feat: add Maple AI provider integration#10436
feat: add Maple AI provider integration#10436marksftw wants to merge 4 commits intoanomalyco:devfrom
Conversation
|
The following comment was made by an LLM, it may be inaccurate: Potentially Related PRs FoundWhile no exact duplicates of PR #10436 were found, there are related PRs that implement similar functionality for other providers:
These PRs share the same architectural pattern of dynamic model discovery from a provider endpoint, which is the core innovation in the Maple AI provider integration. You may want to review how these implementations handle error cases and model caching to ensure consistency across all providers. |
|
I don't think this PR is directly dependent on those PR's referenced by the GitHub action. |
opencode-agent
Bot
force-pushed
the
dev
branch
from
00637c0 to
71e0ba2
Compare
thdxr
force-pushed
the
dev
branch
4 times, most recently
from
f1ae801 to
08fa7f7
Compare
|
Would love to get this merged in soon as a strong privacy and security option for users. Especially on a day like today when Claude goes down :) |
marksftw
force-pushed
the
feature/add-maple-ai-provider
branch
from
d4ec936 to
ae7d92c
Compare
marksftw
force-pushed
the
feature/add-maple-ai-provider
branch
from
ba93bb7 to
d421ab4
Compare
|
Keeping this PR current with latest from |
marksftw
force-pushed
the
feature/add-maple-ai-provider
branch
from
d421ab4 to
8918fb1
Compare
marksftw
force-pushed
the
feature/add-maple-ai-provider
branch
from
1f42c2b to
0f7b5c6
Compare
marksftw
force-pushed
the
feature/add-maple-ai-provider
branch
from
0f7b5c6 to
1f42c2b
Compare
marksftw
force-pushed
the
feature/add-maple-ai-provider
branch
from
1f42c2b to
c518fbd
Compare
Replace the hardcoded GitLab discovery block with a generic loop over all discoveryLoaders entries. Refactor Maple to use the existing discoverModels hook instead of inline fetching.
|
hey @adamdotdevin and @thdxr, I've been keeping this PR up to date with dev. Just pushed an update today that generalizes the model discovery loop to handle both GitLab and Maple. I know there are a lot of PRs to review, so would definitely appreciate if this one got a look sometime soon. We have many users running Maple with OpenCode but it's a manual process to set up. This would make it much smoother by being included in the provider list. |
1 participant
Fixes #10434
What does this PR do?
Adds Maple AI as a first-class provider with dynamic model discovery.
Users run
/connectto add their Maple API key, then/modelsto see available models fetched directly from their Maple proxy.Generalized model discovery
The existing model discovery infrastructure was hardcoded to only run for GitLab. This PR refactors the discovery loop to be generic — it now iterates over all providers that return a
discoverModelsfunction from their custom loader, rather than special-casing a single provider. Maple uses this samediscoverModelshook, so no new discovery mechanism was needed.This means any future provider that needs runtime model discovery can simply return a
discoverModelsfunction and the framework handles the rest (calling it, merging results, error logging, settingproviderID).How did you verify your code works?
Tested locally with my Maple account. Confirmed provider selection, API key configuration, and chat completion requests work correctly. In fact, most of this code change was built using OpenCode connected to Maple.