Declarative providers #5084
Merged
Declarative providers #5084
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 12 commits
October 7, 2025 13:57
This was referenced Oct 11, 2025
Collaborator
Author
|
fixes #4397 |
Collaborator
Author
|
fixes #4221 |
This was referenced Oct 11, 2025
Collaborator
Author
|
fixes #4029 |
Collaborator
Author
|
@michaelneale you were saying that custom providers were confusing and so they were. or really it was all kinda broken. this refactors how things work and allows one to actually edit a custom provider(!). it also bring sin the concept of internal custom providers which should allow us to reduce code duplication. I did it with groq and it worked well. it even now allows streaming with groq where before we didn't have that. there's still work to be done. the frontend has a checkbox for no api key required, but that doesn't seem to be hooked up to anything. there's probably a lot more features (toolshim?) that you'd want to be able to set from the json file but we can bring them in one by one |
9 tasks
Collaborator
|
very nice @DOsinga - didn't get a chance ot try it but I love this approach, this seems the right approach. |
Collaborator
Author
|
fixes #5148 |
michaelneale
approved these changes
Oct 15, 2025
Collaborator
michaelneale
left a comment
michaelneale
left a comment
There was a problem hiding this comment.
not sure what else you want to do here, but I tested this with:
LLAma studio - worked with gptoss
llama-server cli, worked
openrouter openai compatible, just worked.
This is truly execllent, and could save a lot of hassle
added 2 commits
October 15, 2025 08:33
…into declarative-providers
DOsinga
commented
Oct 15, 2025
| Some(Value::String("Payload Too Large".to_string())), | ||
| Err(ProviderError::RequestFailed( | ||
| "Request failed with status: 413 Payload Too Large".to_string(), | ||
| Err(ProviderError::ContextLengthExceeded( |
Collaborator
Author
There was a problem hiding this comment.
hmmm, how is this related ...
tlongwell-block
added a commit
that referenced
this pull request
Oct 15, 2025
…utonomous * origin/main: feat: add Daily Standup Report Generator recipe (#5123) (#5131) Sort providers in alphabetical vs random (#5090) Declarative providers (#5084) adding youtube link to firecrawl mcp tutorial, merge after 9am Eastern Oct 15 (#5173) Ollama integration: modified default model + added models (#5153) Fix codex subagent configuration in documentation (#5180) fix: include apple silicon build of the desktop app in build artifacts (#5174) fixing video embed (#5171) chore: clean up random unused files (#5166) fix: adjust download_cli.sh to tolerate no OS variable (#5169) mcp tutorial page for firecrawl (#5152) Remove orphaned tool calls before compaction (#5059) feat: add copy as markdown button to documentation pages (#5158) chore: include vendored node executable (#5160) remove extra whitespace from message (#5159)
katzdave
added a commit
that referenced
this pull request
Oct 15, 2025
* 'main' of github.com:block/goose: Declarative providers (#5084) adding youtube link to firecrawl mcp tutorial, merge after 9am Eastern Oct 15 (#5173) Ollama integration: modified default model + added models (#5153) Fix codex subagent configuration in documentation (#5180) fix: include apple silicon build of the desktop app in build artifacts (#5174)
wpfleger96
added a commit
to wpfleger96/goose
that referenced
this pull request
Oct 15, 2025
* main: (55 commits) [docs] Add Blog Post: "Designing AI for Users, Not Just LLMs" (block#5190) docs: update cognee, jetbrains, mbot extensions config (block#5172) Minimally disable subagents when not in autonomous model (block#5149) Fix provider sort (block#5188) blog: Getting Started with Goose on Windows (block#5156) feat: add CI/CD Pipeline recipe (block#5183) feat: add Daily Standup Report Generator recipe (block#5123) (block#5131) Sort providers in alphabetical vs random (block#5090) Declarative providers (block#5084) adding youtube link to firecrawl mcp tutorial, merge after 9am Eastern Oct 15 (block#5173) Ollama integration: modified default model + added models (block#5153) Fix codex subagent configuration in documentation (block#5180) fix: include apple silicon build of the desktop app in build artifacts (block#5174) fixing video embed (block#5171) chore: clean up random unused files (block#5166) fix: adjust download_cli.sh to tolerate no OS variable (block#5169) mcp tutorial page for firecrawl (block#5152) Remove orphaned tool calls before compaction (block#5059) feat: add copy as markdown button to documentation pages (block#5158) chore: include vendored node executable (block#5160) ...
michaelneale
added a commit
that referenced
this pull request
Oct 16, 2025
* main: Skip hidden & real format (#5194) docs: Hacktoberfest blog submission - Best Practices for Using Goose in Enterprise Environments by Anudhyan Datta. (#5184) docs: prompt injection detection (#5193) Fix mcp large response race condition (#5065) Compaction overhaul (#5186) fix: #3960 better approach to input schema for dynamic task params (#5189) used recipe id or deeplink to start agent (#5154) [docs] Add Blog Post: "Designing AI for Users, Not Just LLMs" (#5190) docs: update cognee, jetbrains, mbot extensions config (#5172) Minimally disable subagents when not in autonomous model (#5149) Fix provider sort (#5188) blog: Getting Started with Goose on Windows (#5156) feat: add CI/CD Pipeline recipe (#5183) feat: add Daily Standup Report Generator recipe (#5123) (#5131) Sort providers in alphabetical vs random (#5090) Declarative providers (#5084) adding youtube link to firecrawl mcp tutorial, merge after 9am Eastern Oct 15 (#5173) Ollama integration: modified default model + added models (#5153) Fix codex subagent configuration in documentation (#5180)
Merged
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Providers loaded from the file system