Repository navigation
Conversation
- Add Fix My Agent for Environments (shipped in v1.58.0; beta, per organization) - Drop Trace Ingestion Limits (source work not accepted for release) - Malformed metadata header is flagged, not rejected - Output guardrails: non-streamed responses on every route; streaming not claimed - Input guardrails: add native GenAI route - Pricing: drop search (/v1/search not available yet), GenAI embedding only, one additional catalogue source, reseller models were mispriced not only zero - Vector Store: writes, searches and deletes only; deletes never refused for budget Co-Authored-By: Claude Opus 5.5 <[email protected]>
jedigalt
changed the title
jedigalt
marked this pull request as ready for review
November 10, 2026 12:41
- Shorten Faster, More Reliable Environment Builds - Drop the Assistants runs / Vector Store budget and logging sentence; retitle the remaining bullet to Gateway Pricing Lookup Fixes - Metadata header: flagged in the Request Log instead of disappearing without a trace Co-Authored-By: Claude Opus 5.5 <[email protected]>
jedigalt
commented
Nov 11, 2026
- Remove the internal Slack alerts item and the SKIPPED notes - Rename Fix My Agent to Epoch, reword its opening, drop the beta caveat - Move Open the Source Trace to Bugs/Improvements - Reword Environment Builds and Debug Failures as improvements - Combine gateway changes into two bullets and guardrail changes into two, with plain-English budget wording and no repeated claims Co-Authored-By: Claude Opus 5.5 <[email protected]>
Carried over from the week of 2026-10-26, where the duplicate gateway items were removed. Co-Authored-By: Claude Opus 5.5 <[email protected]>
…026-11-02 The stream, Request Log, provider, cost, budget and guardrail-route fixes first shipped in v1.56.1 and now live in the week of 2026-10-26. What remains: models.dev pricing gaps, key-scoped model list, Gemini tool call ids, Guardrails Test tab, auth failures and self-hosted Eval guardrail. Co-Authored-By: Claude Opus 5.5 <[email protected]>
cdileep23
previously approved these changes
Nov 11, 2026
NVJKKartik
previously approved these changes
Nov 11, 2026
- The auth-failure fix covers the CrowdStrike guardrail only. - Parallelism applies to chat runs (24-scenario suite: 31–38 min to 6.8 min), not builds; retitled accordingly. - Approve-all in the builder chat keeps separate approval for deletions and structural changes. - The REST API also rejects malformed dataset row writes. Co-Authored-By: Claude Opus 5.5 <[email protected]>
cdileep23
approved these changes
Nov 12, 2026
This branch has not been 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.
Automated draft from the release-notes workflow in future-agi/internal-tools, built from this period's release-please releases (v1.57.0, v1.58.0) with the release-notes-technical skill. A human reviews and merges; nothing auto-merges.
Review fixes applied
The review agent's 7 open findings were each checked against the source PR, then fixed:
/v1/searchreturns 501), the embedding claim is narrowed to GenAI embedding, the catalogue now draws on one additional public source, and reseller models are described as mispriced rather than only billed at zero.Added
Gate re-run on the edited section: leak-scan pass, check.sh pass. A second fact-check pass covered every changed claim.
The workflow's original review report and held items are in the run artifact: https://github.com/future-agi/internal-tools/actions/runs/42611014531
🤖 Generated with Claude Code