Bump req_llm from 1.5.1 to 1.9.0

[dependabot]

Bumps req_llm from 1.5.1 to 1.9.0.

Release notes

Sourced from req_llm's releases.

Release v1.9.0

See https://github.com/agentjido/req_llm/blob/HEAD/CHANGELOG.md for details.

Release v1.8.0

See https://github.com/agentjido/req_llm/blob/HEAD/CHANGELOG.md for details.

Release v1.7.1

See https://github.com/agentjido/req_llm/blob/HEAD/CHANGELOG.md for details.

Release v1.7.0

See https://github.com/agentjido/req_llm/blob/HEAD/CHANGELOG.md for details.

Release v1.6.0

See https://github.com/agentjido/req_llm/blob/HEAD/CHANGELOG.md for details.

Changelog

Sourced from req_llm's changelog.

v1.9.0 (2026-03-27)

Features:

• add mistral provider (#554) by mikehostetler

• add thinkingLevel support to Google provider (#565) by Tom Taylor

• add thinkingLevel support to Google provider by Tom Taylor

• add finch_request_adapter config to modify streaming requests (#566) by johantell

• add FinchRequestAdapter for config-level streaming request transforms by johantell

• add OpenAI websocket streaming and realtime support (#559) by mikehostetler

• allow unknown models with warnings instead of errors (#561) by dl-alexandre

• add reranking API with batch processing (#553) by mikehostetler

• add OpenTelemetry bridge and telemetry stubs (#548) by mikehostetler

• add video URL message support (#549) by mikehostetler

• support Anthropic native tool options (#547) by mikehostetler

• support Anthropic native tool options by mikehostetler

• add Google Imagen image generation support (#550) by mikehostetler

• generation: repair lightly malformed structured JSON (#543) by mikehostetler

• add available model discovery (#544) by mikehostetler

• add application-layer cache hooks (#541) by mikehostetler

• generation: add application cache hooks by mikehostetler

• rate limit retry (429) and custom headers for streaming (#537) by dl-alexandre

• pass custom headers to Finch streaming requests by dl-alexandre

• Add Deepseek support (#538) by Luis Ezcurdia

Bug Fixes:

• openai: retrieve structured output from tool call (#572) by Robin Verton

... (truncated)

Commits

• d9bc3b5 chore: release version v1.9.0
• 3a301ef fix(openai): retrieve structured output from tool call (#572)
• d6a65c4 chore: align quality gate with credo strict (#571)
• d6295b4 test: raise core API coverage (#568)
• 213e696 test: expand streaming core coverage (#569)
• 15156c3 test: expand openai coverage helpers (#570)
• a2fb317 docs: clarify structured tool result content (#567)
• 6ba1b71 feat: add mistral provider (#554)
• 28a2c74 feat: add thinkingLevel support to Google provider (#565)
• e6fc78e test: isolate finch request adapter tests from env api keys
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)