Repository navigation
Bring the Zoo Code access page in line with the deployed setup - #34
Merged
Merged
Conversation
Verified against the live host on 2026-09-04: llama.cpp runs a 45,056-token context, the gateway ceiling is 16,384 output tokens, the model ID is kevinbellm-27b, and the /v1/* path answers 403 without Cloudflare Access service-token headers, so the displayed numbers already matched. The page text around them did not. - Match the reasoning-effort step to the guide: turn Enable Reasoning Effort on and choose Max, which the gateway runs as xhigh; leaving it off is equivalent and Minimal is rejected. - Add the remote-path step for the two Cloudflare Access custom headers. - Explain that Last used records the latest API request at most once every five minutes, so an old date means idle rather than broken. - Clarify the Base URL step and note that Max Output Tokens is also the server ceiling that shares the context window with the prompt. - Correct the guide's Marketplace publisher name and current version. Signed-off-by: Kevin Bell <kevinBell@Linux.com>
bell-kevin
added a commit
that referenced
this pull request
Sep 5, 2026
Bring the Zoo Code access page in line with the deployed setup
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
The Zoo Code access page's numbers were checked against the live host on 2026-09-04 and already match: llama.cpp reports a 45,056-token context, the gateway ceiling is 16,384 output tokens, the served model ID is
kevinbellm-27b, and new credentials expire after 30 days. The surrounding instructions were out of date, so this PR fixes the text rather than the values.docs/ZOO_CODE.md: turn Enable Reasoning Effort on and choose Max (the gateway runs it asxhigh); leaving it off gives the same depth and Minimal is rejected./v1/*path answers 403 without them.Test plan
pytest tests/test_app.py tests/test_zoo_api.pyinservices/assistant-web: 44 passedscripts/check-public-tree.shpasseskevinbellm-remote.service, then confirm the new steps on the signed-in page