[Bug]: Warning: The `api_key` argument of `chat_google_gemini()` is deprecated as of ellmer

[bulbusheadgang]

Confirm setup

• I have installed the development version of {gptstudio} (pak::pak("MichelNivard/gptstudio")) and tested if the problem remains.
• I have installed the {reprex} and {sessioninfo} packages to be able to run this issue's code snippet pak::pak(c("reprex", "sessioninfo")).

What happened?

I use Posit Cloud

Before this bug I was experiencing what was in this bug report: #258
After troubleshooting that bug I am now experiencing this one: after I try to send a query to gemini the "Viewer: in Posit Cloud goes blank and I get "Warning: The api_key argument of chat_google_gemini() is deprecated as of ellmer"

Relevant log output

Loading required package: shiny

Listening on http://127.0.0.1:7615
ℹ Fetching models for google service...
✔ Got models!
Warning: The `api_key` argument of `chat_google_gemini()` is deprecated as of ellmer
0.4.0.
ℹ Please use the `credentials` argument instead.
ℹ The deprecated feature was likely used in the gptstudio package.
  Please report the issue at
  <https://github.com/MichelNivard/gptstudio/issues>.
Warning in process_chat$invoke(prompt = input$chat_input, service = settings$service,  :
  ERROR: An error occurred when invoking the ExtendedTask.
Caused by error in `purrr::map()`:
ℹ In index: 1.
Caused by error in `ellmer::Turn()`:
! unused argument (role = .x$role)
Warning: Error in purrr::map: ℹ In index: 1.
Caused by error in `ellmer::Turn()`:
! unused argument (role = .x$role)
  167: base$onError
  166: base$onError
  165: base$onError
  164: base$onError
  163: base$onError
  162: base$onError
  161: base$onError
  160: base$onError
  159: base$onError
  158: domain$onError
  157: promiseDomain$onError
  156: <Anonymous>
  155: stop
  154: signalConditions
  153: value.Future
  142: check
  141: action
  134: promise
  133: as.promise.Future
  131: private$doResolve
  124: resolve
  123: work_fn
  122: private$do_work
  121: private$attempt_work
  120: queue$schedule_work
  119: action
  112: promise
  111: promises::future_promise
  110: <Anonymous>
   86: private$do_invoke
   85: process_chat$invoke
   84: observe
   83: <observer:observeEvent(input$chat)>
    4: shiny::runApp
    3: eval
    2: eval
    1: .rs.sourceWithProgress


Execution halted

Session info

r
gptstudio::gptstudio_sitrep()
#> 
#> ── Configuration for gptstudio ─────────────────────────────────────────────────
#> Using user configuration file at
#> '/cloud/home/r3312025/.config/R/gptstudio/config.yml'
#> 
#> 
#> ── Current Settings ──
#> 
#> 
#> 
#> - Model: gemini-2.5-pro
#> 
#> - Task: coding
#> 
#> - Language: en
#> 
#> - Service: google
#> 
#> - Custom prompt:
#> 
#> - Stream: TRUE
#> 
#> - Code style: tidyverse
#> 
#> - Skill: genius
#> 
#> 
#> 
#> ── Checking API connections ──
#> 
#> 
#> 
#> ── Checking OpenAI API connection 
#> 
#> ✖ API key is not set or invalid for openai service.
#> 
#> 
#> 
#> ── Checking HuggingFace API connection 
#> 
#> ✖ API key is not set or invalid for huggingface service.
#> 
#> 
#> 
#> ── Checking Anthropic API connection 
#> 
#> ✖ API key is not set or invalid for anthropic service.
#> 
#> 
#> 
#> ── Checking Google AI Studio API connection 
#> 
#> Using model = "gemini-2.5-flash".
#> Warning: The `api_key` argument of `chat_google_gemini()` is deprecated as of ellmer
#> 0.4.0.
#> ℹ Please use the `credentials` argument instead.
#> ℹ The deprecated feature was likely used in the gptstudio package.
#>   Please report the issue at
#>   <https://github.com/MichelNivard/gptstudio/issues>.
#> This warning is displayed once every 8 hours.
#> Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
#> generated.
#> ✖ Failed to connect to the google API service.
#> 
#> ── Checking Azure OpenAI API connection 
#> ✖ API key is not set or invalid for azure_openai service.
#> 
#> ── Checking Perplexity API connection 
#> ✖ API key is not set or invalid for perplexity service.
#> 
#> ── Checking Cohere API connection 
#> ✖ API key is not set or invalid for cohere service.
#> 
#> ── Check Ollama for Local API connection 
#> ✖ Couldn't connect to Ollama in <http://localhost:11434>. Is it running there?
#> 
#> ── Getting help ──
#> 
#> See the gptstudio homepage (<https://michelnivard.github.io/gptstudio/>) for
#> getting started guides and package documentation. File an issue or contribute
#> to the package at the GitHub repo
#> (<https://github.com/MichelNivard/gptstudio>).── End of gptstudio configuration ──────────────────────────────────────────────

Code of Conduct

• I agree to follow this project's Code of Conduct

[calderonsamuel]

Thanks for reporting! I'll take a look soon, patience please 🙏 we also accept PRs!