agent-runtime-kit 0.5.4__tar.gz → 0.5.6__tar.gz

{agent_runtime_kit-0.5.4 → agent_runtime_kit-0.5.6}/CHANGELOG.md

@@ -5,6 +5,30 @@ All notable changes to this project are documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## 0.5.6 - 2026-11-08
+
+### Changed
+
+- Updated the tested Claude Agent SDK to `0.2.179`, Antigravity to `0.1.23`,
+  and the exactly coupled Codex SDK and CLI to `0.167.0`. Raised the Codex
+  upper bound to `<0.168` after inspecting the exact candidate versions.
+
+### Fixed
+
+- SDK evolution now collects official release notes for Claude's bundled CLI,
+  verifies its version against the inspected SDK distribution, and blocks on
+  incomplete or contradictory runtime evidence.
+- Implementation snapshots distinguish a public class replaced by an alias
+  from a removed name, including in isolated candidate environments.
+
+## 0.5.5 - 2026-10-22
+
+### Changed
+
+- Updated tested Claude Agent SDK from `0.2.168` to `0.2.172`, including bundled
+  Claude CLI `2.1.308`, after exact-version API and behavior checks. Codex SDK
+  and its exactly coupled CLI remain `0.163.0`; Antigravity remains `0.1.22`.
+
 ## 0.5.4 - 2026-10-18
 
 ### Changed

{agent_runtime_kit-0.5.4 → agent_runtime_kit-0.5.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: agent-runtime-kit
-Version: 0.5.4
+Version: 0.5.6
 Summary: One typed runtime API for Claude, Codex, and Antigravity agent SDKs.
 Project-URL: Homepage, https://github.com/ebarti/agent-runtime-kit
 Project-URL: Repository, https://github.com/ebarti/agent-runtime-kit
@@ -23,13 +23,13 @@ Requires-Dist: tomli<3,>=2; python_version < '3.11'
 Provides-Extra: all
 Requires-Dist: claude-agent-sdk<0.3,>=0.2.87; extra == 'all'
 Requires-Dist: google-antigravity<0.2,>=0.1.2; extra == 'all'
-Requires-Dist: openai-codex<0.164,>=0.157.1; extra == 'all'
+Requires-Dist: openai-codex<0.168,>=0.157.1; extra == 'all'
 Provides-Extra: antigravity
 Requires-Dist: google-antigravity<0.2,>=0.1.2; extra == 'antigravity'
 Provides-Extra: claude
 Requires-Dist: claude-agent-sdk<0.3,>=0.2.87; extra == 'claude'
 Provides-Extra: codex
-Requires-Dist: openai-codex<0.164,>=0.157.1; extra == 'codex'
+Requires-Dist: openai-codex<0.168,>=0.157.1; extra == 'codex'
 Description-Content-Type: text/markdown
 
 # agent-runtime-kit

{agent_runtime_kit-0.5.4 → agent_runtime_kit-0.5.6}/docs/sdk-evolution-agent.md

@@ -173,18 +173,31 @@ files and Python AST definitions, compares adjacent releases, and writes the
 result to `implementation_diffs.json`. History also includes the exact locked
 baseline and candidate when they fall outside the latest three releases, so
 the changes between the installed baseline and the recent releases remain
-visible. Claude probes construct permission, budget, session, MCP and schema
-options; Codex probes construct configuration and validated thread/turn wire
+visible. Module-level capitalized alias assignments are fingerprinted alongside
+class and function definitions, so replacing a class with an alias is
+distinguished from deleting the name. These are static source observations,
+not proof that a conditional assignment is present at runtime. Claude probes
+construct permission, budget, session, MCP and schema options; Codex probes
+construct configuration and validated thread/turn wire
 parameters, including permissions, reasoning effort and structured output.
 These checks complement real-adapter regression tests and live runtime checks;
 they do not establish behavior inside opaque executables.
-Source is never copied into the report;
+Implementation source is never copied into the report;
 only paths, counts, sizes, and hashes are retained. Candidate inspection is
 opt-in because it executes freshly downloaded upstream code; historical
 inspection uses the same explicit consent. Without the flag, missing trend
 evidence is reported as `no-transition` rather than being replaced with
 dependency advice.
 
+For a Claude SDK update, release evidence also covers its bundled Claude Code
+CLI. The runner matches each SDK tag's CLI-version file against the fingerprint
+of the exact inspected distribution, then records official CLI release notes
+between the baseline and candidate. The SDK's own note status remains separate:
+CLI notes do not turn an absent SDK changelog entry into a match. Missing or
+contradictory version mappings, an incomplete release index, and missing CLI
+release text block promotion. The CLI remains opaque even when its release
+notes are available.
+
 ## Upstream Implementation Trends
 
 `direction_analysis.json` is an implementation-trend report. It answers what

{agent_runtime_kit-0.5.4 → agent_runtime_kit-0.5.6}/examples/sdk_evolution_agent/cli.py

@@ -237,7 +237,9 @@ async def run_agent(
             _progress("collecting release notes and executable behavior probes")
             release_notes = [
                 to_jsonable(item)
-                for item in collect_release_notes(evidence.get("packages", []), update_versions)
+                for item in collect_release_notes(
+                    evidence.get("packages", []), update_versions, snapshots=snapshots
+                )
             ]
             behavior = to_jsonable(
                 collect_behavior_evidence(

{agent_runtime_kit-0.5.4 → agent_runtime_kit-0.5.6}/examples/sdk_evolution_agent/models.py

@@ -152,6 +152,28 @@ class ImplementationDiff:
     limitations: tuple[str, ...] = ()
 
 
+@dataclass(frozen=True)
+class BundledRuntimeRelease:
+    """An official release note for a runtime bundled inside an SDK."""
+
+    version: str
+    url: str
+    notes: str
+
+
+@dataclass(frozen=True)
+class BundledRuntimeEvidence:
+    """Provenance and release notes for an SDK's exact bundled runtime."""
+
+    name: str
+    from_version: str | None
+    to_version: str | None
+    status: str
+    sources: tuple[SourceRef, ...] = ()
+    releases: tuple[BundledRuntimeRelease, ...] = ()
+    unavailable_reason: str = ""
+
+
 @dataclass(frozen=True)
 class ReleaseNoteEvidence:
     """Release-note evidence collected for one package interval."""
@@ -164,6 +186,7 @@ class ReleaseNoteEvidence:
     summaries: tuple[str, ...] = ()
     checked_urls: tuple[str, ...] = ()
     unavailable_reason: str = ""
+    bundled_runtime: BundledRuntimeEvidence | None = None
 
 
 @dataclass(frozen=True)

{agent_runtime_kit-0.5.4 → agent_runtime_kit-0.5.6}/examples/sdk_evolution_agent/release_notes.py

@@ -2,7 +2,9 @@
 
 from __future__ import annotations
 
+import ast
 import gzip
+import hashlib
 import json
 import os
 import re
@@ -11,7 +13,15 @@ import urllib.parse
 import urllib.request
 from collections.abc import Callable, Mapping, Sequence
 
-from examples.sdk_evolution_agent.models import ReleaseNoteEvidence, SourceRef
+from packaging.version import Version
+
+from examples.sdk_evolution_agent.models import (
+    ApiSnapshot,
+    BundledRuntimeEvidence,
+    BundledRuntimeRelease,
+    ReleaseNoteEvidence,
+    SourceRef,
+)
 
 ReleaseNoteFetcher = Callable[[str], str]
 
@@ -88,6 +98,7 @@ def collect_release_notes(
     update_versions: Mapping[str, str],
     *,
     fetcher: ReleaseNoteFetcher | None = None,
+    snapshots: Sequence[ApiSnapshot] | None = None,
 ) -> tuple[ReleaseNoteEvidence, ...]:
     """Collect primary-source release-note evidence for update candidates."""
 
@@ -219,6 +230,11 @@ def collect_release_notes(
             status = "unavailable"
             unavailable_reason = "no release-note source configured"
 
+        bundled_runtime = None
+        if name == "claude-agent-sdk" and snapshots is not None:
+            bundled_runtime = _collect_claude_bundled_runtime(
+                from_version, to_version, snapshots=snapshots, fetcher=fetcher
+            )
         evidence.append(
             ReleaseNoteEvidence(
                 package=name,
@@ -229,11 +245,188 @@ def collect_release_notes(
                 summaries=tuple(_dedupe(summaries)[:8]),
                 checked_urls=tuple(checked_urls),
                 unavailable_reason=unavailable_reason,
+                bundled_runtime=bundled_runtime,
             )
         )
     return tuple(evidence)
 
 
+def _collect_claude_bundled_runtime(
+    from_version: str | None,
+    to_version: str,
+    *,
+    snapshots: Sequence[ApiSnapshot],
+    fetcher: ReleaseNoteFetcher,
+) -> BundledRuntimeEvidence:
+    """Resolve CLI versions from exact SDK snapshots, then collect their releases.
+
+    The upstream SDK tag is only accepted when its version file has
+    the same fingerprint as the inspected distribution. A release index or tag
+    that cannot be reconciled is evidence of a gap, not an empty changelog.
+    """
+
+    sources: list[SourceRef] = []
+    versions: list[str] = []
+    try:
+        for sdk_version in (from_version, to_version):
+            if not sdk_version or not re.fullmatch(r"[0-9A-Za-z][0-9A-Za-z.+-]*", sdk_version):
+                raise ValueError(f"invalid or missing Claude SDK version: {sdk_version!r}")
+            snapshot = next(
+                (
+                    item
+                    for item in snapshots
+                    if item.package == "claude-agent-sdk"
+                    and item.version == sdk_version
+                    and not item.import_error
+                ),
+                None,
+            )
+            if snapshot is None:
+                raise ValueError(f"missing exact SDK snapshot for {sdk_version}")
+            version_file = next(
+                (
+                    item
+                    for item in snapshot.implementation_files
+                    if item.path == "claude_agent_sdk/_cli_version.py"
+                ),
+                None,
+            )
+            if version_file is None:
+                raise ValueError(f"missing bundled CLI version fingerprint for SDK {sdk_version}")
+            url = (
+                "https://raw.githubusercontent.com/anthropics/claude-agent-sdk-python/"
+                f"v{urllib.parse.quote(sdk_version, safe='')}/src/claude_agent_sdk/_cli_version.py"
+            )
+            _progress(f"checking bundled Claude CLI version from SDK {sdk_version}")
+            try:
+                content = fetcher(url)
+                digest = hashlib.sha256(content.encode("utf-8")).hexdigest()
+                if digest != version_file.sha256:
+                    raise ValueError(
+                        f"bundled CLI version fingerprint mismatch for SDK {sdk_version}"
+                    )
+                cli_version = _claude_cli_version(content)
+            except Exception as exc:
+                sources.append(
+                    SourceRef(
+                        kind="sdk-runtime-version",
+                        label="Claude SDK bundled CLI version",
+                        url=url,
+                        version=sdk_version,
+                        available=False,
+                        note=str(exc),
+                    )
+                )
+                raise
+            sources.append(
+                SourceRef(
+                    kind="sdk-runtime-version",
+                    label="Claude SDK bundled CLI version",
+                    url=url,
+                    version=sdk_version,
+                    note="Source fingerprint matches the inspected SDK distribution.",
+                )
+            )
+            versions.append(cli_version)
+
+        baseline, candidate = (Version(value) for value in versions)
+        if candidate < baseline:
+            raise ValueError("candidate bundled CLI version is older than the baseline")
+        if candidate == baseline:
+            return BundledRuntimeEvidence(
+                "claude-code", versions[0], versions[1], "not-needed", tuple(sources)
+            )
+
+        releases: dict[Version, BundledRuntimeRelease] = {}
+        covered_baseline = False
+        for page in range(1, 6):
+            url = (
+                "https://api.github.com/repos/anthropics/claude-code/releases"
+                f"?per_page=100&page={page}"
+            )
+            _progress(f"checking bundled Claude CLI release notes, page {page}")
+            try:
+                rows = json.loads(fetcher(url))
+                if not isinstance(rows, list):
+                    raise ValueError("release index is not a list")
+            except Exception as exc:
+                sources.append(
+                    SourceRef(
+                        kind="release-index",
+                        label="Claude Code releases",
+                        url=url,
+                        available=False,
+                        note=str(exc),
+                    )
+                )
+                raise
+            sources.append(SourceRef(kind="release-index", label="Claude Code releases", url=url))
+            for row in rows:
+                if not isinstance(row, Mapping):
+                    raise ValueError("release index contains a malformed entry")
+                if row.get("draft") or row.get("prerelease"):
+                    continue
+                tag = str(row.get("tag_name") or "")
+                if not re.fullmatch(r"v?\d+\.\d+\.\d+", tag):
+                    continue
+                release_version = Version(tag.lstrip("v"))
+                if release_version <= baseline:
+                    covered_baseline = True
+                if baseline < release_version <= candidate:
+                    release_url = f"https://github.com/anthropics/claude-code/releases/tag/{tag}"
+                    release = BundledRuntimeRelease(
+                        version=str(release_version),
+                        url=release_url,
+                        notes=str(row.get("body") or "").strip(),
+                    )
+                    if release_version in releases and releases[release_version] != release:
+                        raise ValueError(f"contradictory CLI releases for {release_version}")
+                    releases[release_version] = release
+            if covered_baseline or len(rows) < 100:
+                covered_baseline = True
+                break
+
+        missing = [str(version) for version, release in releases.items() if not release.notes]
+        problems = []
+        if not covered_baseline:
+            problems.append("release-index pagination did not reach the baseline")
+        if candidate not in releases:
+            problems.append(f"candidate CLI release {candidate} not found")
+        if missing:
+            problems.append("release notes missing for " + ", ".join(sorted(missing)))
+        return BundledRuntimeEvidence(
+            name="claude-code",
+            from_version=versions[0],
+            to_version=versions[1],
+            status="incomplete" if problems else "found",
+            sources=tuple(sources),
+            releases=tuple(releases[key] for key in sorted(releases)),
+            unavailable_reason="; ".join(problems),
+        )
+    except Exception as exc:
+        return BundledRuntimeEvidence(
+            name="claude-code",
+            from_version=versions[0] if versions else None,
+            to_version=versions[1] if len(versions) > 1 else None,
+            status="unavailable",
+            sources=tuple(sources),
+            unavailable_reason=str(exc),
+        )
+
+
+def _claude_cli_version(content: str) -> str:
+    tree = ast.parse(content)
+    for node in tree.body:
+        if isinstance(node, ast.Assign) and any(
+            isinstance(target, ast.Name) and target.id == "__cli_version__"
+            for target in node.targets
+        ):
+            value = ast.literal_eval(node.value)
+            if isinstance(value, str) and re.fullmatch(r"\d+\.\d+\.\d+", value):
+                return value
+    raise ValueError("SDK bundled CLI version is missing or unsupported")
+
+
 def fetch_url_text(url: str) -> str:
     """Fetch a release-note source as text."""
 

{agent_runtime_kit-0.5.4 → agent_runtime_kit-0.5.6}/examples/sdk_evolution_agent/report.py

@@ -154,6 +154,19 @@ def render_markdown_report(
         for item in release_notes
         if isinstance(item, dict) and item.get("to_version")
     ]
+    for item in release_notes:
+        if not isinstance(item, dict):
+            continue
+        bundled = item.get("bundled_runtime")
+        if isinstance(bundled, dict):
+            release_lines.append(
+                "- {name} (bundled): {status} ({from_version} -> {to_version})".format(
+                    name=bundled.get("name"),
+                    status=bundled.get("status"),
+                    from_version=bundled.get("from_version"),
+                    to_version=bundled.get("to_version"),
+                )
+            )
     behavior_summary = assess_behavior_payload(
         behavior,
         expectations=behavior_expectations_from_evidence(evidence),

{agent_runtime_kit-0.5.4 → agent_runtime_kit-0.5.6}/examples/sdk_evolution_agent/snapshots.py

@@ -584,6 +584,25 @@ def _definition_fingerprints(
                     )
                 )
                 visit(child, (*parents, child.name))
+            elif (
+                not parents
+                and isinstance(child, (ast.Assign, ast.AnnAssign))
+                and isinstance(child.value, (ast.Name, ast.Attribute))
+            ):
+                targets = child.targets if isinstance(child, ast.Assign) else [child.target]
+                fingerprint = hashlib.sha256(
+                    ast.dump(child, include_attributes=False).encode("utf-8")
+                ).hexdigest()
+                for target in targets:
+                    if isinstance(target, ast.Name) and target.id[:1].isupper():
+                        definitions.append(
+                            ImplementationDefinition(
+                                name=f"{path}:{target.id}",
+                                kind="alias",
+                                path=path,
+                                sha256=fingerprint,
+                            )
+                        )
             else:
                 visit(child, parents)
 
@@ -657,6 +676,23 @@ _SNAPSHOT_SCRIPT = textwrap.dedent(
                         "sha256": fingerprint,
                     })
                     visit(child, (*parents, child.name))
+                elif (
+                    not parents
+                    and isinstance(child, (ast.Assign, ast.AnnAssign))
+                    and isinstance(child.value, (ast.Name, ast.Attribute))
+                ):
+                    targets = child.targets if isinstance(child, ast.Assign) else [child.target]
+                    fingerprint = hashlib.sha256(
+                        ast.dump(child, include_attributes=False).encode("utf-8")
+                    ).hexdigest()
+                    for target in targets:
+                        if isinstance(target, ast.Name) and target.id[:1].isupper():
+                            definitions.append({
+                                "name": f"{path}:{target.id}",
+                                "kind": "alias",
+                                "path": path,
+                                "sha256": fingerprint,
+                            })
                 else:
                     visit(child, parents)
 

{agent_runtime_kit-0.5.4 → agent_runtime_kit-0.5.6}/examples/sdk_evolution_agent/stages.py

@@ -567,6 +567,35 @@ def with_release_note_guard(
         for item in release_notes
         if item.get("to_version") and item.get("status") == "unavailable"
     ]
+    for item in release_notes:
+        runtime = item.get("bundled_runtime")
+        if item.get("package") != "claude-agent-sdk" or not item.get("to_version"):
+            continue
+        if not isinstance(runtime, Mapping) or runtime.get("status") not in {
+            "found",
+            "not-needed",
+        }:
+            failed.append("claude-agent-sdk bundled claude-code")
+        elif runtime.get("status") == "not-needed" and (
+            not runtime.get("from_version")
+            or runtime.get("from_version") != runtime.get("to_version")
+        ):
+            failed.append("claude-agent-sdk bundled claude-code")
+        elif runtime.get("status") == "found":
+            releases = runtime.get("releases")
+            if (
+                not runtime.get("from_version")
+                or not runtime.get("to_version")
+                or not isinstance(releases, list)
+                or not any(
+                    isinstance(release, Mapping)
+                    and release.get("version") == runtime.get("to_version")
+                    and isinstance(release.get("notes"), str)
+                    and bool(release["notes"].strip())
+                    for release in releases
+                )
+            ):
+                failed.append("claude-agent-sdk bundled claude-code")
     if not failed:
         return dict(architecture)
     result = dict(architecture)
@@ -970,6 +999,8 @@ def _stage_system_prompt(stage: str, schema: JsonSchema) -> str:
             "evidence, remains a hard blocker. Release-note status found "
             "is direct release-note evidence. Status no-matching-version is source "
             "coverage with explicit uncertainty, not unavailable evidence."
+            " Bundled runtime release notes are separate from SDK release notes; "
+            "unavailable or incomplete bundled-runtime evidence is a hard blocker."
         )
     if stage == "review":
         prompt += " The review status must be exactly pass or reject."

{agent_runtime_kit-0.5.4 → agent_runtime_kit-0.5.6}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "agent-runtime-kit"
-version = "0.5.4"
+version = "0.5.6"
 description = "One typed runtime API for Claude, Codex, and Antigravity agent SDKs."
 readme = "README.md"
 requires-python = ">=3.10"
@@ -48,12 +48,12 @@ dependencies = ["jsonschema>=4.18,<5", "tomli>=2,<3; python_version < '3.11'"]
 claude = ["claude-agent-sdk>=0.2.87,<0.3"]
 # 0.157.1 is the minimum SDK and CLI pair for native named profiles. Earlier
 # bundled CLIs do not enforce every profile rule needed by restricted runtimes.
-codex = ["openai-codex>=0.157.1,<0.164"]
+codex = ["openai-codex>=0.157.1,<0.168"]
 antigravity = ["google-antigravity>=0.1.2,<0.2"]
 all = [
     "claude-agent-sdk>=0.2.87,<0.3",
     "google-antigravity>=0.1.2,<0.2",
-    "openai-codex>=0.157.1,<0.164",
+    "openai-codex>=0.157.1,<0.168",
 ]
 
 [project.urls]

{agent_runtime_kit-0.5.4 → agent_runtime_kit-0.5.6}/src/agent_runtime_kit/compatibility.py

@@ -66,17 +66,17 @@ COMPATIBILITY_MANIFEST: tuple[RuntimeCompatibility, ...] = (
         package="claude-agent-sdk",
         module="claude_agent_sdk",
         version_specifier=">=0.2.87,<0.3",
-        tested_version="0.2.168",
+        tested_version="0.2.179",
     ),
     RuntimeCompatibility(
         kind=AgentRuntimeKind.CODEX_AGENT_SDK,
         extra="codex",
         package="openai-codex",
         module="openai_codex",
-        version_specifier=">=0.157.1,<0.164",
-        tested_version="0.163.0",
+        version_specifier=">=0.157.1,<0.168",
+        tested_version="0.167.0",
         tested_runtime_dependencies=(
-            PackageVersion(package="openai-codex-cli-bin", version="0.163.0"),
+            PackageVersion(package="openai-codex-cli-bin", version="0.167.0"),
         ),
     ),
     RuntimeCompatibility(
@@ -85,7 +85,7 @@ COMPATIBILITY_MANIFEST: tuple[RuntimeCompatibility, ...] = (
         package="google-antigravity",
         module="google.antigravity",
         version_specifier=">=0.1.2,<0.2",
-        tested_version="0.1.22",
+        tested_version="0.1.23",
     ),
 )