Skip to content

[FIX] Bump Authlib 1.2.1 -> 1.6.12 & PyMySQL 1.1.0 -> 1.1.1 (clear critical Dependabot alerts)#2041

Open
jaseemjaskp wants to merge 1 commit into
mainfrom
fix/dependabot-authlib-pymysql
Open

[FIX] Bump Authlib 1.2.1 -> 1.6.12 & PyMySQL 1.1.0 -> 1.1.1 (clear critical Dependabot alerts)#2041
jaseemjaskp wants to merge 1 commit into
mainfrom
fix/dependabot-authlib-pymysql

Conversation

@jaseemjaskp

Copy link
Copy Markdown
Contributor

What

Bumps two hard-pinned Python packages to clear their critical Dependabot alerts:

  • Authlib 1.2.1 → 1.6.12 (backend/pyproject.toml)
  • PyMySQL 1.1.0 → 1.1.1 (unstract/connectors/pyproject.toml)

Re-locks the affected workspaces: backend/uv.lock, unstract/connectors/uv.lock, workers/uv.lock, uv.lock.

Why

  • Authlib 1.2.1 carried the 🔴 critical JWS JWK header-injection signature-verification bypass, plus high-severity OIDC fail-open, JWE RSA1_5 Bleichenbacher padding oracle, unknown-crit-header bypass, and oversized-JOSE DoS. Notably, backend was the only place still on 1.2.1 — every other service in the monorepo already runs 1.6.12, so this just brings backend in line (no new Authlib version introduced).
  • PyMySQL 1.1.0 carried the 🔴 critical SQL-injection alert. It's pinned only in connectors, but appears (via unstract-connectors) in the backend/workers/root locks too — bumping the connectors pin propagates to all of them.

How

  • Edited both pins, then uv lock --upgrade-package for authlib/pymysql across backend, connectors, workers, and the root workspace.

Can this PR break any existing features. If yes, please list possible items. If no, please explain why. (PS: Admins do not merge the PR without this section filled)

PyMySQL is a patch bump (1.1.0 → 1.1.1) — negligible risk.

Authlib 1.2 → 1.6 is the one to watch. It's a multi-minor jump and backend's auth plugins import Authlib directly, so JWS/JWT/OIDC behaviour could shift. Mitigating factors:

  • Every other monorepo service already runs 1.6.12 successfully, and backend depends on those shared packages — so 1.6.x is already proven compatible with the shared code paths.
  • Backend lock diff is Authlib + PyMySQL only (no transitive churn); all four locks pass uv lock --check.

👉 Reviewers: please exercise the auth flows (login/OAuth/JWT) in CI/staging before merge — a local backend import smoke-test could not be run (backend env creation is blocked by an unrelated, pre-existing django-celery-beat==2.5.0 wheel packaging quirk that uv rejects).

Database Migrations

None.

Env Config

None.

Relevant Docs

Authlib changelog

Related Issues or PRs

Dependabot remediation series — follows #2038 (frontend), #2039 (Python transitive), #2040 (Django).

Dependencies Versions

Authlib 1.2.1 → 1.6.12 · PyMySQL 1.1.0 → 1.1.1

Notes on Testing

  • uv lock --check on backend / connectors / workers / root ✓
  • PyMySQL 1.1.1 install confirmed (uv pip show + pymysql.VERSION (1,1,1,'final',1)).
  • Authlib auth-flow testing to be done in CI/staging (local backend env blocked, see above).

Screenshots

N/A — dependency bump.

Checklist

I have read and understood the Contribution Guidelines.

…abot)

Both were hard-pinned, so this updates the pins plus the affected locks.

- Authlib (backend/pyproject.toml): 1.2.1 -> 1.6.12 — clears the critical
  JWS JWK header-injection signature-verification bypass, plus OIDC
  fail-open, JWE RSA1_5 Bleichenbacher oracle, unknown-crit-header bypass,
  and oversized-JOSE DoS. 1.6.12 matches the version every other service
  in the monorepo already runs (no third Authlib version introduced).
- PyMySQL (unstract/connectors/pyproject.toml): 1.1.0 -> 1.1.1 — clears the
  critical SQL injection alert; propagated to backend, workers and root
  locks (they get PyMySQL via unstract-connectors).

Verified: backend, connectors, workers and root locks pass 'uv lock --check';
backend lock diff is Authlib + PyMySQL only (no transitive churn); PyMySQL
1.1.1 confirmed installed (uv pip show + pymysql.VERSION).

Note: Authlib 1.2 -> 1.6 is a multi-minor jump touching the backend auth
plugins — auth flows must be exercised in CI/staging. Local backend import
is blocked by the unrelated django-celery-beat 2.5.0 wheel quirk.
@coderabbitai

coderabbitai Bot commented Jun 11, 2026

Copy link
Copy Markdown
Contributor

Summary by CodeRabbit

  • Chores
    • Updated authentication library dependency to version 1.6.12
    • Updated MySQL database connector dependency to version 1.1.1

Walkthrough

Two dependency version updates across separate project modules: Authlib upgraded from 1.2.1 to 1.6.12 in the backend, and PyMySQL upgraded from 1.1.0 to 1.1.1 in the connectors subsystem.

Changes

Dependency Version Updates

Layer / File(s) Summary
Authlib auth plugin dependency upgrade
backend/pyproject.toml
Authlib dependency bumped from 1.2.1 to 1.6.12 in backend project dependencies for auth plugins.
PyMySQL connector dependency upgrade
unstract/connectors/pyproject.toml
PyMySQL dependency upgraded from 1.1.0 to 1.1.1 in connectors module for MySQL connectivity.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The title accurately summarizes the main changes: bumping Authlib and PyMySQL versions to clear critical Dependabot alerts, which aligns with the changeset.
Description check ✅ Passed The description is comprehensive and covers all template sections with substantial detail about vulnerability fixes, risks, testing approach, and interdependencies.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch fix/dependabot-authlib-pymysql

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@sonarqubecloud

Copy link
Copy Markdown

@github-actions

Copy link
Copy Markdown
Contributor

Unstract test results

Per-group results

Status Group Tier Passed Failed Errors Skipped Duration (s)
unit-connectors unit 64 12 0 3 16.5
unit-core unit 0 0 2 0 1.1
unit-platform-service unit 9 0 1 0 1.2
unit-prompt-service unit 15 0 0 0 20.0
unit-rig unit 53 0 0 0 3.1
unit-runner unit 11 0 0 0 3.0
unit-sdk1 unit 390 0 0 0 20.9
unit-tool-registry unit 0 0 1 0 1.3
unit-workers unit 0 0 0 0 16.9
TOTAL 542 12 4 3 84.0

Critical paths

⚠️ Critical paths not yet covered

  • auth-login — User can log in and obtain a session cookie. (entry: POST /api/v1/auth/login; declared coverage: no groups declared)
  • adapter-register-llm — Register and validate an LLM adapter. (entry: POST /api/v1/adapter/; declared coverage: no groups declared)
  • workflow-create-execute — Create a workflow, configure source+destination, execute, poll, fetch result. (entry: POST /api/v1/workflow/{id}/execute/; declared coverage: e2e-workflow)
  • api-deployment-run — Deploy a workflow as an API, POST a document, receive structured JSON. (entry: POST /deployment/api/{org}/{name}/; declared coverage: e2e-api-deployment)
  • prompt-studio-fetch-response — Prompt Studio: create project, add prompt, run single-pass, get response. (entry: POST /api/v1/prompt-studio/prompt-studio-tool/{id}/fetch_response/; declared coverage: e2e-prompt-studio)
  • pipeline-etl-execute — Run an ETL pipeline from source connector to destination. (entry: POST /api/v1/pipeline/{id}/execute/; declared coverage: no groups declared)
  • usage-token-tracking — Per-execution token usage is recorded and retrievable. (entry: GET /api/v1/usage/get_token_usage/; declared coverage: no groups declared)
  • workflow-execution-fan-out — Multi-file workflow execution fans out to file-processing workers and rejoins. (entry: internal: backend → rabbitmq → workers/file_processing; declared coverage: no groups declared)
  • callback-result-delivery — Async results are posted back via the callback worker. (entry: internal: workers/callback → backend /internal endpoints; declared coverage: no groups declared)
✅ Covered critical paths
  • tool-sandbox-exec — covered by unit-runner

@greptile-apps

greptile-apps Bot commented Jun 11, 2026

Copy link
Copy Markdown
Contributor

Greptile Summary

This PR bumps two hard-pinned Python dependencies to address critical Dependabot security alerts: Authlib 1.2.1 → 1.6.12 in backend/pyproject.toml and PyMySQL 1.1.0 → 1.1.1 in unstract/connectors/pyproject.toml, with the four affected lock files regenerated consistently.

  • Authlib bump (backend only): Resolves critical JWS header-injection signature-verification bypass, OIDC fail-open, JWE Bleichenbacher padding oracle, and unknown-crit-header bypass CVEs. The only direct Authlib consumer in the visible codebase is the auth_sample plugin stub (authlib.integrations.django_client.OAuth), which is unlikely to be affected by the 1.2→1.6 API delta; however, actual authentication plugins (likely private) must be exercised in CI/staging before merge.
  • PyMySQL bump (connectors workspace): Patch-level fix (1.1.0 → 1.1.1) for the critical SQL-injection CVE; propagates cleanly to backend, workers, and root lock files via the unstract-connectors dependency chain.
  • Lock file hygiene: All four lock files (backend/uv.lock, unstract/connectors/uv.lock, workers/uv.lock, uv.lock) are updated with only the expected Authlib and PyMySQL hash swaps — no transitive churn.

Confidence Score: 4/5

Safe to merge once auth flows (login/OAuth/JWT) are exercised in CI or staging — the lock files are clean and no transitive packages shifted.

Both pin changes are minimal and well-scoped: PyMySQL is a patch bump with negligible risk, and the Authlib hashes in all four lock files match the expected PyPI artifacts with no transitive churn. The only direct Authlib consumer visible in the repository is the auth_sample stub, which uses only the high-level django_client.OAuth integration — a stable surface across 1.x. The real concern is the actual (private) authentication plugins that the backend loads at runtime: the 1.2→1.6 multi-minor jump includes behavioural changes to JWS, JWE, and OIDC handling that could silently alter token validation. The PR author flagged this and requested CI/staging auth-flow testing, which is the right gate before merging.

No files require structural attention. The four lock files are all correctly regenerated; if reviewers want to spot-check, backend/uv.lock is the most meaningful one since it carries both the Authlib and PyMySQL bumps.

Important Files Changed

Filename Overview
backend/pyproject.toml Authlib pin updated from 1.2.1 to 1.6.12; single-line change, correct version string
unstract/connectors/pyproject.toml PyMySQL pin bumped from 1.1.0 to 1.1.1; single-line patch-level fix
backend/uv.lock Lock updated for Authlib (1.2.1→1.6.12) and PyMySQL (1.1.0→1.1.1) with new PyPI hashes; no transitive package churn observed
unstract/connectors/uv.lock PyMySQL hash swapped to 1.1.1 wheel and sdist; lock is consistent with the pin change
uv.lock Root workspace lock updated for both Authlib and PyMySQL; changes are minimal and match expected bump
workers/uv.lock Workers lock updated for PyMySQL 1.1.1; Authlib was already resolved to 1.6.12 in workers (no change needed there)

Flowchart

%%{init: {'theme': 'neutral'}}%%
flowchart TD
    A["backend/pyproject.toml<br/>Authlib==1.6.12<br/>PyMySQL via connectors"] --> B["backend/uv.lock<br/>Authlib 1.2.1 → 1.6.12<br/>PyMySQL 1.1.0 → 1.1.1"]
    C["unstract/connectors/pyproject.toml<br/>PyMySQL==1.1.1"] --> D["unstract/connectors/uv.lock<br/>PyMySQL 1.1.0 → 1.1.1"]
    C --> E["workers/uv.lock<br/>PyMySQL 1.1.0 → 1.1.1"]
    C --> F["uv.lock (root)<br/>Authlib 1.2.1 → 1.6.12<br/>PyMySQL 1.1.0 → 1.1.1"]
    A --> F
    B --> G["backend auth plugins<br/>authlib.integrations.django_client.OAuth<br/>Needs CI/staging auth flow test"]
    D --> H["MySQL connectors<br/>patch bump — negligible risk"]
Loading

Reviews (1): Last reviewed commit: "[FIX] Bump Authlib 1.2.1 -> 1.6.12 and P..." | Re-trigger Greptile

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 2

🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@backend/pyproject.toml`:
- Line 16: You upgraded Authlib to 1.6.12 which crosses several breaking
changes; either pin the dependency to a safe tested version (e.g., maintain
1.2.x) or run and update our auth/OIDC/JWT codepaths: audit usages of
has_client_secret, request_invalid, token_revoked, ClientSecretJWT.sign,
InvalidGrantError handling, OpenIDImplicitGrant/OpenIDHybridGrant redirect_uri
behavior, any custom OAuth2AuthorizationCodeMixin code, and authlib.jose.jwt
JWE/JWT algorithm handling (and check Python 3.8 support), then update
callers/handlers and tests to match the new APIs before merging.

In `@unstract/connectors/pyproject.toml`:
- Line 42: Replace the pinned dependency string "PyMySQL==1.1.1" with the
current release "PyMySQL==1.2.0" in the project's pyproject.toml dependency list
to move to the latest patched version; update any lockfile or regenerate
dependencies (e.g., poetry lock / pip-compile) and run tests to ensure
compatibility with the bumped PyMySQL version.
🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

  • Push a commit to this branch (recommended)
  • Create a new PR with the fixes

ℹ️ Review info
⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: 333dd116-6685-468e-b889-77e66a13d338

📥 Commits

Reviewing files that changed from the base of the PR and between cafcca7 and 832c6d7.

⛔ Files ignored due to path filters (4)
  • backend/uv.lock is excluded by !**/*.lock
  • unstract/connectors/uv.lock is excluded by !**/*.lock
  • uv.lock is excluded by !**/*.lock
  • workers/uv.lock is excluded by !**/*.lock
📒 Files selected for processing (2)
  • backend/pyproject.toml
  • unstract/connectors/pyproject.toml

Comment thread backend/pyproject.toml

dependencies = [
"Authlib==1.2.1", # For Auth plugins
"Authlib==1.6.12", # For Auth plugins

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟠 Major

🧩 Analysis chain

🌐 Web query:

Authlib changelog breaking changes from version 1.2.1 to 1.6.12 migration guide

💡 Result:

Authlib changelog “breaking changes” from 1.2.1 to 1.6.12 (migration guidance): 1) Versions 1.2.1 (2023-06-25): remove/behavior changes you may need to account for - Removed has_client_secret method and its documentation. [1][2] - Removed request_invalid and token_revoked remaining occurrences and documentation. [1][2] - ClientSecretJWT.sign now applies headers (via PR #552), which can affect how client secrets are signed. [1][2] - authorize_redirect fix for Starlette v0.26.0. [1][2] - grant uri params: “Allow falsy but non-None grant uri params” (PR #544) may change validation logic around grant URI parameters. [1][2] - Fixed RFC7591 grant_types and response_types default values. [1][2] 2) Authlib 1.6.x line: additional breaking changes called out in the changelog - Authlib 1.6.0 page exists and indicates there are “Breaking changes” sections between 1.x releases; use the changelog view to extract the specific items for the versions you are skipping. [3] - In the repo changelog file, Authlib 1.6.9 shows breaking changes including: a) Support for acr and amr claims in id_token, requiring a migration in OAuth2AuthorizationCodeMixin to support new fields. [4] b) Stop support for Python 3.8. [4] c) Raise InvalidGrantError for invalid code, redirect_uri and no user errors in OAuth 2.0 server (i.e., changed error behavior). [4] d) authlib.jose.jwt only works with JWS algorithms by default; to use JWT with JWE algorithms you must pass an algorithms parameter (example shown in changelog). [4] 3) 1.6.12 (2026-05-04): last-mile change in your target range - v1.6.12 fixes redirecting to an unvalidated redirect_uri on InvalidScopeError in OpenIDImplicitGrant and OpenIDHybridGrant. [5] 4) Most important “migration guide” aspect in this range: prepare for the jose -> joserfc migration Authlib’s upgrade material for the broader 1.x -> 2.0 transition highlights a major module migration: - There is an explicit “Upgrade Guide: joserfc migration.” link on the Authlib upgrades changelog pages. [6] - Authlib notes it will remove the authlib.jose module in 2.0.0, and to use joserfc instead (migration PR message). [7] Practical migration approach (how to apply the above): - Start by searching the Authlib stable changelog between exactly the versions you skip (1.2.1 -> 1.6.12) and copy the “Breaking changes” bullet points for each intermediate release that you’re not already on. The official changelog provides a full list of changes “between each Authlib release.” [1] - Specifically review for removed APIs: has_client_secret, and request_invalid/token_revoked documentation/occurrences. [1][2] - Specifically review for behavior changes around OAuth error handling and validation: InvalidGrantError changes and redirect_uri handling in 1.6.12. [4][5] - If you rely on id_token customization: ensure OAuth2AuthorizationCodeMixin migration for acr/amr support (1.6.9 breaking change). [4] - If your deployment still targets Python 3.8, this must change (1.6.9 breaking change). [4] - If you use authlib.jose JWT/JWE: pass algorithms explicitly to use JWE algorithms (1.6.9 breaking change). [4] - Plan for jose -> joserfc migration even though it’s not necessarily “breaking” for 1.6.12 itself; the project is actively documenting and moving away from authlib.jose. [6][7] If you want, paste your stack (OAuth2 vs OIDC, client vs server, frameworks, and which classes you use), and I’ll map the above breaking bullets to the most likely code changes in your app.

Citations:


Authlib 1.6.12 upgrade: changelog shows auth/OIDC/JWT breaking/behavior changes

Even though the security fix is important, the jump from Authlib 1.2.1 → 1.6.12 crosses multiple “breaking changes” in the 1.2.x–1.6.x line. Key items to validate for your auth plugins:

  • Removed/changed APIs: has_client_secret; request_invalid / token_revoked remnants; ClientSecretJWT.sign behavior now applies headers
  • OAuth/OIDC error/redirect behavior: InvalidGrantError handling changes; 1.6.12 redirect_uri validation fix on InvalidScopeError in OpenIDImplicitGrant / OpenIDHybridGrant
  • OIDC id_token claim support: 1.6.9 introduces acr/amr support in id_token (may require OAuth2AuthorizationCodeMixin migration if you customize)
  • jose/JWT/JWE compatibility: authlib.jose.jwt algorithm handling changes (JWE may require passing algorithms)
  • Environment constraints: 1.6.9 drops Python 3.8 support
  • Also consider the broader documented authlib.josejoserfc migration path

Run/confirm integration coverage for the specific auth/OIDC/JWT codepaths in this backend (redirect_uri handling, token/authorization flows, and any client secret/JWT/JWE logic) before relying on the change.

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@backend/pyproject.toml` at line 16, You upgraded Authlib to 1.6.12 which
crosses several breaking changes; either pin the dependency to a safe tested
version (e.g., maintain 1.2.x) or run and update our auth/OIDC/JWT codepaths:
audit usages of has_client_secret, request_invalid, token_revoked,
ClientSecretJWT.sign, InvalidGrantError handling,
OpenIDImplicitGrant/OpenIDHybridGrant redirect_uri behavior, any custom
OAuth2AuthorizationCodeMixin code, and authlib.jose.jwt JWE/JWT algorithm
handling (and check Python 3.8 support), then update callers/handlers and tests
to match the new APIs before merging.

"google-cloud-bigquery==3.11.4", # For Bigquery
"pymssql==2.3.4", # For MSSQL
"PyMySQL==1.1.0", # For MySQL
"PyMySQL==1.1.1", # For MySQL

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
# Description: Verify PyMySQL version 1.1.1 is current and secure

# Check PyPI for the latest PyMySQL version
echo "=== Latest PyMySQL version on PyPI ==="
curl -s https://pypi.org/pypi/pymysql/json | jq -r '.info.version'

# Check for security advisories using GitHub CLI
echo -e "\n=== Security advisories for PyMySQL ==="
gh api graphql -f query='
{
  securityVulnerabilities(first: 10, ecosystem: PIP, package: "pymysql") {
    nodes {
      advisory {
        summary
        severity
        publishedAt
      }
      vulnerableVersionRange
      firstPatchedVersion {
        identifier
      }
    }
  }
}'

Repository: Zipstack/unstract

Length of output: 1986


🌐 Web query:

PyPI latest version pymysql 1.1.1

💡 Result:

As of June 11, 2026, the latest version of PyMySQL on PyPI is 1.2.0, which was released on May 19, 2026 [1][2][3]. PyMySQL 1.1.1 was released on May 21, 2024 [4][5]. It is a historical version that included a fix for a security vulnerability (CVE-2024-36039), which addressed a potential SQL injection issue related to dict parameters in Cursor.execute() [5][6]. Users are encouraged to update to the latest available version (1.2.0) to ensure they have the most recent security patches and features [3].

Citations:


🌐 Web query:

OSV or GitHub security advisories for pymysql affected versions

💡 Result:

The primary security advisory for PyMySQL is CVE-2024-36039, which is documented in the GitHub Advisory Database as GHSA-v9hf-5j83-6xpp [1][2]. Affected Versions All versions of PyMySQL up to and including 1.1.0 are affected by this vulnerability [3][2]. Patched Version The vulnerability was resolved in version 1.1.1 [4][5]. Users are strongly recommended to upgrade to version 1.1.1 or later to mitigate this risk [6][5]. Vulnerability Details The issue is an SQL injection vulnerability (CWE-89) [3][2]. It occurs because the library's escape_dict function does not properly escape dictionary keys when processing untrusted JSON input, potentially allowing an attacker to execute arbitrary SQL commands [2][7]. In version 1.1.1, the maintainers addressed this by prohibiting the use of dictionary parameters in the Cursor.execute method, as this usage pattern did not produce valid SQL and introduced the injection risk [6][4][5]. If an immediate upgrade is not possible, maintainers recommend ensuring that any input from untrusted sources is strictly validated to have the expected type, as dictionary inputs are the primary attack vector [6][8][5].

Citations:


Update PyMySQL pin: 1.1.1 is patched but not latest (as of 2026-06-11).

  • PyMySQL==1.1.1 fixes the SQL-injection issue for CVE-2024-36039 / GHSA-v9hf-5j83-6xpp (affected through 1.1.0), so the security intent of the bump is correct.
  • PyPI latest is PyMySQL==1.2.0 (released 2026-05-19), so consider bumping from 1.1.11.2.0 to stay current with any additional patches.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@unstract/connectors/pyproject.toml` at line 42, Replace the pinned dependency
string "PyMySQL==1.1.1" with the current release "PyMySQL==1.2.0" in the
project's pyproject.toml dependency list to move to the latest patched version;
update any lockfile or regenerate dependencies (e.g., poetry lock / pip-compile)
and run tests to ensure compatibility with the bumped PyMySQL version.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant