chore(deps): bump github.com/agentplexus/omnillm from 0.9.0 to 0.11.0

[dependabot]

Bumps github.com/agentplexus/omnillm from 0.9.0 to 0.11.0.

Release notes

Sourced from github.com/agentplexus/omnillm's releases.

v0.11.0

Release Notes: https://github.com/agentplexus/omnillm/blob/HEAD/RELEASE_NOTES_v0.11.0.md

Full Changelog: agentplexus/omnillm@v0.10.0...v0.11.0

v0.10.0

Release Notes https://github.com/agentplexus/omnillm/blob/HEAD/RELEASE_NOTES_v0.10.0.md

Full Changelog: agentplexus/omnillm@v0.9.0...v0.10.0

Changelog

Sourced from github.com/agentplexus/omnillm's changelog.

[v0.11.0] - 2026-01-10

Highlights

• Reliability: Automatic failover with fallback providers and circuit breaker pattern ensure your app stays up even when providers fail
• Cost Optimization: Response caching reduces API costs by returning cached responses for identical requests
• Error Prevention: Pre-flight token estimation validates requests before sending, avoiding context window limit errors

Added

• Fallback Providers: Automatic failover to backup providers when primary fails (retryable errors only) (6a9f4c9)
• Circuit Breaker: Prevents cascading failures by temporarily skipping unhealthy providers (f5bd1e9)
• Token Estimation: Pre-flight token counting to validate requests before sending to API (60573ba)
• Response Caching: Cache identical requests using KVS backend with configurable TTL (1dc3c79)
• FallbackProviders and CircuitBreakerConfig fields in ClientConfig (582c556)
• TokenEstimator interface with built-in context windows for 40+ models (60573ba)
• CacheManager with SHA-256 based cache key generation (1dc3c79)
• ErrorCategory type with ClassifyError() and IsRetryableError() for error classification (9939ee9)
• FallbackError type with detailed attempt tracking (6a9f4c9)
• TokenLimitError for pre-flight validation failures (60573ba)
• TopK sampling parameter in ChatCompletionRequest (Anthropic, Gemini, Ollama) (e7dc833)
• Seed parameter for reproducible outputs (OpenAI, X.AI, Ollama) (e7dc833)
• N parameter for multiple completions (OpenAI) (e7dc833)
• ResponseFormat type and field for JSON mode responses (OpenAI, Gemini) (e7dc833)
• Logprobs and TopLogprobs parameters for log probability output (OpenAI) (e7dc833)
• ErrNoProviders error for when ClientConfig.Providers is empty (0d06bd1)

Changed

• BREAKING: ClientConfig refactored to use unified Providers []ProviderConfig slice (index 0 = primary, 1+ = fallbacks) (0d06bd1)
• BREAKING: Removed redundant Provider, APIKey, BaseURL, Region, Timeout, HTTPClient, CustomProvider, Extra, FallbackProviders fields from ClientConfig (0d06bd1)
• ProviderConfig now supports CustomProvider field for 3rd party provider injection (0d06bd1)
• Provider constructors refactored to accept ProviderConfig instead of ClientConfig (0d06bd1)
• CreateChatCompletion now supports optional token validation and response caching (582c556)
• All provider adapters updated to pass through newly supported parameters (e7dc833)

Documentation

• README.md updated with Fallback Providers, Circuit Breaker, Token Estimation, and Response Caching documentation (3e22925)
• RELEASE_NOTES_v0.11.0.md added with comprehensive release notes (3e22925)

Tests

• Circuit breaker tests added (circuitbreaker_test.go) (f5bd1e9)
• Fallback provider tests added (fallback_test.go) (6a9f4c9)
• Token estimation tests added (tokens_test.go) (60573ba)
• Response caching tests added (cache_test.go) (1dc3c79)

[v0.10.0] - 2026-01-04

... (truncated)

Commits

• 8631e81 chore(CHANGELOG): add commit hashes for all entries
• e0e19cd chore(CHANGELOG): add v prefix to version tags
• e369c6c docs(CHANGELOG): regenerate with updated sclog tool
• 6ad6782 docs: update documentation for unified Providers API
• 14296a3 refactor(examples): update examples for unified Providers API
• 93370c0 test: update tests for unified Providers API
• 0d06bd1 refactor(api)!: unify provider configuration with Providers slice
• 17b405a docs: update documentation for v0.11.0 release
• 582c556 feat(client): integrate fallback, tokens, and caching into ChatClient
• 1dc3c79 feat: add response caching with KVS backend
• 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 merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @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)