chore(deps): bump the all-dependencies group across 1 directory with 9 updates

[dependabot]

Bumps the all-dependencies group with 9 updates in the /python/agents/travel-concierge directory:

Package	From	To
python-dotenv	1.2.1	1.2.2
google-genai	1.56.0	1.65.0
google-adk	1.21.0	1.26.0
openinference-instrumentation	0.1.42	0.1.46
arize	7.51.2	8.4.0
arize-phoenix-evals	2.7.1	2.11.0
ruff	0.14.10	0.15.4
types-requests	2.32.4.20250913	2.32.4.20260107
absl-py	2.3.1	2.4.0

Updates python-dotenv from 1.2.1 to 1.2.2

Release notes

Sourced from python-dotenv's releases.

v1.2.2

Added

• Support for Python 3.14, including the free-threaded (3.14t) build. (#)

Changed

• The dotenv run command now forwards flags directly to the specified command by @​bbc2 in theskumar/python-dotenv#607
• Improved documentation clarity regarding override behavior and the reference page.
• Updated PyPy support to version 3.11.
• Documentation for FIFO file support.
• Support for Python 3.9.

Fixed

• Improved set_key and unset_key behavior when interacting with symlinks by @​bbc2 in #790c5
• Corrected the license specifier and added missing Python 3.14 classifiers in package metadata by @​JYOuyang in theskumar/python-dotenv#590

Breaking Changes

• dotenv.set_key and dotenv.unset_key used to follow symlinks in some situations. This is no longer the case. For that behavior to be restored in all cases, follow_symlinks=True should be used.

• In the CLI, set and unset used to follow symlinks in some situations. This is no longer the case.

• dotenv.set_key, dotenv.unset_key and the CLI commands set and unset used to reset the file mode of the modified .env file to 0o600 in some situations. This is no longer the case: The original mode of the file is now preserved. Is the file needed to be created or wasn't a regular file, mode 0o600 is used.

Misc

• skip 000 permission tests for root user by @​burnout-projects in theskumar/python-dotenv#561
• Bump actions/checkout from 5 to 6 in the github-actions group by @​dependabot[bot] in theskumar/python-dotenv#593
• Add Windows testing to CI by @​bbc2 in theskumar/python-dotenv#604
• Improve workflow efficiency with best practices by @​theskumar in theskumar/python-dotenv#609
• Remove the use of sh in tests by @​bbc2 in theskumar/python-dotenv#612

New Contributors

• @​JYOuyang made their first contribution in theskumar/python-dotenv#590
• @​burnout-projects made their first contribution in theskumar/python-dotenv#561
• @​cpackham-atlnz made their first contribution in theskumar/python-dotenv#597

Full Changelog: theskumar/python-dotenv@v1.2.1...v1.2.2

Changelog

Sourced from python-dotenv's changelog.

[1.2.2] - 2026-03-01

Added

• Support for Python 3.14, including the free-threaded (3.14t) build. (#588)

Changed

• The dotenv run command now forwards flags directly to the specified command by [@​bbc2] in #607
• Improved documentation clarity regarding override behavior and the reference page.
• Updated PyPy support to version 3.11.
• Documentation for FIFO file support.
• Dropped Support for Python 3.9.

Fixed

• Improved set_key and unset_key behavior when interacting with symlinks by [@​bbc2] in [790c5c0]
• Corrected the license specifier and added missing Python 3.14 classifiers in package metadata by [@​JYOuyang] in #590

Breaking Changes

• dotenv.set_key and dotenv.unset_key used to follow symlinks in some situations. This is no longer the case. For that behavior to be restored in all cases, follow_symlinks=True should be used.

• In the CLI, set and unset used to follow symlinks in some situations. This is no longer the case.

• dotenv.set_key, dotenv.unset_key and the CLI commands set and unset used to reset the file mode of the modified .env file to 0o600 in some situations. This is no longer the case: The original mode of the file is now preserved. Is the file needed to be created or wasn't a regular file, mode 0o600 is used.

Commits

• 36004e0 Bump version: 1.2.1 → 1.2.2
• eb20252 docs: update changelog for v1.2.2
• 790c5c0 Merge commit from fork
• 43340da Remove the use of sh in tests (#612)
• 09d7cee docs: clarify override behavior and document FIFO support (#610)
• c8de288 ci: improve workflow efficiency with best practices (#609)
• 7bd9e3d Add Windows testing to CI (#604)
• 1baaf04 Drop Python 3.9 support and update to PyPy 3.11 (#608)
• 4a22cf8 ci: enable testing on Python 3.14t (free-threaded) (#588)
• e2e8e77 Fix license specifier (#597)
• Additional commits viewable in compare view

Updates google-genai from 1.56.0 to 1.65.0

Release notes

Sourced from google-genai's releases.

v1.65.0

1.65.0 (2026-02-26)

Features

• Add gemini-3.1-pro-preview to list of models in Interactions (fe86870)
• Add Image Grounding support to GoogleSearch tool (0035182)
• Enable server side MCP and disable all other AFC when server side MCP is configured. (4dd7b16)
• Support more image sizes and resolutions (8b2a4e0)

Bug Fixes

• Change interactions media mime type to enum (breaking change for experimental feature) (e0f3378)
• Handle non-list response_stream in HttpResponse.json property (006042d)
• Handle non-list response_stream in HttpResponse.json property (#1903) (61aec34)
• Make aiohttp an optional dependency, bump aiohttp version upperbound, and ensure HttpOptions.async_client_args propagates to custom aiohttp.ClientSession request args for proxy etc. (b28d144), closes #2090 #2051 #1950

Documentation

• Regenerate docs for 1.64.0 (a023141)
• Update README and codegen_instructions for structured outputs (4d5a978)

v1.64.0

1.64.0 (2026-02-18)

Features

• Add UnifiedMetric support to Vertex Tuning evaluation config (9a9908a)
• Support multimodal embedding for Gemini Embedding 2.0 and support MaaS models in Models.embed_content() (Vertex AI API) (af40cc6)

v1.63.0

1.63.0 (2026-02-11)

Features

• Add INCOMPLETE status to Interaction. (1a84605)
• Support encryption_spec in tuning job creation configuration for GenAI SDK (057d6f0)

Bug Fixes

• Base_url and global location parsing (2c40555)
• Remove build warning due to extra comma: assertion on a tuple is always true (1cc2c2d)
• Remove debug print statement. (60c0a2f)
• Remove unused import of websockets (3b82b5f)

... (truncated)

Changelog

Sourced from google-genai's changelog.

1.65.0 (2026-02-26)

Features

• Add gemini-3.1-pro-preview to list of models in Interactions (fe86870)
• Add Image Grounding support to GoogleSearch tool (0035182)
• Enable server side MCP and disable all other AFC when server side MCP is configured. (4dd7b16)
• Support more image sizes and resolutions (8b2a4e0)

Bug Fixes

• Change interactions media mime type to enum (breaking change for experimental feature) (e0f3378)
• Handle non-list response_stream in HttpResponse.json property (006042d)
• Handle non-list response_stream in HttpResponse.json property (#1903) (61aec34)
• Make aiohttp an optional dependency, bump aiohttp version upperbound, and ensure HttpOptions.async_client_args propagates to custom aiohttp.ClientSession request args for proxy etc. (b28d144), closes #2090 #2051 #1950

Documentation

• Regenerate docs for 1.64.0 (a023141)
• Update README and codegen_instructions for structured outputs (4d5a978)

1.64.0 (2026-02-18)

Features

• Add UnifiedMetric support to Vertex Tuning evaluation config (9a9908a)
• Support multimodal embedding for Gemini Embedding 2.0 and support MaaS models in Models.embed_content() (Vertex AI API) (af40cc6)

1.63.0 (2026-02-11)

Features

• Add INCOMPLETE status to Interaction. (1a84605)
• Support encryption_spec in tuning job creation configuration for GenAI SDK (057d6f0)

Bug Fixes

• Base_url and global location parsing (2c40555)
• Remove build warning due to extra comma: assertion on a tuple is always true (1cc2c2d)
• Remove debug print statement. (60c0a2f)
• Remove unused import of websockets (3b82b5f)

Documentation

... (truncated)

Commits

• b2be501 chore(main): release 1.65.0 (#2075)
• 7028a9c chore: update InteractionCompleteEvent comment
• 0035182 feat: Add Image Grounding support to GoogleSearch tool
• 8b2a4e0 feat: Support more image sizes and resolutions
• b28d144 fix: Make aiohttp an optional dependency, bump aiohttp version upperbound, an...
• c04c489 chore: Improve error message for missing API key.
• af94e53 chore: Update comments
• 006042d Copybara import of the project:
• ecfa90c chore: internal change
• 61aec34 fix: handle non-list response_stream in HttpResponse.json property (#1903)
• Additional commits viewable in compare view

Updates google-adk from 1.21.0 to 1.26.0

Release notes

Sourced from google-adk's releases.

v1.26.0

1.26.0 (2026-02-26)

Features

• [Core]

  • Add intra-invocation compaction and token compaction pre-request (485fcb8)
  • Use --memory_service_uri in ADK CLI run command (a7b5097)

• [Models]

  • Add /chat/completions integration to ApigeeLlm (9c4c445)
  • Add /chat/completions streaming support to Apigee LLM (121d277)
  • Expand LiteLlm supported models and add registry tests (d5332f4)

• [Tools]

  • Add load_skill_from_dir() method (9f7d5b3)
  • Agent Skills spec compliance — validation, aliases, scripts, and auto-injection (223d9a7)
  • BigQuery ADK support for search catalog tool (bef3f11)
  • Make skill instruction optimizable and can adapt to user tasks (21be6ad)
  • Pass trace context in MCP tool call's _meta field with OpenTelemetry propagator (bcbfeba)

• [Evals]

  • Introduce User Personas to the ADK evaluation framework (6a808c6)

• [Services]

  • Add generate/create modes for Vertex AI Memory Bank writes (811e50a)
  • Add support for memory consolidation via Vertex AI Memory Bank (4a88804)

• [A2A]

  • Add interceptor framework to A2aAgentExecutor (87fcd77)

• [Auth]

  • Add native support for id_token in OAuth2 credentials (33f7d11)
  • Support ID token exchange in ServiceAccountCredentialExchanger (7be90db), closes #4458

• [Integrations]

  • Agent Registry in ADK (abaa929)
  • Add schema auto-upgrade, tool provenance, HITL tracing, and span hierarchy fix to BigQuery Agent Analytics plugin (4260ef0)
  • Change default BigQuery table ID and update docstring (7557a92)
  • Update Agent Registry to create AgentCard from info in get agents endpoint (c33d614)

• [Web]

  • Enable dependency injection for agent loader in FastAPI app gen (34da2d5)

Bug Fixes

• Add OpenAI strict JSON schema enforcement in LiteLLM (2dbd1f2), closes #4573
• Add push notification config store to agent_to_a2a (4ca904f), closes #4126

... (truncated)

Changelog

Sourced from google-adk's changelog.

1.26.0 (2026-02-26)

Features

• [Core]

  • Add intra-invocation compaction and token compaction pre-request (485fcb8)
  • Use --memory_service_uri in ADK CLI run command (a7b5097)

• [Models]

  • Add /chat/completions integration to ApigeeLlm (9c4c445)
  • Add /chat/completions streaming support to Apigee LLM (121d277)
  • Expand LiteLlm supported models and add registry tests (d5332f4)

• [Tools]

  • Add load_skill_from_dir() method (9f7d5b3)
  • Agent Skills spec compliance — validation, aliases, scripts, and auto-injection (223d9a7)
  • BigQuery ADK support for search catalog tool (bef3f11)
  • Make skill instruction optimizable and can adapt to user tasks (21be6ad)
  • Pass trace context in MCP tool call's _meta field with OpenTelemetry propagator (bcbfeba)

• [Evals]

  • Introduce User Personas to the ADK evaluation framework (6a808c6)

• [Services]

  • Add generate/create modes for Vertex AI Memory Bank writes (811e50a)
  • Add support for memory consolidation via Vertex AI Memory Bank (4a88804)

• [A2A]

  • Add interceptor framework to A2aAgentExecutor (87fcd77)

• [Auth]

  • Add native support for id_token in OAuth2 credentials (33f7d11)
  • Support ID token exchange in ServiceAccountCredentialExchanger (7be90db), closes #4458

• [Integrations]

  • Agent Registry in ADK (abaa929)
  • Add schema auto-upgrade, tool provenance, HITL tracing, and span hierarchy fix to BigQuery Agent Analytics plugin (4260ef0)
  • Change default BigQuery table ID and update docstring (7557a92)
  • Update Agent Registry to create AgentCard from info in get agents endpoint (c33d614)

• [Web]

  • Enable dependency injection for agent loader in FastAPI app gen (34da2d5)

Bug Fixes

• Add OpenAI strict JSON schema enforcement in LiteLLM (2dbd1f2), closes #4573
• Add push notification config store to agent_to_a2a (4ca904f), closes #4126
• Add support for injecting a custom google.genai.Client into Gemini models (48105b4), closes #2560

... (truncated)

Commits

• 427a983 chore: update last-release-sha for next release
• 934289a chore(release/candidate): release 1.26.0 (#4610)
• ab32f33 fix: Validate session before streaming instead of eagerly advancing the runne...
• 40ec134 fix: Re-export DEFAULT_SKILL_SYSTEM_INSTRUCTION to skills and skill/prompt.py...
• 8f54281 fix: Update sample skills agent to use weather-skill instead of weather_skill
• 121d277 feat: Add /chat/completions streaming support to Apigee LLM
• 48105b4 fix: Add support for injecting a custom google.genai.Client into Gemini models
• ee8d956 fix: Update agent_engine_sandbox_code_executor in ADK
• 7be90db feat: Support ID token exchange in ServiceAccountCredentialExchanger
• c615757 fix: Add support for injecting a custom google.genai.Client into Gemini models
• Additional commits viewable in compare view

Updates openinference-instrumentation from 0.1.42 to 0.1.46

Release notes

Sourced from openinference-instrumentation's releases.

python-openinference-instrumentation: v0.1.46

0.1.46 (2026-03-04)

Features

• claude-agent-sdk: Add support for Claude Agent SDK (#2796) (6f627e7)

python-openinference-instrumentation: v0.1.45

0.1.45 (2026-02-24)

Documentation

• python spec: add instructions for working on python instrumentation packages (#2757) (b8bd7ca)

python-openinference-instrumentation: v0.1.44

0.1.44 (2026-02-01)

Bug Fixes

• instrumentation: update openinference span kind helper to include prompt (#2672) (6603d44)

python-openinference-instrumentation: v0.1.43

0.1.43 (2026-01-26)

Features

• add Open Agent Spec Instrumentor (#2560) (48a8722)

Commits

• c94ab4d chore: release main (#2835)
• 6f627e7 feat(claude-agent-sdk): Add support for Claude Agent SDK (#2796)
• 8a8094e chore: release main (#2834)
• 0b70006 feat(semconv): add TOOL_ID (tool.id) to Python and JS semconv (#2831)
• bfbcdf6 chore: add Makefile and pre-commit hooks for local dev tooling (#2833)
• 8ba0e19 chore(agno, beeai): fix brotli-compressed VCR cassettes and stale type ignore...
• 0d71dd2 fix: address high severity security vulnerabilities (#2811)
• e8b9ceb chore: release main (#2829)
• fb97839 fix(google-adk): Suppress duplicate generate_content spans from native ADK tr...
• 863d39e chore: release main (#2823)
• Additional commits viewable in compare view

Updates arize from 7.51.2 to 8.4.0

Changelog

Sourced from arize's changelog.

8.4.0 (2026-02-20)

🎁 New Features

• Annotation configs (#63369) (d6a6b00)

8.3.0 (2026-02-18)

🎁 New Features

• deprecation: add deprecation utilities and warnings to Arize SDK (#62599) (7784067)
• spans: add prerelease list endpoint with generated API client support (#63340) (15319d0)

8.2.1 (2026-02-13)

🐛 Bug Fixes

• dict-to-model conversions using from_dict and remove redundant id indexing (#62818) (14779c0)

8.2.0 (2026-02-11)

🎁 New Features

• Support text annotations when updating annotations (#62764) (545eb42)

8.1.0 (2026-02-09)

🎁 New Features

• responses: support one-level expansion in to_df methods (#62391) (899edeb)
• regions: add Region.list_regions class method

🐛 Bug Fixes

• config: add max_val constraint to stream_max_workers

8.0.2 (2026-02-04)

📚 Documentation

• add optional extras to RTD build and local install (#62097) (2549d6c)

8.0.1 (2026-02-04)

... (truncated)

Commits

• See full diff in compare view

Updates arize-phoenix-evals from 2.7.1 to 2.11.0

Release notes

Sourced from arize-phoenix-evals's releases.

arize-phoenix-evals: v2.11.0

2.11.0 (2026-02-27)

Features

• evals: add conciseness classification evaluator (#11437) (d43c4ee)
• evals: add refusal evaluator (#11718) (45a88fc)
• evals: Add utility to convert Phoenix prompts to evals templates (#11696) (ded46ba)

Bug Fixes

• evals: handle litellm 1.81.16 no longer auto-converting usage=None to Usage(0,0,0) (#11754) (ad516c8)
• update slack invitation link (#11612) (316833e)

---

This PR was generated with Release Please. See documentation.

arize-phoenix-evals: v2.10.0

2.10.0 (2026-02-13)

Features

• add tool response handling evaluator template (#11276) (0738cb9)
• dataset evaluators (1274b03)
• dataset evaluators (5f47820)
• dataset evaluators (cf0e09a)
• enable full mustache prompt templates in the server (#11229) (68ba0ed)
• filter built-in classification evaluators by label (#11416) (aa95a3f)

Bug Fixes

• templates: simplify template formatters (#11410) (1f6df01)

Miscellaneous Chores

• release 2.10.0 (4561612)

---

This PR was generated with Release Please. See documentation.

arize-phoenix-evals: v2.9.0

... (truncated)

Changelog

Sourced from arize-phoenix-evals's changelog.

12.11.0 (2025-11-07)

Features

• user display timezone preference (#10133) (e4d0174)

Bug Fixes

• bump minimum version of client (#10165) (396cac1)
• improve identifier form validation (#10149) (d4a4111)
• make lastN time ranges work for metrics page (#10154) (72e5068)

12.10.0 (2025-11-05)

Features

• add es2022 as new target (#10143) (cccc40a)
• Add extra body param (#10131) (41e1746)
• add system theme (#10030) (90f133a)
• add valueFrom option to auth.secret (#9932) (0c6a3e8)
• added additionalEnv support (#10022) (b2aadb3)
• auth: hide prominent actions for viewers. (#10124) (bd24cba)
• classnames migration to vendored approach (#10098) (37e106b)
• helm: Allow fullname override, enhance helm tests (#10106) (1788b84)
• metadata for prompts (#10097) (0c92232)
• OIDC role mapping (#9982) (29615ef)
• prometheus metrics for trace retention sweeper (#10130) (3c9d92b)
• resume experiment and evaluation (#9994) (557865c)
• ui: playground dataset label (#9902) (12d6855)

Bug Fixes

• helm: in-memory deployment from conflicting values (#10118) (8e16a62)
• playground: remove useMemo (#10110) (bcbe5bd)
• render tool messages with undefined outputs (#10116) (c7d76e1)

12.9.0 (2025-10-29)

Features

• Create more menu abstractions (#9877) (0c0ccde)
• display metadata for experiment run annotations (#9904) (0e9cba3)
• Enable AWS IAM auth for DB configuration (#9936) (465015d)
• experiments: move reference output to bottom pane of compare slideover (#10027) (14dc381)
• Merge dataset label application with new label creation (#10014) (c6cb7da)

... (truncated)

Commits

• f284fe6 chore(main): release arize-phoenix-evals 2.11.0 (#11597)
• 575b95a ci: remove sparse checkout (#11762)
• 2b3c50d ci: remove sparse checkout (#11761)
• 2a6c74a refactor(ci): split release into release-please + publish workflow (#11759)
• ad516c8 fix(evals): handle litellm 1.81.16 no longer auto-converting usage=None to Us...
• f9c57e3 chore: remove AGENTS.md contents (#11748)
• 192b69a chore(main): release arize-phoenix 13.4.0 (#11608)
• 05d3ea4 fix(security): update dependencies in internal_docs and scripts direc… (#11749)
• 36c71bb docs(tutorials): add Colab badge to all tutorial notebooks (#11752)
• cd425a5 Update Agent Spec logo to greyscale SVG (#11751)
• Additional commits viewable in compare view

Updates ruff from 0.14.10 to 0.15.4

Release notes

Sourced from ruff's releases.

0.15.4

Release Notes

Released on 2026-02-26.

This is a follow-up release to 0.15.3 that resolves a panic when the new rule PLR1712 was enabled with any rule that analyzes definitions, such as many of the ANN or D rules.

Bug fixes

• Fix panic on access to definitions after analyzing definitions (#23588)
• [pyflakes] Suppress false positive in F821 for names used before del in stub files (#23550)

Documentation

• Clarify first-party import detection in Ruff (#23591)
• Fix incorrect import-heading example (#23568)

Contributors

• @​stakeswky
• @​ntBre
• @​thejcannon
• @​GeObts

Install ruff 0.15.4

Install prebuilt binaries via shell script

curl --proto '=https' --tlsv1.2 -LsSf https://github.com/astral-sh/ruff/releases/download/0.15.4/ruff-installer.sh | sh

Install prebuilt binaries via powershell script

powershell -ExecutionPolicy Bypass -c "irm https://github.com/astral-sh/ruff/releases/download/0.15.4/ruff-installer.ps1 | iex"

Download ruff 0.15.4

File	Platform	Checksum
ruff-aarch64-apple-darwin.tar.gz	Apple Silicon macOS	checksum
ruff-x86_64-apple-darwin.tar.gz	Intel macOS	checksum
ruff-aarch64-pc-windows-msvc.zip	ARM64 Windows	checksum
ruff-i686-pc-windows-msvc.zip	x86 Windows	checksum
ruff-x86_64-pc-windows-msvc.zip	x64 Windows	checksum
ruff-aarch64-unknown-linux-gnu.tar.gz	ARM64 Linux	checksum
ruff-i686-unknown-linux-gnu.tar.gz	x86 Linux	checksum
ruff-powerpc64-unknown-linux-gnu.tar.gz	PPC64 Linux	checksum

... (truncated)

Changelog

Sourced from ruff's changelog.

0.15.4

Released on 2026-02-26.

This is a follow-up release to 0.15.3 that resolves a panic when the new rule PLR1712 was enabled with any rule that analyzes definitions, such as many of the ANN or D rules.

Bug fixes

• Fix panic on access to definitions after analyzing definitions (#23588)
• [pyflakes] Suppress false positive in F821 for names used before del in stub files (#23550)

Documentation

• Clarify first-party import detection in Ruff (#23591)
• Fix incorrect import-heading example (#23568)

Contributors

• @​stakeswky
• @​ntBre
• @​thejcannon
• @​GeObts

0.15.3

Released on 2026-02-26.

Preview features

• Drop explicit support for .qmd file extension (#23572)

  This can now be enabled instead by setting the extension option:

  # ruff.toml
  extension = { qmd = "markdown" }
  pyproject.toml
  [tool.ruff]
  extension = { qmd = "markdown" }

• Include configured extensions in file discovery (#23400)

• [flake8-bandit] Allow suspicious imports in TYPE_CHECKING blocks (S401-S415) (#23441)

• [flake8-bugbear] Allow B901 in pytest hook wrappers (#21931)

• [flake8-import-conventions] Add missing conventions from upstream (ICN001, ICN002) (#21373)

... (truncated)

Commits

• f14edd8 Bump 0.15.4 (#23595)
• fd09d37 Fix panic on access to definitions after analyzing definitions (#23588)
• 81d655f [pyflakes] suppress false positive in ...

  Description has been truncated

[dependabot]

This pull request was built based on a group rule. Closing it will not ignore any of these versions in future pull requests.

To ignore these dependencies, configure ignore rules in dependabot.yml