Repository navigation
docs(decisions): document input_json parts on /v1/decisions - #3148
Merged
Merged
Conversation
|
@mateo-berri is attempting to deploy a commit to the Berri AI Team on Vercel. A member of the Team first needs to authorize it. |
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
…leftover input, and date the Gemini row
… messages, fallbacks and cooldowns, and date the Gemini page
mateo-berri
marked this pull request as draft
November 20, 2026 05:21
… hide-secrets and cooldown text
…_json keys and numbers
…list input_json on the guardrail pages
zoveki
marked this pull request as ready for review
November 20, 2026 21:33
This branch was successfully deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
This documents the
input_jsoncontent part on/v1/decisions, which LiteLLM #52805 adds for OpenAI and LiteLLM #52807 ports to the 1.108.x LTS line. The request fields table, the features table and the availability table now list it. A new JSON input section covers the 400 for developer and system messages, thedrop_paramsbehavior, thehide-secretscheck of the keys and string values insidedata, with a numbered name for a redacted key that would clash with another, how LLM Shield swaps the keys, strings and numbers insidedata, the 400 Cisco AI Defense answers when it would redact a JSON request, and how a load-balanced group routes JSON requests, with fallbacks and cooldowns. The cooldown case answers a 429 on the LTS line, so the page says so. Withdrop_paramson, a deployment without JSON support can answer from the rest of the input, so the page suggests a model group of its own for JSON deployments. Thehide-secretsand LLM Shield pages now link to the JSON input sectionThe Supported column names OpenAI only, since no Azure Decisions model answers a call yet and
azure/has no row in the supported providers list. The Notes column saysazure/deployments send the parts on, which a unit test in #52805 checksThe Gemini row now names
v1.111.0-rc.1, the releasefirst_release.py 51220gives for Gemini Decision 1, instead of saying it is not in a release yet. The Gemini provider page's badge namesv1.111.0and its sentence says first inv1.111.0-rc.1, as CONTRIBUTING.md asksThe JSON row names
v1.112.0-rc.1andv1.108.14, the first releasesfirst_release.py 52805andfirst_release.py 52807give.v1.108.13shipped on Nov 19 without #52807. This PR stays a draft until #52805 merges, and then the names and the behavior text are checked again against the merged codeProof
E2E exception at c2e3052. The diff is docs only, so there is no before leg.
check-docs.pypasses at c2e3052 against the merge base ada2e67, and the JSON input section's curl example ran against a proxy at #52805's d85536a675e. Against today's main the checker also flagsdocs/proxy/lens/deployment/docker.md, a page main removed in #3190, which this PR does not touchThe curl example returns OpenAI's decision through a proxy at #52805's d85536a675e. The run changed only the URL to a tunnel to the QA proxy and the model to that proxy's OpenAI
gpt-6-lunagroupCommand and output
The 400 that names
input_json, thedrop_paramsdrop, the mixed-group routing, the fallback, thehide-secretsredaction with its numbered keys and the LLM Shield swaps of keys and numbers the page describes are each a live cell in the proof of LiteLLM #52805 at d85536a675e, and of LiteLLM #52807 at 3e5f3d895d6 for the LTS lineCaveats (if any)
Medium
v1.108.14is tagged.first_release.pychecks both again right before this PR mergesLow