docs: fill coverage gaps across API reference, CLI, Omni, and app dev guide#2055
Open
kenvandine wants to merge 3 commits into
Open
docs: fill coverage gaps across API reference, CLI, Omni, and app dev guide#2055kenvandine wants to merge 3 commits into
kenvandine wants to merge 3 commits into
Conversation
… guide API reference: - openai.md: document enable_thinking/thinking params for reasoning model control; add SSE streaming client-side guidance (reconnection, cold-start, error handling) - lemonade.md: add GET /v1/system-stats, POST /v1/log-level, POST /v1/params endpoint sections with request/response examples; add sdcpp_args, flm_args, and vllm_args to the /v1/load parameters table; update summary table - anthropic.md: expand from a 2-line stub to a full API reference with parameter table, curl + Python SDK examples, non-streaming and streaming response formats, and error response table CLI reference: - cli.md: add lemonade config to the Server commands table and ToC; add "Options for config" section with examples and link to /v1/params Omni/collection docs: - lemonade-omni.md: add REST API section for collection create/query/delete; document component loading behavior and LRU eviction implications; add chat-transcription model guide covering when to use native multimodal models vs OmniRouter, message format, and label-based discovery New app developer guide: - building-apps.md: new guide covering connection pattern, model discovery, inference examples (chat, embeddings, images, audio), streaming best practices, runtime model management, error handling reference table, authentication, and performance tips - dev/README.md: restructure to surface building-apps.md and examples index for app developers alongside the existing contributor docs https://claude.ai/code/session_01RZAtERd26JPV38HTa8Sj9d
jeremyfowers
reviewed
Jun 1, 2026
jeremyfowers
reviewed
Jun 1, 2026
jeremyfowers
reviewed
Jun 1, 2026
jeremyfowers
reviewed
Jun 1, 2026
| @@ -0,0 +1,331 @@ | |||
| # Building Apps with Lemonade | |||
Member
There was a problem hiding this comment.
Yeah, something like this is probably needed. We need a whole "SDK" landing page tbh.
- Remove /v1/params docs: intentionally undocumented, planned for removal - Remove /v1/system-stats docs: endpoint to be moved to /internal - Remove "Managing collections via the API" from lemonade-omni.md: intentionally single-sourced in custom-models.md - Clean up building-apps.md references to removed endpoints Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
fl0rianr
requested changes
Jun 3, 2026
Collaborator
fl0rianr
left a comment
There was a problem hiding this comment.
Thanks for filling these docs gaps — the new app-dev guide is good, but I think this needs a small cleanup before merge:
/v1/log-levelis documented as requiring LEMONADE_ADMIN_API_KEY, but it is registered as a regular/v1/*route. With only LEMONADE_ADMIN_API_KEY configured, regular API routes are still unauthenticated, so this doc currently overstates the protection. Either move this to/internal/*or document the actual auth behavior. I think Jeremy's comment was not addresed.- The CLI docs say
lemonade configusesPOST /v1/params, but the CLI calls/internal/set.
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
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.
API reference:
add SSE streaming client-side guidance (reconnection, cold-start, error handling)
endpoint sections with request/response examples; add sdcpp_args, flm_args,
and vllm_args to the /v1/load parameters table; update summary table
table, curl + Python SDK examples, non-streaming and streaming response formats,
and error response table
CLI reference:
"Options for config" section with examples and link to /v1/params
Omni/collection docs:
document component loading behavior and LRU eviction implications; add
chat-transcription model guide covering when to use native multimodal models
vs OmniRouter, message format, and label-based discovery
New app developer guide:
inference examples (chat, embeddings, images, audio), streaming best practices,
runtime model management, error handling reference table, authentication, and
performance tips
app developers alongside the existing contributor docs
https://claude.ai/code/session_01RZAtERd26JPV38HTa8Sj9d