Repository navigation
docs: resolve throttled probes and compare Kimi protocols - #69
Merged
Merged
Conversation
Contributor
Author
How to use the Graphite Merge QueueAdd either label to this PR to merge it via the merge queue:
You must have a Graphite account in order to use the merge queue. Sign up using this link. An organization admin has enabled the Graphite Merge Queue in this repository. Please do not merge from GitHub as this will restart CI on PRs being processed by the merge queue. This stack of pull requests is managed by Graphite. Learn more about stacking. |
Merge activity
|
The support matrix still showed 15 rate-limit failures after the catalog sweep. Isolated retries now resolve all 15: 13 pass, while GPT-5 and GPT-5 Nano reasoning fail on malformed proxy stream events. Kimi K3's blocking tool loop also passes on retry; its JSON-plus-tools probe still skips execution. The existing overview and JSON preserve prior outcomes and the unchanged CLI catalog snapshot. Compare Kimi protocols against official Moonshot docs and live Foundry probes: Responses supports text and blocking tools but still fails streaming and skips tools with JSON; Anthropic is rejected by this enrollment's backend. Foundry rejects Chat Completions reasoning_content, while Responses reasoning cannot round-trip without encrypted content under store=false. Keep current routing and document these limits. Validation: 17 focused catalog probes; bounded Kimi raw/SDK route comparisons; all 83 offline tests and pnpm run verify passed. No live testing added to CI. Only the existing two documentation files changed.
graphite-app
Bot
force-pushed
the
test/focused-model-reruns
branch
from
September 14, 2026 04:07
9c6d760 to
9983f5c
Compare
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.
The support matrix still showed 15 rate-limit failures after the catalog sweep. Isolated retries now resolve all 15: 13 pass, while GPT-5 and GPT-5 Nano reasoning fail on malformed proxy stream events. Kimi K3's blocking tool loop also passes on retry; its JSON-plus-tools probe still skips execution. The existing overview and JSON preserve prior outcomes and the unchanged CLI catalog snapshot.
Compare Kimi protocols against official Moonshot docs and live Foundry probes: Responses supports text and blocking tools but still fails streaming and skips tools with JSON; Anthropic is rejected by this enrollment's backend. Foundry rejects Chat Completions reasoning_content, while Responses reasoning cannot round-trip without encrypted content under store=false. Keep current routing and document these limits.
Validation: 17 focused catalog probes; bounded Kimi raw/SDK route comparisons; all 83 offline tests and pnpm run verify passed. No live testing added to CI. Only the existing two documentation files changed.