From ffaeba86641098bb468e0ce23fc6ac9cbea3b313 Mon Sep 17 00:00:00 2001
From: Mason Daugherty <mason@langchain.dev>
Date: Wed, 10 Jun 2026 22:45:17 -0400
Subject: [PATCH] ci(infra): validate release versions before publishing
 (#38055)

Release jobs can now be given an expected package version and will stop
early if that value does not match the package metadata. The workflow
also checks PyPI for an existing normalized release so duplicate version
attempts fail before build and publish steps continue.
---
 .github/workflows/_release.yml | 95 ++++++++++++++++++++++++++++------
 1 file changed, 80 insertions(+), 15 deletions(-)

diff --git a/.github/workflows/_release.yml b/.github/workflows/_release.yml
index 205706748ba..5f000b68e2f 100644
--- a/.github/workflows/_release.yml
+++ b/.github/workflows/_release.yml
@@ -26,6 +26,11 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
+      release-version:
+        required: false
+        type: string
+        default: ""
+        description: "Expected package version. If provided, must match pyproject.toml."
       allow-prereleases:
         required: false
         type: boolean
@@ -134,6 +139,81 @@ jobs:
           python-version: ${{ env.PYTHON_VERSION }}
           enable-cache: "false"
 
+      - name: Check version
+        id: check-version
+        shell: python
+        working-directory: ${{ env.EFFECTIVE_WORKING_DIR }}
+        env:
+          RELEASE_VERSION_INPUT: ${{ inputs.release-version }}
+        run: |
+          import os
+          import re
+          import sys
+          import tomllib
+          import urllib.error
+          import urllib.request
+
+          with open("pyproject.toml", "rb") as f:
+              data = tomllib.load(f)
+
+          pkg_name = data["project"]["name"]
+          version = data["project"]["version"]
+          requested_version = os.environ.get("RELEASE_VERSION_INPUT", "").strip()
+
+
+          def normalize(v):
+              # Lightweight PEP 440 comparison key: lowercase and drop the `-`,
+              # `_`, or `.` separators that precede a pre/post/dev segment so that
+              # e.g. `0.1.0-rc1` and `0.1.0rc1` compare equal. Full canonicalization
+              # lives in `packaging`, which isn't installed in this bare release step.
+              return re.sub(r"[-_.]+(?=[a-z])", "", v.lower())
+
+
+          if requested_version and normalize(requested_version) != normalize(version):
+              print(
+                  f"::error::Requested release version {requested_version!r} does "
+                  f"not match {pkg_name} pyproject.toml version {version!r}."
+              )
+              sys.exit(1)
+
+          # Query the per-version endpoint so PyPI applies PEP 440 normalization
+          # (e.g. `0.1.0-rc1` and `0.1.0rc1` resolve to the same release): HTTP 200
+          # means the version is already published, 404 means it's available
+          # (including the first-ever release of a new package). Only the status
+          # code is used, so a malicious or malformed response body can't mislead us.
+          url = f"https://pypi.org/pypi/{pkg_name}/{version}/json"
+          try:
+              with urllib.request.urlopen(url, timeout=10):
+                  already_published = True
+          except urllib.error.HTTPError as err:
+              if err.code == 404:
+                  already_published = False
+              else:
+                  # Fail closed: an unexpected status means we can't verify.
+                  print(
+                      f"::error::PyPI returned HTTP {err.code} checking whether "
+                      f"{pkg_name}=={version} exists; cannot verify, aborting."
+                  )
+                  sys.exit(1)
+          except urllib.error.URLError as err:
+              # Fail closed: if PyPI is unreachable we must not assume the version
+              # is free, or we risk re-publishing an existing release.
+              print(
+                  f"::error::Could not reach PyPI to verify {pkg_name}=={version} "
+                  f"({err.reason}); cannot verify, aborting."
+              )
+              sys.exit(1)
+
+          if already_published:
+              print(f"::error::{pkg_name}=={version} already exists on PyPI.")
+              sys.exit(1)
+
+          print(f"::notice::{pkg_name}=={version} is not yet on PyPI; proceeding.")
+
+          with open(os.environ["GITHUB_OUTPUT"], "a") as f:
+              f.write(f"pkg-name={pkg_name}\n")
+              f.write(f"version={version}\n")
+
       # We want to keep this build stage *separate* from the release stage,
       # so that there's no sharing of permissions between them.
       # (Release stage has trusted publishing and GitHub repo contents write access,
@@ -155,21 +235,6 @@ jobs:
         with:
           name: dist
           path: ${{ env.EFFECTIVE_WORKING_DIR }}/dist/
-
-      - name: Check version
-        id: check-version
-        shell: python
-        working-directory: ${{ env.EFFECTIVE_WORKING_DIR }}
-        run: |
-          import os
-          import tomllib
-          with open("pyproject.toml", "rb") as f:
-              data = tomllib.load(f)
-          pkg_name = data["project"]["name"]
-          version = data["project"]["version"]
-          with open(os.environ["GITHUB_OUTPUT"], "a") as f:
-              f.write(f"pkg-name={pkg_name}\n")
-              f.write(f"version={version}\n")
   release-notes:
     name: 📝 Generate release notes
     # release-notes must run before publishing because its check-tags step