release: v6.7.0 - #40
Merged
Merged
Conversation
Add the Axon Lumen 4 Code model in 200K and 400K context variants (axon-lumen-4-code-200k, axon-lumen-4-code-400k) with plan-gated access restricted to Pro Plus and Ultra subscriptions. - Define Lumen model entries in BUILTIN_AXON_MODELS with pricing and context window metadata - Add canUseLumenModels() and isLumenAxonModel() helpers alongside a shared normalizePlan() utility - Update UI model picker to lock Lumen models with a plan badge when the account tier doesn't include them - Apply automatic fallback to the default Eido model when a stored Lumen selection is loaded on an ineligible plan - Gate Lumen model usage in headless/CLI mode with a descriptive error message and exit - Extend is400kAxonModel() to cover Lumen 400k variants, and wire get200kAxonFallback() accordingly - Add tests for Lumen model definitions, plan restrictions, and identification helpers Also includes error message sanitization in agent.ts — introducing streamErrorLabel() and sanitizeErrorMessage() to prevent raw HTML or oversized upstream error bodies from leaking into the transcript UI. Applies the new sanitizer in the stream retry loop, the interrupt handler, and the compaction error path.
Contributor
Summary By MatterAI
🔄 What ChangedThis PR bumps the project version to 🔍 Impact of the ChangeExpands the LLM offering with high-performance Axon Lumen models while enforcing strict subscription tier gating. Enhances CLI stability and error sanitization by stripping raw upstream HTML error bodies. 📁 Total Files ChangedClick to Expand
🧪 Test Added/RecommendedAdded
🔒 Security Vulnerabilities
|
Contributor
|
✅ Reviewed the changes: Clean release PR adding Axon Lumen 4 models with plan-based access control, error sanitization for upstream HTML responses, and comprehensive test coverage. No issues found in the new code. |
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
1 participant
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.
v6.7.0
Added
axon-lumen-4-codein 200K and 400K context variants (axon-lumen-4-code-200kandaxon-lumen-4-code-400k). Lumen models are available on Pro Plus and Ultra plans.Changelog
Full diff: v6.6.8...v6.7.0