chore(deps): update python-nonmajor

[renovate-bot]

ℹ️ Note

This PR body was truncated due to platform limits.

This PR contains the following updates:

Package	Change	Age	Confidence
black (changelog)	==26.1.0 → ==26.3.1
google-adk (changelog)	==1.27.2 → ==1.27.5
google-auth	==2.45.0 → ==2.49.1
google-auth	==2.47.0 → ==2.49.1
google-auth-oauthlib (source)	==1.2.1 → ==1.3.0
google-cloud-storage	==3.7.0 → ==3.10.1
isort (changelog)	==8.0.0 → ==8.0.1
langchain-core (changelog)	==1.2.11 → ==1.2.22
llama-index-core	==0.14.12 → ==0.14.19
opentelemetry-exporter-gcp-trace (source)	==1.9.0 → ==1.11.0
opentelemetry-exporter-otlp-proto-http	==1.37.0 → ==1.40.0
opentelemetry-sdk	==1.37.0 → ==1.40.0
pillow (changelog)	==12.1.0 → ==12.1.1
pytest-cov (changelog)	==7.0.0 → ==7.1.0
requests (changelog)	==2.32.5 → ==2.33.0
typing-extensions (changelog)	==4.14.1 → ==4.15.0

---

Release Notes

psf/black (black)

v26.3.1

Compare Source

Stable style

• Prevent Jupyter notebook magic masking collisions from corrupting cells by using
  exact-length placeholders for short magics and aborting if a placeholder can no longer
  be unmasked safely (#​5038)

Configuration

• Always hash cache filename components derived from --python-cell-magics so custom
  magic names cannot affect cache paths (#​5038)

Blackd

• Disable browser-originated requests by default, add configurable origin allowlisting
  and request body limits, and bound executor submissions to improve backpressure
  (#​5039)

v26.3.0

Compare Source

Stable style

• Don't double-decode input, causing non-UTF-8 files to be corrupted (#​4964)
• Fix crash on standalone comment in lambda default arguments (#​4993)
• Preserve parentheses when # type: ignore comments would be merged with other
  comments on the same line, preventing AST equivalence failures (#​4888)

Preview style

• Fix bug where if guards in case blocks were incorrectly split when the pattern had
  a trailing comma (#​4884)
• Fix string_processing crashing on unassigned long string literals with trailing
  commas (one-item tuples) (#​4929)
• Simplify implementation of the power operator "hugging" logic (#​4918)

Packaging

• Fix shutdown errors in PyInstaller builds on macOS by disabling multiprocessing in
  frozen environments (#​4930)

Performance

• Introduce winloop for windows as an alternative to uvloop (#​4996)
• Remove deprecated function uvloop.install() in favor of uvloop.new_event_loop()
  (#​4996)
• Rename maybe_install_uvloop function to maybe_use_uvloop to simplify loop
  installation and creation of either a uvloop/winloop evenloop or default eventloop
  (#​4996)

Output

• Emit a clear warning when the target Python version is newer than the running Python
  version, since AST safety checks cannot parse newer syntax. Also replace the
  misleading "INTERNAL ERROR" message with an actionable error explaining the version
  mismatch (#​4983)

Blackd

• Introduce winloop to be used when windows in use which enables blackd to run faster on
  windows when winloop is installed. (#​4996)

Integrations

• Remove unused gallery script (#​5030)
• Harden parsing of black requirements in the GitHub Action when use_pyproject is
  enabled so that only version specifiers are accepted and direct references such as
  black @​ https://... are rejected. Users should upgrade to the latest version of the
  action as soon as possible. This update is received automatically when using
  psf/black@stable, and is independent of the version of Black installed by the
  action. (#​5031)

Documentation

• Expand preview style documentation with detailed examples for wrap_comprehension_in,
  simplify_power_operator_hugging, and wrap_long_dict_values_in_parens features
  (#​4987)
• Add detailed documentation for formatting Jupyter Notebooks (#​5009)

google/adk-python (google-adk)

v1.27.5

Compare Source

Bug Fixes

• Update eval extras to Vertex SDK package version with constrained LiteLLM upperbound (77928a8)

v1.27.4

Compare Source

Bug Fixes

• Exclude compromised LiteLLM versions from dependencies pin to 1.82.6 (fa5e707)
• gate builder endpoints behind web flag (44b3f72)

v1.27.3

Compare Source

Bug Fixes

• add protection for arbitrary module imports (276adfb)

googleapis/google-auth-library-python (google-auth)

v2.48.0

Compare Source

Features

• add cryptography as required dependency (#​1929) (52558ae2881b1e6555f6f5c0d76365c15807ead9)
• Support the mTLS IAM domain for Certificate based Access (#​1938) (8dcf91a1b05c85fbbd0bcee78d66e498099102ab)
• add configurable GCE Metadata Server retries (#​1488) (454b441b478ec62bbf1a6ad5bceb6c7cbbfd0c37)
• honor NO_GCE_CHECK environment variable (#​1610) (383c9827536d9376e8248370ce4c2b83e468d027)

Bug Fixes

• resolve circular imports (#​1942) (25c1b064545702cbef087cfcd15fbbb6ef1af74f)
• removes content-header from AWS IMDS get request (#​1934) (97bfea9e02ede953fc8ee154e0deed3a3cfc6dcc)
• detect correct auth when ADC env var is set but empty (#​1374) (bfc07e1050bd0aa86fa3b08cdf70c9b68b5fe6a2)
• replace deprecated utcfromtimestamp (#​1799) (e431f20cf73ccac71926a23ec454468cea92e053)
• Use user_verification=preferred for ReAuth WebAuthn challenge (#​1798) (3f88a24089c4ee6822d510de0db210b54260d873)

v2.47.0

Compare Source

Features

• drop cachetools dependency in favor of simple local implementation (#​1590) (5c07e1c4f52bc77a1b16fa3b7b3c5269c242f6f4)

Bug Fixes

• Python 3.8 support (#​1918) (60dc20014a35ec4ba71e8065b9a33ecbdbeca97a)

v2.46.0

Compare Source

Documentation

• update urllib3 docstrings for v2 compatibility (#​1903) (3f1aeea2d1014ea1d244a4c3470e52d74d55404b)

Features

• Recognize workload certificate config in has_default_client_cert_source for mTLS for Agentic Identities (#​1907) (0b9107d573123e358c347ffa067637f992af61b4)

Bug Fixes

• add types to default and verify_token and Request init based on comments in the source code. (#​1588) (59a5f588f7793b59d923a4185c8c07738da618f7)
• fix the document of secure_authorized_session (#​1536) (5d0014707fc359782df5ccfcaa75fd372fe9dce3)
• remove setup.cfg configuration for creating universal wheels (#​1693) (c767531ce05a89002d109f595187aff1fcaacfb7)
• use .read() instead of .content.read() in aiohttp transport (#​1899) (12f4470f808809e8abf1141f98d88ab720c3899b)
• raise RefreshError for missing token in impersonated credentials (#​1897) (94d04e090fdfc61926dd32bc1d65f8820b9cede5)
• Fix test coverage for mtls_helper (#​1886) (02e71631fe275d93825c2e957e830773e75133f7)

googleapis/google-cloud-python (google-auth-oauthlib)

v1.3.0: google-auth-oauthlib: v1.3.0

Compare Source

Features

• Log the flow.run_local_server redirect URL (#​362) (84599aa0)

Bug Fixes

• Raise meaningful exception when oauth callback times out (#​363) (adc3ee60)

googleapis/python-storage (google-cloud-storage)

v3.10.1

Compare Source

Bug Fixes

• raise ValueError if api_endpoint is unset when using AnonymousCredentials in AsyncGrpcClient. (#​1778) (17828ea316872938a98a6360b10a2495c54bbbcb)

v3.10.0

Compare Source

Features

• [Bucket Encryption Enforcement] add support for bucket encryption enforcement config (#​1742) (2a6e8b00e4e6ff57460373f8e628fd363be47811)

Perf Improvments

• [Rapid Buckets Reads] Use raw proto access for read resumption strategy (#​1764) (14cfd61ce35365a409650981239ef742cdf375fb)
• [Rapid Buckets Benchmarks] init mp pool & grpc client once, use os.sched_setaffinity (#​1751) (a9eb82c1b9b3c6ae5717d47b76284ed0deb5f769)
• [Rapid Buckets Writes] don't flush at every append, results in bad perf (#​1746) (ab62d728ac7d7be3c4fe9a99d72e35ead310805a)

Bug Fixes

• [Windows] skip downloading blobs whose name contain ":" eg: C: D: etc when application runs in Windows. (#​1774) (558198823ed51918db9c0137715d1e7f5b593975)
• [Path Traversal] Prevent path traversal in download_many_to_path (#​1768) (700fec3bf7aa37bd5ea4b163cc3f9e8e6892bd5a)
• [Rapid Buckets] pass token correctly, '&' instead of ',' (#​1756) (d8dd1e074d2431de9b45e0103181dce749a447a0)

v3.9.0

Compare Source

Features

• add get_object method for async grpc client (#​1735) (0e5ec29bc6a31b77bcfba4254cef5bffb199095c)
• expose DELETE_OBJECT in AsyncGrpcClient (#​1718) (c8dd7a0b124c395b7b60189ee78f47aba8d51f7d)
• update generation for MRD (#​1730) (08bc7082db7392f13bc8c51511b4afa9c7b157c9)
• Move Zonal Buckets features of _experimental (#​1728) (74c9ecc54173420bfcd48498a8956088a035af50)
• add default user agent for grpc (#​1726) (7b319469d2e495ea0bf7367f3949190e8f5d9fff)
• expose finalized_time in blob.py applicable for GET_OBJECT in ZB (#​1719) (8e21a7fe54d0a043f31937671003630a1985a5d2)
• add context manager to mrd (#​1724) (5ac2808a69195c688ed42c3604d4bfadbb602a66)
• integrate writes strategy and appendable object writer (#​1695) (dbd162b3583e32e6f705a51f5c3fef333a9b89d0)
• Add support for opening via write_handle and fix write_handle type (#​1715) (2bc15fa570683ba584230c51b439d189dbdcd580)
• Add micro-benchmarks for writes comparing standard (regional) vs rapid (zonal) buckets. (#​1707) (dbe9d8b89d975dfbed8c830a5687ccfafea51d5f)
• Add micro-benchmarks for reads comparing standard (regional) vs rapid (zonal) buckets. (#​1697) (1917649fac41481da1adea6c2a9f4ab1298a34c4)
• send user_agent to grpc channel (#​1712) (cdb2486bb051dcbfbffc2510aff6aacede5e54d3)
• add samples for appendable objects writes and reads (#​1705) (2e1a1eb5cbe1c909f1f892a0cc74fe63c8ef36ff)
• add samples for appendable objects writes and reads (2e1a1eb5cbe1c909f1f892a0cc74fe63c8ef36ff)
• add support for generation=0 to avoid overwriting existing objects and add is_stream_open support (#​1709) (ea0f5bf8316f4bfcff2728d9d1baa68dde6ebdae)
• add support for generation=0 to prevent overwriting existing objects (ea0f5bf8316f4bfcff2728d9d1baa68dde6ebdae)
• add is_stream_open property to AsyncAppendableObjectWriter for stream status check (ea0f5bf8316f4bfcff2728d9d1baa68dde6ebdae)

Bug Fixes

• receive eof while closing reads stream (#​1733) (2ef63396dca1c36f9b0f0f3cf87a61b5aa4bd465)
• Change contructors of MRD and AAOW AsyncGrpcClient.grpc_client to AsyncGrpcClient (#​1727) (e730bf50c4584f737ab86b2e409ddb27b40d2cec)
• instance grpc client once per process in benchmarks (#​1725) (721ea2dd6c6db2aa91fd3b90e56a831aaaa64061)
• update write handle on every recv() (#​1716) (5d9fafe1466b5ccb1db4a814967a5cc8465148a2)
• Fix formatting in setup.py dependencies list (#​1713) (cc4831d7e253b265b0b96e08b5479f4c759be442)
• implement requests_done method to signal end of requests in async streams. Gracefully close streams. (#​1700) (6c160794afded5e8f4179399f1fe5248e32bf707)
• implement requests_done method to signal end of requests in async streams. Gracefully close streams. (6c160794afded5e8f4179399f1fe5248e32bf707)

v3.8.0

Compare Source

Features

• flush the last chunk in append method (#​1699) (89bfe7a5fcd0391da35e9ceccc185279782b5420)
• add write resumption strategy (#​1663) (a57ea0ec786a84c7ae9ed82c6ae5d38ecadba4af)
• add bidi stream retry manager. (#​1632) (d90f0ee09902a21b186106bcf0a8cb0b81b34340)
• implement "append_from_file" (#​1686) (1333c956da18b4db753cda98c41c3619c84caf69)
• make flush size configurable (#​1677) (f7095faf0a81239894ff9d277849788b62eb6ac5)
• compute chunk wise checksum for bidi_writes (#​1675) (139390cb01f93a2d61e7ec201e3637dffe0b2a34)
• expose persisted size in mrd (#​1671) (0e2961bef285fc064174a5c18e3db05c7a682521)

Bug Fixes

• add system test for opening with read_handle (#​1672) (6dc711dacd4d38c573aa4ca9ad71fe412c0e49c1)
• no state lookup while opening bidi-write stream (#​1636) (2d5a7b16846a69f3a911844971241899f60cce14)
• close write object stream always (#​1661) (4a609a4b3f4ba1396825911cb02f8a9649135cd5)

PyCQA/isort (isort)

v8.0.1

Compare Source

Changes

• Fix #​2461: Added compression to stdlibs for Python 3.14 in isort/stdlibs/py314.py (#​2463) @​FinlayTheBerry
• Fix unindented comments being corrupted in indented blocks (#​2459) @​worksbyfriday

run-llama/llama_index (llama-index-core)

v0.14.19

Compare Source

llama-index-agent-agentmesh [0.2.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)

llama-index-callbacks-argilla [0.5.0]

• chore(deps): bump the uv group across 3 directories with 1 update (#​21069)

llama-index-core [0.14.19]

• fix: pass delete_from_docstore parameter in BaseIndex.delete_ref_doc (#​20990)
• fix(core): preserve CTE names during schema prefixing in SQLDatabase.run_sql (#​21028)
• fix(core): align sync retrieval dedup key with async (hash + ref_doc_id) (#​21034)
• fix(core): raise ValueError instead of returning string from structured_predict (#​21036)
• fix(core): remove incorrect per-node delete calls in index helpers (#​21050)
• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)
• enable llama-cloud>1.0 install (#​21140)

llama-index-embeddings-fireworks [0.5.2]

• test(embeddings-fireworks): add test suite and fix docs (#​20977)

llama-index-embeddings-upstage [0.6.1]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)

llama-index-indices-managed-llama-cloud [0.11.1]

• fix: llama-cloud managed index and remove llamaparse reader (#​21043)
• enable llama-cloud>1.0 install (#​21140)

llama-index-llms-azure-openai [0.5.3]

• azure openai responses support (#​21088)
• fix azure openai responses (#​21099)

llama-index-llms-bedrock-converse [0.14.3]

• use proper tool choice format in bedrock converse (#​21098)

llama-index-llms-cohere [0.8.0]

• docs(cohere): update first basic usage example to chat API (#​21108)

llama-index-llms-google-genai [0.9.1]

• feat: gemini 3 default and temperature (#​21060)
• fix(google-genai): avoid mutating messages list in prepare_chat_params (#​21141)

llama-index-llms-litellm [0.7.1]

• Add support for custom LLM provider in model kwargs (#​21095)

llama-index-llms-minimax [0.1.0]

• feat: add MiniMax LLM provider integration with M2.7 default (#​20955)

llama-index-llms-ollama [0.10.1]

• fix(ollama): pass custom headers to auto-created clients (#​21091)

llama-index-llms-openai [0.7.3]

• feat(llms/openai): Add support for Mini and Nano variants of GPT 5.4 (#​21065)

llama-index-llms-ovhcloud [0.2.1]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)

llama-index-packs-agent-search-retriever [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-amazon-product-extraction [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-arize-phoenix-query-engine [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-auto-merging-retriever [0.6.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-code-hierarchy [0.7.1]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-cohere-citation-chat [0.6.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-deeplake-deepmemory-retriever [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-deeplake-multimodal-retrieval [0.4.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-dense-x-retrieval [0.6.1]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-diff-private-simple-dataset [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-evaluator-benchmarker [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-fusion-retriever [0.6.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-fuzzy-citation [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-gmail-openai-agent [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-koda-retriever [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-llama-dataset-metadata [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-llama-guard-moderator [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-llava-completion [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-longrag [0.6.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-mixture-of-agents [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-multi-tenancy-rag [0.6.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-multidoc-autoretrieval [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-nebulagraph-query-engine [0.6.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-neo4j-query-engine [0.5.1]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-node-parser-semantic-chunking [0.5.1]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-ollama-query-engine [0.6.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-panel-chatbot [0.5.0]

• chore(deps): bump the uv group across 3 directories with 1 update (#​21069)
• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-raft-dataset [0.5.1]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-ragatouille-retriever [0.6.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-raptor [0.4.1]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-recursive-retriever [0.8.1]

• chore(deps): bump the uv group across 3 directories with 1 update (#​21069)
• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-searchain [0.3.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-self-discover [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-self-rag [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-sentence-window-retriever [0.6.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-snowflake-query-engine [0.6.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-stock-market-data-query-engine [0.6.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-streamlit-chatbot [0.5.2]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-sub-question-weaviate [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-packs-timescale-vector-autoretrieval [0.5.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)
• chore(deps): bump the uv group across 44 directories with 1 update (#​21097)

llama-index-postprocessor-google-rerank [0.1.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)

llama-index-readers-llama-parse [0.6.1]

• enable llama-cloud>1.0 install (#​21140)

llama-index-readers-service-now [0.3.0]

• chore(deps): bump nltk from 3.9.1 to 3.9.3 in /llama-index-integrations/readers/llama-index-readers-service-now in the uv group across 1 directory (#​21080)

llama-index-storage-chat-store-opensearch [0.2.0]

• chore(deps): bump the uv group across 49 directories with 1 update (#​21083)

llama-index-tools-aws-bedrock-agentcore [0.3.1]

• feat(tools/agentcore): add AgentCoreRuntime adapter (#​21008)
• fix bedrock tests (#​21129)

llama-index-tools-exa [0.5.1]

• update exa tool description and default search type (#​21096)

llama-index-vector-stores-redis [0.8.0]

• feat(redis): implement safe get_nodes and delete_nodes support (#​20972)

llama-index-voice-agents-gemini-live [0.4.0]

• feat: latest gemini model default (#​21061)

v0.14.18

llama-index-agent-agentmesh [0.2.0]

• chore: deprecate python 3.9 once and for all (#​20956)

llama-index-agent-azure [0.3.0]

• chore: deprecate python 3.9 once and for all (#​20956)

llama-index-callbacks-agentops [0.5.0]

• chore: deprecate python 3.9 once and for all (#​20956)

llama-index-callbacks-argilla [0.5.0]

• chore: deprecate python 3.9 once and for all (#​20956)

llama-index-callbacks-arize-phoenix [0.7.0]

• chore: deprecate python 3.9 once and for all (#​20956)

llama-index-callbacks-honeyhive [0.5.0]

• chore: deprecate python 3.9 once and for all (#​20956)
• chore(deps): bump the uv group across 51 directories with 3 updates (#​20962)

llama-index-callbacks-langfuse [0.5.0]

• chore: deprecate python 3.9 once and for all (#​20956)

llama-index-callbacks-literalai [1.4.0]

• chore: deprecate python 3.9 once and for all (#​20956)

llama-index-callbacks-openinference [0.5.0]

• chore: deprecate python 3.9 once and for all (#​20956)

llama-index-callbacks-opik [1.3.0]

• chore: deprecate python 3.9 once and for all (#​20956)

llama-index-callbacks-promptlayer [0.5.0]

• chore: deprecate python 3.9 once and for all (#​20956)

llama-index-callbacks-uptrain [0.6.0]

• chore: deprecate python 3.9 once and for all (#​20956)

llama-index-callbacks-wandb [0.5.0]

• chore: deprecate python 3.9 once and for all (#​20956)

llama-index-core [0.14.18]

• feat: align text match filters across core and vector backends (#​20883)
• fix(chat_engine): preserve chat history on incomplete stream consumption (#​20897)
• fix: guard against ZeroDivisionError in LlamaDebugHandler._get_time_stats_from_event_pairs (#​20937)
• fix: add stacklevel=2 to warnings.warn() for accurate caller reporting ([#&chore: Update renovate config to group kokoro dependency upgrades. #82

---

Configuration

📅 Schedule: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined).

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

👻 Immortal: This PR will be recreated if closed unmerged. Get config help if that's undesired.

---

• If you want to rebase/retry this PR, check this box

---

This PR was generated by Mend Renovate. View the repository job log.

[anubhav756]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[anubhav756]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[anubhav756]

/gcbrun

[dpebot]

/gcbrun

[anubhav756]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun

[dpebot]

/gcbrun