Skip to content

Env var to set Ollama request timeout #3516

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
michaelneale merged 1 commit into from
Jul 22, 2025
Merged

Env var to set Ollama request timeout #3516

michaelneale merged 1 commit into from
Jul 22, 2025

Conversation

@bickelj
Copy link
Contributor

@bickelj bickelj commented Jul 18, 2025

Without this change, even if one recompiles ollama to extend timeouts there, goose times out HTTP requests to ollama at ten minutes.

Those of us who choose to run LLMs on CPUs, despite the slowness, profit from LLMs doing asynchronous work. This change allows users to increase the timeout goose sets on HTTP requests to ollama.

@bickelj bickelj force-pushed the ollama-timeout-env-var branch from aa80360 to 8e26d0d Compare July 18, 2025 17:32
bickelj
bickelj commented Jul 18, 2025
View reviewed changes
@michaelneale
Copy link
Collaborator

michaelneale commented Jul 21, 2025

@bickelj thanks for this - can you run cargo fmt just to tidy it up again, but this LGTM - yeah it can be slow and sometimes that is ok!

@michaelneale michaelneale self-assigned this Jul 21, 2025
@taniandjerry
Copy link
Contributor

taniandjerry commented Jul 21, 2025

@bickelj thanks for this - can you run cargo fmt just to tidy it up again, but this LGTM - yeah it can be slow and sometimes that is ok!

Let us know when you've been able to run this, @bickelj !

@bickelj
Env var to set Ollama request timeout
aff8645 
Without this change, even if one recompiles `ollama` to extend
timeouts there, `goose` times out HTTP requests to `ollama` at ten
minutes.

Those of us who choose to run LLMs on CPUs, despite the slowness,
profit from LLMs doing asynchronous work. This change allows users to
increase the timeout `goose` sets on HTTP requests to `ollama`.

Signed-off-by: Jesse Bickel <[email protected]>
@bickelj bickelj force-pushed the ollama-timeout-env-var branch from 8e26d0d to aff8645 Compare July 21, 2025 14:28
@bickelj
Copy link
Contributor Author

bickelj commented Jul 21, 2025

@michaelneale @taniashiba After freeing some space (apparently I need 55GiB free to run cargo build), I was able to run cargo check && cargo fmt && cargo clippy. I admit not all tests passed locally. I hope it is simply because I didn't have llama3.2 locally. One of the reasons I run ollama locally is to avoid proprietary models such as llama.

@bickelj
Copy link
Contributor Author

bickelj commented Jul 21, 2025

By the way, thank you for goose and for your consideration of this PR!

@bickelj bickelj requested a review from michaelneale July 21, 2025 19:41
@michaelneale
Copy link
Collaborator

michaelneale commented Jul 21, 2025

@bickelj no worries - will run tests here (I rarely run them all locally), taking a look now

@michaelneale michaelneale merged commit 5f3c7d3 into block:main Jul 22, 2025
7 checks passed
lifeizhou-ap added a commit that referenced this pull request Jul 22, 2025
@lifeizhou-ap
Merge branch 'main' into lifei/fix-error-message-when-ctrlc
6f4bf54 
* main: (32 commits)
  fix: use sequential when sub recipe task is 1. (#3573)
  fix: track message id to keep like with like (#3572)
  Replace mcp_core::prompt with rmcp::model types (#3561)
  feat (ui): close recipe modals with esc key (#3568)
  feat: recipes can retry with success criteria (#3474)
  Env var to set Ollama request timeout (#3516)
  Updating docs to match new UI (#3552)
  Improve Claude Code provider error message for missing CLI (#3363)
  feat: Work around Gemini API tool call quirks (#3328)
  feat(ui): Source CashSans-Bold and improve overall text rendering (#3091)
  refactor: Use openapi for recipe endpoint types and in frontend (#3548)
  Fix Google Analytics error for local dev (#3544)
  Extension Library Improvements (#3541)
  fix(ui): enable selection of zero-config providers in desktop GUI (#3378)
  refactor: Renames recipe route to recipes to be consistent (#3540)
  Blog: Orchestrating 6 Subagents to Build a Collaborative API Playground (#3528)
  Catch json errors a little better (#3437)
  Rust debug (#3510)
  refactor: Centralise deeplink encode and decode into server (#3489)
  feat: deprecate jetbrains extension in favor of public one (#2589)
  ...
michaelneale added a commit that referenced this pull request Jul 22, 2025
@michaelneale
Merge branch 'main' into micn/install-with-openrouter
be9da5c 
* main:
  fix: use sequential when sub recipe task is 1. (#3573)
  fix: track message id to keep like with like (#3572)
  Replace mcp_core::prompt with rmcp::model types (#3561)
  feat (ui): close recipe modals with esc key (#3568)
  feat: recipes can retry with success criteria (#3474)
  Env var to set Ollama request timeout (#3516)
  Updating docs to match new UI (#3552)
  Improve Claude Code provider error message for missing CLI (#3363)
  feat: Work around Gemini API tool call quirks (#3328)
  feat(ui): Source CashSans-Bold and improve overall text rendering (#3091)
  refactor: Use openapi for recipe endpoint types and in frontend (#3548)
  Fix Google Analytics error for local dev (#3544)
zanesq added a commit that referenced this pull request Jul 22, 2025
@zanesq
Merge branch 'main' of github.com:block/goose into zane/recipe-parame…
1a0cd8c 
…ters

* 'main' of github.com:block/goose:
  Add recipe install warning (#3537)
  Replace mcp_core::resource::* with rmcp types (#3563)
  Add YouTube video embed to using-goosehints.md (#3560)
  fix: ensure retry-config and success-criteria are populated in openapi spec (#3575)
  fix: use sequential when sub recipe task is 1. (#3573)
  fix: track message id to keep like with like (#3572)
  Replace mcp_core::prompt with rmcp::model types (#3561)
  feat (ui): close recipe modals with esc key (#3568)
  feat: recipes can retry with success criteria (#3474)
  Env var to set Ollama request timeout (#3516)
zanesq added a commit that referenced this pull request Jul 22, 2025
@zanesq
Merge branch 'zane/recipe-parameters' of github.com:block/goose into …
c8dc5f6 
…zane/recipe-parameters

* 'zane/recipe-parameters' of github.com:block/goose:
  Add recipe install warning (#3537)
  Replace mcp_core::resource::* with rmcp types (#3563)
  Add YouTube video embed to using-goosehints.md (#3560)
  fix: ensure retry-config and success-criteria are populated in openapi spec (#3575)
  fix: use sequential when sub recipe task is 1. (#3573)
  fix: track message id to keep like with like (#3572)
  Replace mcp_core::prompt with rmcp::model types (#3561)
  feat (ui): close recipe modals with esc key (#3568)
  feat: recipes can retry with success criteria (#3474)
  Env var to set Ollama request timeout (#3516)
katzdave added a commit that referenced this pull request Jul 22, 2025
@katzdave
Merge branch 'main' of github.com:block/goose into dkatz/goose-compact2
c4ec13f 
* 'main' of github.com:block/goose: (23 commits)
  fix: add fallback id to messages if none provided (#3584)
  feat: migrate ErrorData from internal mcp crates to rmcp version (#3586)
  fix: adjust subrecipe description to allow running tests (#3585)
  Scenario tests (#3430)
  feat: migrate JsonRpcMessage/Request/Response/Error/Notification from internal mcp crates to rmcp versions (#3564)
  Restore recipe parameters functionality (#3530)
  feat: Enhanced loading states with thinking icons and flying bird animation (#3478)
  Agent loop defensive (#3554)
  chore: remove needless clone() in goose/providers (#2528)
  Add recipe install warning (#3537)
  Replace mcp_core::resource::* with rmcp types (#3563)
  Add YouTube video embed to using-goosehints.md (#3560)
  fix: ensure retry-config and success-criteria are populated in openapi spec (#3575)
  fix: use sequential when sub recipe task is 1. (#3573)
  fix: track message id to keep like with like (#3572)
  Replace mcp_core::prompt with rmcp::model types (#3561)
  feat (ui): close recipe modals with esc key (#3568)
  feat: recipes can retry with success criteria (#3474)
  Env var to set Ollama request timeout (#3516)
  Updating docs to match new UI (#3552)
  ...
atarantino pushed a commit to atarantino/goose that referenced this pull request Aug 5, 2025
@bickelj
Env var to set Ollama request timeout (block#3516)
ecf43b5 
Signed-off-by: Jesse Bickel <[email protected]>
Co-authored-by: Jesse Bickel <[email protected]>
Signed-off-by: Adam Tarantino <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@michaelneale michaelneale michaelneale approved these changes

Assignees

@michaelneale michaelneale

Labels

waiting

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@bickelj @michaelneale @taniandjerry