server-side service; use the MCP server when the caller is a local LLM client.
 
 ---
 

{sum_engine-0.5.0 → sum_engine-0.6.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "sum-engine"
-version = "0.5.0"
+version = "0.6.0"
 description = "SUM — bidirectional knowledge distillation with optional cryptographic attestation. Pipe prose, get a CanonicalBundle (HMAC / Ed25519 / W3C VC 2.0), verify anywhere."
 readme = "README.md"
 license = { text = "Apache-2.0" }
@@ -39,10 +39,19 @@ dependencies = [
 [project.optional-dependencies]
 # Dependency-injection extras. Users pick the extractor they want:
 #   pip install sum-engine[sieve]   # deterministic, offline spaCy path
-#   pip install sum-engine[llm]     # OpenAI structured-output path
-#   pip install sum-engine[all]     # both, plus dev tooling
+#   pip install sum-engine[openai]  # OpenAI structured-output path
+#   pip install sum-engine[llm]     # alias for [openai] (legacy name)
+#   pip install sum-engine[all]     # everything, plus dev tooling
 sieve = ["spacy>=3.7.0"]
-llm = ["openai>=1.40.0,<3.0.0", "pydantic>=2.0.0"]
+# `[openai]` is the canonical, vendor-named extra; `[llm]` is kept as a
+# back-compat alias because it predates the multi-provider dispatcher
+# (Anthropic and OpenAI now have their own named extras). Both install
+# identical dependencies — the openai SDK plus pydantic for structured
+# outputs. The vendor adapter is at
+# sum_engine_internal/ensemble/llm_dispatch.py::OpenAIAdapter; the
+# render-path TS companion is worker/src/routes/render.ts::callOpenAI.
+openai = ["openai>=1.40.0,<3.0.0", "pydantic>=2.0.0"]
+llm = ["sum-engine[openai]"]
 # Anthropic Messages-API adapter (Claude family). Installed alongside
 # [llm] for the §2.5 frontier-LLM benchmark runs that compare
 # generator-side interventions across providers. The runner picks
@@ -107,7 +116,7 @@ dev = [
 ]
 all = [
     "sum-engine[sieve]",
-    "sum-engine[llm]",
+    "sum-engine[openai]",
     "sum-engine[anthropic]",
     "sum-engine[receipt-verify]",
     "sum-engine[mcp]",

sum_engine-0.6.0/sum_cli/audit_log.py

@@ -0,0 +1,171 @@
+"""sum_cli.audit_log — universal audit-log streaming for compliance.
+
+When the ``SUM_AUDIT_LOG`` environment variable is set to a file path,
+every ``sum attest`` / ``sum verify`` / ``sum render`` operation
+appends a single JSONL row to that file describing what was done.
+
+This is the regime-agnostic foundation of the compliance primitives
+direction (Path 3). A specific regime (GDPR-Art-30, HIPAA-164.514,
+EU AI Act Annex IV, etc.) can be implemented as a downstream
+consumer of this audit log: tail the file, validate per-regime
+required fields, raise on policy violation. The audit log itself
+makes no regime-specific assumptions — it records *what happened*
+verbatim so any auditor can reconstruct the operation.
+
+Schema: ``sum.audit_log.v1`` — additive; new optional fields may
+appear in future minor versions; consumers should ignore unknown
+keys.
+
+Required fields per row:
+  - ``schema`` = ``"sum.audit_log.v1"``
+  - ``timestamp`` (ISO 8601 UTC, e.g. ``"2026-05-01T18:35:14.123Z"``)
+  - ``operation`` ∈ ``{"attest", "verify", "render"}``
+  - ``cli_version`` (the ``sum-cli`` version that produced the row)
+
+Operation-specific optional fields:
+  - attest:  ``source_uri``, ``state_integer_digits``, ``axiom_count``,
+             ``extractor``, ``signed`` (bool — Ed25519 attached?),
+             ``hmac`` (bool), ``branch``
+  - verify:  ``state_integer_digits``, ``axiom_count``, ``signatures``
+             ``{ed25519, hmac}``, ``branch``, ``ok`` (bool)
+  - render:  ``axiom_count_input``, ``mode`` (``"local-deterministic"``
+             or ``"worker"``), ``sliders``, ``render_receipt_kid`` (if
+             worker), ``worker_url`` (if worker)
+
+Failures (exit code != 0) emit a row with ``error`` field describing
+the failure class. Audit-log writes themselves never fail loudly —
+if ``SUM_AUDIT_LOG`` points at a non-writable path, the operation
+proceeds and the failure is reported on stderr only when ``--verbose``
+is set; the audit semantics fail-open by design (a non-functional
+audit destination should not break the trust loop).
+
+Env var precedence:
+  1. ``SUM_AUDIT_LOG`` env var (path to JSONL file; appended to)
+  2. unset → no audit logging
+
+The path may be ``-`` for stdout (rare; mostly useful for piping
+into another tool); otherwise treated as a file path with append-mode
+open.
+
+Concurrency: writes are O_APPEND on POSIX, so multiple sum
+processes writing to the same audit log produce a serialised
+ordering (atomic per write() up to PIPE_BUF on most systems —
+single-line JSONL records well under that bound). We write each
+row in one ``f.write()`` call to maximise atomicity.
+"""
+from __future__ import annotations
+
+import json
+import os
+import sys
+from datetime import datetime, timezone
+from typing import Any
+
+
+_AUDIT_LOG_SCHEMA = "sum.audit_log.v1"
+
+
+def _audit_log_path() -> str | None:
+    """Return the configured audit-log destination, or None if unset."""
+    p = os.environ.get("SUM_AUDIT_LOG")
+    if p is None or p == "":
+        return None
+    return p
+
+
+def _identity_fields() -> dict[str, Any]:
+    """Optional identity fields populated from env vars.
+
+    Sprint 4 of the intensification path to arXiv (PR #140). Closes
+    the PCI DSS Req 10.2.2 user-identification gap named in
+    ``docs/COMPLIANCE_PCI_DSS_4_REQ_10.md``. Three env vars are
+    consulted; each populated value becomes an optional field on
+    the audit-log row:
+
+      - ``SUM_AUDIT_USER_ID`` → ``user_id`` field. Per PCI Req 10.2.2,
+        "user identification" is the FIRST required field for each
+        audit-log event. Operators running SUM behind an
+        authenticating proxy populate this from the proxy's session
+        identity at process start.
+      - ``SUM_AUDIT_HOST_ID`` → ``host_id`` field. Multi-host
+        deployments (clusters, k8s pods, container fleets) use this
+        to attribute events to specific compute units.
+      - ``SUM_AUDIT_IP_ADDRESS`` → ``ip_address`` field. Network-
+        layer origination, useful for incident-response / forensic
+        analysis under PCI Req 10.2.2's "origination of event"
+        requirement.
+
+    All three are *optional*. An unset env var produces an absent
+    field (not a null value). The audit-log schema stays at
+    ``sum.audit_log.v1``; these are additive optional fields under
+    the existing schema's "consumers should ignore unknown keys"
+    convention. Backward compat: rows without these fields still
+    pass every existing validator.
+
+    PCI DSS validator R7 (``pci-dss-4-req-10.user-identification-
+    recommended``, added in the same PR as this function) treats
+    a missing ``user_id`` as a Req 10.2.2 violation in compliance-
+    mode runs.
+    """
+    out: dict[str, Any] = {}
+    for env_var, field in (
+        ("SUM_AUDIT_USER_ID", "user_id"),
+        ("SUM_AUDIT_HOST_ID", "host_id"),
+        ("SUM_AUDIT_IP_ADDRESS", "ip_address"),
+    ):
+        value = os.environ.get(env_var)
+        if value:  # non-empty (skips both None and empty string)
+            out[field] = value
+    return out
+
+
+def emit_audit_event(operation: str, payload: dict[str, Any]) -> None:
+    """Append a single JSONL row to the audit log if configured.
+
+    Fail-open: if the audit destination is unwritable, the operation
+    proceeds normally; the failure is silent unless verbose stderr
+    is enabled by the caller. Audit logging is *advisory* — the
+    canonical bundle / receipt still carries the load-bearing trust
+    properties; the audit log is for downstream compliance tools
+    to ingest.
+
+    Identity fields (``user_id`` / ``host_id`` / ``ip_address``) are
+    populated from env vars by :func:`_identity_fields`. They appear
+    on the row only when the corresponding env var is set; absent
+    env vars produce absent fields (not null values). The
+    ``payload`` argument takes precedence over identity fields if
+    a caller passes overlapping keys — useful for tests that want
+    to pin specific identity values without touching the
+    environment.
+    """
+    path = _audit_log_path()
+    if path is None:
+        return
+
+    from sum_cli import __version__
+
+    row = {
+        "schema": _AUDIT_LOG_SCHEMA,
+        "timestamp": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%S.")
+                     + f"{datetime.now(timezone.utc).microsecond // 1000:03d}Z",
+        "operation": operation,
+        "cli_version": __version__,
+        # Identity fields from env, then payload last so the caller
+        # wins on overlap (intentional for test seams).
+        **_identity_fields(),
+        **payload,
+    }
+    line = json.dumps(row, separators=(",", ":")) + "\n"
+
+    try:
+        if path == "-":
+            sys.stdout.write(line)
+            sys.stdout.flush()
+        else:
+            with open(path, "a", encoding="utf-8") as f:
+                f.write(line)
+    except OSError:
+        # Fail-open: audit destination unavailable; do not block
+        # the operation. The canonical bundle / receipt remains the
+        # load-bearing trust artifact.
+        pass

{sum_engine-0.5.0 → sum_engine-0.6.0}/sum_cli/main.py

@@ -420,6 +420,18 @@ def cmd_attest(args: argparse.Namespace) -> int:
             f"{len(bundle['state_integer'])} digits",
             file=sys.stderr,
         )
+
+    from sum_cli.audit_log import emit_audit_event
+    emit_audit_event("attest", {
+        "source_uri": source_uri,
+        "axiom_count": len(triples),
+        "state_integer_digits": len(bundle["state_integer"]),
+        "extractor": extractor,
+        "branch": args.branch,
+        "signed": "public_signature" in bundle,
+        "hmac": "signature" in bundle,
+        "input_format": format_sidecar.get("input_format"),
+    })
     return 0
 
 
@@ -844,6 +856,16 @@ def cmd_verify(args: argparse.Namespace) -> int:
         f"sum: ✓ verified {axioms} axiom(s), state integer matches ({marks})",
         file=sys.stderr,
     )
+
+    from sum_cli.audit_log import emit_audit_event
+    emit_audit_event("verify", {
+        "ok": True,
+        "axiom_count": axioms,
+        "state_integer_digits": len(claimed_state_str),
+        "branch": bundle.get("branch", "main"),
+        "signatures": {"hmac": hmac_status, "ed25519": ed25519_status},
+        "extraction": extraction,
+    })
     return 0
 
 
@@ -926,7 +948,15 @@ def _post_render_to_worker(
         endpoint,
         data=payload,
         method="POST",
-        headers={"content-type": "application/json"},
+        headers={
+            "content-type": "application/json",
+            # Cloudflare in front of hosted Workers (incl. the
+            # default sum-demo.ototao.workers.dev) rejects the
+            # default Python urllib User-Agent with HTTP 403 /
+            # error 1010. Identify ourselves as a known scripted
+            # client so the request passes the bot-detection layer.
+            "user-agent": f"sum-cli/{__version__} (+https://github.com/OtotaO/SUM)",
+        },
     )
     try:
         with urllib.request.urlopen(req, timeout=60) as resp:
@@ -1130,6 +1160,20 @@ def _emit_render_output(envelope: dict, args: argparse.Namespace) -> int:
             kid = envelope["render_receipt"].get("kid", "?")
             msg += f", receipt kid={kid}"
         print(msg, file=sys.stderr)
+
+    from sum_cli.audit_log import emit_audit_event
+    audit_payload: dict = {
+        "mode": envelope.get("mode"),
+        "axiom_count_input": envelope.get("axiom_count_input"),
+        "tome_chars": len(tome_text),
+        "sliders": envelope.get("sliders"),
+    }
+    if "render_receipt" in envelope:
+        receipt = envelope["render_receipt"]
+        audit_payload["render_receipt_kid"] = receipt.get("kid")
+        audit_payload["render_receipt_schema"] = receipt.get("schema")
+        audit_payload["worker_url"] = envelope.get("worker_url")
+    emit_audit_event("render", audit_payload)
     return 0
 
 
@@ -1499,6 +1543,172 @@ def cmd_schema(args: argparse.Namespace) -> int:
     return 0
 
 
+# ─── compliance ──────────────────────────────────────────────────────
+#
+# Per-regime validators consuming sum.audit_log.v1. The audit log is
+# regime-agnostic substrate; ``sum compliance check`` is the actionable
+# layer that turns it into a pass/fail verdict for a specific regime.
+# Exit code 0 when ok=true, 1 otherwise — pipe-friendly for CI gates.
+
+_COMPLIANCE_REGIMES: dict[str, str] = {
+    "eu-ai-act-article-12": (
+        "EU AI Act (Regulation (EU) 2024/1689) Article 12 — record-"
+        "keeping for high-risk AI systems. Pins per-row traceability "
+        "fields (timestamp, operation, cli_version), schema, and "
+        "operation-specific anchors (source_uri / axiom_count / "
+        "state_integer_digits / mode)."
+    ),
+    "gdpr-article-30": (
+        "GDPR (Regulation (EU) 2016/679) Article 30 — Records of "
+        "Processing Activities. Pins the per-row floor enabling Art "
+        "30 reporting (schema, timestamp, ISO-8601-UTC parseability, "
+        "processing-category indicator, processor identity). The "
+        "controller separately maintains record-set-scope metadata "
+        "(Art 30(1)(a)–(g) controller name, purposes, categories, "
+        "recipients, transfers, retention, security measures) "
+        "out-of-band; this validator does not pin those."
+    ),
+    "hipaa-164-312-b": (
+        "HIPAA Security Rule 45 CFR § 164.312(b) — Audit Controls "
+        "(Technical Safeguards). Pins the per-row form requirements "
+        "for an audit recording that supports examination of "
+        "activity (schema, timestamp, ISO-8601-UTC, activity type, "
+        "system component identification, per-operation examination "
+        "anchors). Deployment-scope obligations — auditor function, "
+        "retention, ePHI inventory — live outside this validator."
+    ),
+    "iso-27001-8-15": (
+        "ISO/IEC 27001:2022 Annex A.8.15 — Logging. Pins the per-"
+        "row form floor an audit log must satisfy for the recording "
+        "to count as a 'produced' log under A.8.15 (schema, "
+        "timestamp, ISO-8601-UTC, activity, system component). The "
+        "'stored', 'protected', 'analysed' verbs map to deployment-"
+        "scope obligations (file-system policy, access control, "
+        "SIEM integration) outside this validator."
+    ),
+    "soc-2-cc-7-2": (
+        "SOC 2 Trust Services Criteria CC7.2 — System Operations. "
+        "Pins the per-row form floor required to enable the "
+        "monitoring criterion (schema, timestamp, ISO-8601-UTC, "
+        "activity classification, system component identification). "
+        "The detection / monitoring / analysis activities themselves "
+        "(SIEM rules, alert routing, oncall rotations) live at "
+        "deployment scope outside this validator."
+    ),
+    "pci-dss-4-req-10": (
+        "PCI DSS v4.0 Requirement 10 — Log and Monitor All Access "
+        "to System Components and Cardholder Data. Pins per-row "
+        "content visible in audit_log.v1 against Req 10.2.2 (event "
+        "content) plus 10.6 (consistent time): schema, timestamp, "
+        "ISO-8601-UTC, event type, origination, event-content "
+        "completeness. NOT pinned: 10.1 organisational policies; "
+        "10.2.1.* specific event-type coverage; 10.2.2 user "
+        "identification (audit_log.v1 has no user_id field); 10.3 "
+        "log file protection; 10.4 log review process; 10.5 12-"
+        "month retention; 10.7 failure detection / alerting."
+    ),
+}
+
+
+def _compliance_validators():
+    """Return the regime → validate-callable dispatch table.
+
+    Built lazily to avoid importing compliance modules at CLI
+    startup (each module imports the dataclass infrastructure;
+    deferring keeps `sum --help` cold-start fast). Registered
+    regimes must match :data:`_COMPLIANCE_REGIMES` keys exactly —
+    a mismatch surfaces as a KeyError at dispatch, intentional
+    (better than silent fallthrough)."""
+    from sum_engine_internal.compliance import (  # local import — see docstring
+        eu_ai_act_article_12,
+        gdpr_article_30,
+        hipaa_164_312_b,
+        iso_27001_8_15,
+        pci_dss_4_req_10,
+        soc_2_cc_7_2,
+    )
+    return {
+        "eu-ai-act-article-12": eu_ai_act_article_12.validate,
+        "gdpr-article-30": gdpr_article_30.validate,
+        "hipaa-164-312-b": hipaa_164_312_b.validate,
+        "iso-27001-8-15": iso_27001_8_15.validate,
+        "soc-2-cc-7-2": soc_2_cc_7_2.validate,
+        "pci-dss-4-req-10": pci_dss_4_req_10.validate,
+    }
+
+
+def cmd_compliance_check(args: argparse.Namespace) -> int:
+    if args.regime not in _COMPLIANCE_REGIMES:
+        print(
+            f"sum: unknown regime {args.regime!r}. Known: "
+            f"{sorted(_COMPLIANCE_REGIMES)}",
+            file=sys.stderr,
+        )
+        return 2
+
+    if args.audit_log == "-":
+        text = sys.stdin.read()
+    else:
+        try:
+            with open(args.audit_log, "r", encoding="utf-8") as f:
+                text = f.read()
+        except OSError as e:
+            print(f"sum: cannot read --audit-log {args.audit_log!r}: {e}", file=sys.stderr)
+            return 2
+
+    rows: list[dict] = []
+    parse_errors: list[tuple[int, str]] = []
+    for i, line in enumerate(text.splitlines()):
+        line = line.strip()
+        if not line:
+            continue
+        try:
+            rows.append(json.loads(line))
+        except json.JSONDecodeError as e:
+            parse_errors.append((i, str(e)))
+
+    validators = _compliance_validators()
+    try:
+        validate = validators[args.regime]
+    except KeyError:
+        # Defensive — _COMPLIANCE_REGIMES gate above should have caught this.
+        # Reaching here means a regime is registered in _COMPLIANCE_REGIMES
+        # but missing from _compliance_validators() — a wiring drift.
+        print(
+            f"sum: regime {args.regime!r} listed but not wired "
+            f"(internal: missing from _compliance_validators dispatch)",
+            file=sys.stderr,
+        )
+        return 2
+    report = validate(rows)
+
+    out = report.to_dict()
+    if parse_errors:
+        # Surface parse errors alongside rule violations — both are
+        # compliance-relevant. A malformed JSONL line is itself a
+        # traceability defect.
+        out["parse_errors"] = [
+            {"line_index": idx, "error": msg} for idx, msg in parse_errors
+        ]
+
+    json.dump(out, sys.stdout, indent=2 if args.pretty else None)
+    sys.stdout.write("\n")
+    return 0 if (report.ok and not parse_errors) else 1
+
+
+def cmd_compliance_regimes(args: argparse.Namespace) -> int:
+    out = {
+        "schema": "sum.compliance_regimes.v1",
+        "regimes": [
+            {"id": rid, "description": desc}
+            for rid, desc in sorted(_COMPLIANCE_REGIMES.items())
+        ],
+    }
+    json.dump(out, sys.stdout, indent=2)
+    sys.stdout.write("\n")
+    return 0
+
+
 # ─── Argparse wiring ─────────────────────────────────────────────────
 
 def build_parser() -> argparse.ArgumentParser:
@@ -1878,6 +2088,60 @@ def build_parser() -> argparse.ArgumentParser:
     )
     p_schema.set_defaults(func=cmd_schema)
 
+    # compliance — regime validators consuming sum.audit_log.v1.
+    p_compliance = subparsers.add_parser(
+        "compliance",
+        help="Validate a sum.audit_log.v1 stream against a compliance regime.",
+        description=(
+            "Apply a per-regime validator to a sum.audit_log.v1 JSONL stream "
+            "and emit a sum.compliance_report.v1 verdict. The audit log is "
+            "regime-agnostic substrate; this verb is the actionable layer "
+            "that turns it into a compliance-grade pass/fail."
+        ),
+    )
+    p_compliance_sub = p_compliance.add_subparsers(
+        dest="compliance_cmd", required=True, metavar="<compliance-cmd>",
+    )
+
+    p_comp_check = p_compliance_sub.add_parser(
+        "check",
+        help="Validate an audit-log stream against a regime; emit a JSON report.",
+        description=(
+            "Read a sum.audit_log.v1 JSONL stream from --audit-log (or stdin "
+            "if '-'), validate against the named regime, emit a "
+            "sum.compliance_report.v1 JSON object on stdout. Exit code is "
+            "0 when ok=true, 1 otherwise — pipe-friendly for CI gates."
+        ),
+    )
+    p_comp_check.add_argument(
+        "--regime",
+        required=True,
+        choices=["eu-ai-act-article-12"],
+        help="Compliance regime to validate against.",
+    )
+    p_comp_check.add_argument(
+        "--audit-log",
+        required=True,
+        help="Path to a sum.audit_log.v1 JSONL file ('-' for stdin).",
+    )
+    p_comp_check.add_argument(
+        "--pretty",
+        action="store_true",
+        help="Pretty-print the report JSON.",
+    )
+    p_comp_check.set_defaults(func=cmd_compliance_check)
+
+    p_comp_regimes = p_compliance_sub.add_parser(
+        "regimes",
+        help="List available compliance regimes.",
+        description=(
+            "Emit the set of regime identifiers this CLI can validate "
+            "against. Adding a new regime appends to this list; "
+            "existing identifiers are stable."
+        ),
+    )
+    p_comp_regimes.set_defaults(func=cmd_compliance_regimes)
+
     return parser
 
 

{sum_engine-0.5.0 → sum_engine-0.6.0}/sum_engine.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sum-engine
-Version: 0.5.0
+Version: 0.6.0
 Summary: SUM — bidirectional knowledge distillation with optional cryptographic attestation. Pipe prose, get a CanonicalBundle (HMAC / Ed25519 / W3C VC 2.0), verify anywhere.
 Author: ototao
 License: Apache-2.0
@@ -25,9 +25,11 @@ Requires-Dist: cryptography>=41.0.0
 Requires-Dist: sympy>=1.12
 Provides-Extra: sieve
 Requires-Dist: spacy>=3.7.0; extra == "sieve"
+Provides-Extra: openai
+Requires-Dist: openai<3.0.0,>=1.40.0; extra == "openai"
+Requires-Dist: pydantic>=2.0.0; extra == "openai"
 Provides-Extra: llm
-Requires-Dist: openai<3.0.0,>=1.40.0; extra == "llm"
-Requires-Dist: pydantic>=2.0.0; extra == "llm"
+Requires-Dist: sum-engine[openai]; extra == "llm"
 Provides-Extra: anthropic
 Requires-Dist: anthropic>=0.97.0; extra == "anthropic"
 Requires-Dist: pydantic>=2.0.0; extra == "anthropic"
@@ -51,7 +53,7 @@ Requires-Dist: build>=1.0.0; extra == "dev"
 Requires-Dist: hypothesis>=6.0.0; extra == "dev"
 Provides-Extra: all
 Requires-Dist: sum-engine[sieve]; extra == "all"
-Requires-Dist: sum-engine[llm]; extra == "all"
+Requires-Dist: sum-engine[openai]; extra == "all"
 Requires-Dist: sum-engine[anthropic]; extra == "all"
 Requires-Dist: sum-engine[receipt-verify]; extra == "all"
 Requires-Dist: sum-engine[mcp]; extra == "all"
@@ -165,7 +167,7 @@ The reverse direction also runs under explicit slider control. The local path ac
 sum render --density 0.5 < bundle.json
 # → keeps the lex-prefix half of the axioms; @sliders header records what was requested
 
-sum render --length 0.9 --use-worker https://sum.ototao.com --json < bundle.json
+sum render --length 0.9 --use-worker https://sum-demo.ototao.workers.dev --json < bundle.json
 # → LLM-conditioned tome + signed render_receipt (sum.render_receipt.v1) on stdout
 ```
 
@@ -192,7 +194,7 @@ pip install 'sum-engine[mcp,sieve]'
 
 ### Calling SUM over HTTP
 
-The hosted Worker at `https://sum.ototao.com` exposes `/api/render`, `/api/complete`, `/api/qid`, and the `/.well-known/{jwks,revoked-kids}.json` verification surfaces. [`docs/API_REFERENCE.md`](docs/API_REFERENCE.md) is the wire spec — request/response shapes, error codes, the six-step receipt-verification flow, working Node + Python examples. Use this when the caller is a web app, mobile app, or server-side service; use the MCP server when the caller is a local LLM client.
+The hosted Worker at `https://sum-demo.ototao.workers.dev` exposes `/api/render`, `/api/complete`, `/api/qid`, and the `/.well-known/{jwks,revoked-kids}.json` verification surfaces. [`docs/API_REFERENCE.md`](docs/API_REFERENCE.md) is the wire spec — request/response shapes, error codes, the six-step receipt-verification flow, working Node + Python examples. Use this when the caller is a web app, mobile app, or server-side service; use the MCP server when the caller is a local LLM client.
 
 ---