-
Notifications
You must be signed in to change notification settings - Fork 2k
chore: bump version 0.13.0 #3050
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
Merged
Conversation
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
* remove enable cache * trigger CI * remove extra with paramters which I believe to be unecessary * try installing uv manuallly to avoid post install step * should be fixed by manually installing and not using the action * remove comment to trigger
* Keep legacy functionality * Refactor for cleanliness
…e file (#5261) refactor into common uri parsing logic, fix test, and fix compose file
* base * use secret field * fix * auth code * stage publish * decouple backfill * revert uncomment * providers and agent vars * mcp * mcp * stage and publish * fix oauth * double encrypt * sandbox --------- Co-authored-by: Letta Bot <[email protected]>
* feat: add new ApprovalReturn list in api layer * use base class * api sync
* feat: add approvals persistence to message orm * fix imports in alembic migration * missing import
* Adapt to support multiple tool returns * remove unused create_tool_return_message * Add explanation to otid index * Simplify explicit tool returns * Simplify function return to only return single object
* feat: gate out hitl for async * add import
… 404s from sentry (#5242) * add multiline log auto detect * implement logger.exception() * filter out 404 * remove potentially problematic changes
* Fix system init messages and anthropic parsing * Add backwards compat tool call id adding
* wip * Fix parallel tool calling interface * wip * wip adapt using id field * Integrate new multi tool return schemas into parallel tool calling * Remove example script * Reset changes to llm stream adapter since old agent loop should not enable parallel tool calling * Clean up fallback logic for extracting tool calls * Remove redundant check * Simplify logic * Clean up logic in handle ai response * Fix tests * Write anthropic dict conversion to be back compatible * wip * Double write tool call id for legacy reasons * Fix override args failures * Patch for approvals * Revert comments * Remove extraneous prints
Remove unuseful tool rules for v1
* base * allow attach * display badge * clean up --------- Co-authored-by: Letta Bot <[email protected]>
skip Co-authored-by: Letta Bot <[email protected]>
* fix: rename current to dev * chore: rename current to dev * chore: next * chore: rename fix --------- Co-authored-by: Shubham Naik <[email protected]>
…43] [LET-3741] (#5710) * chore: add context_window_limit and max_tokens to update agent [LET-3743] * add generated sdk docs * simplify comment
* test dd build * dd agent in cluster * quick poc * refactor and add logging * remove tracing etc. * add changes to otel logging config * refactor to accept my feedback * finishing touches
* Add delete endpoint * Fern autogen
support default empty
…ves attach/detach routes to agents [LET-4428] (#5708) * deprecate ids for identity endpoints in favor of attach * move archive attach/detach to agent * new identities routes * overrides for path --------- Co-authored-by: Ari Webb <[email protected]>
--------- Co-authored-by: Ari Webb <[email protected]> Co-authored-by: Sarah Wooders <[email protected]>
* Add embedding config field to archives * Fix alembic script * Simplify archive manager * Fern autogen * Fix failing tests * Fix alembic
add logger calls instead of prints
* docs: add PDF chat tutorial with correct shell syntax * docs: add PDF chat tutorial to navigation * docs: add requests dependency for Python in pdf_chat tutorial * docs: wrap TypeScript example in async function to fix top-level await error * docs: add error handling for existing folders in pdf_chat tutorial * docs: fix folders.list() to use response.folders property * docs: await PDF download completion to fix race condition * docs: use retrieve_by_name API for proper folder existence handling * docs: fix upload API to use single request object and file stream * docs: fix upload to use folderId as first parameter * docs: simplify upload to use file stream directly * docs: use three-parameter upload signature (folderId, file, options) * docs: fix upload parameter order to (file, folderId, options) * docs: fix attach to pass folderId directly instead of object
…] (#5712) base Co-authored-by: Letta Bot <[email protected]>
* docs: wrap TypeScript complete examples in async functions for copy-paste compatibility * docs: fix blocks.attach to pass blockId directly instead of object * docs: fix blocks.attach in shared-memory-blocks tutorial * docs: add timeout configuration for web search examples
docs: improve Examples & Tutorials page with better organization and content - Reorganize page into clear sections: Getting Started, Ready-to-Deploy, Multi-Agent, Tools & Integrations, SDK Examples, Community Projects, Learning Resources - Add more examples from Awesome Letta including CharacterAI clone, Deep Research Agent, DuckDB Agent, and various integrations - Add helpful Info box pointing to Quickstart, DeepLearning.AI Course, and Awesome Letta - Improve card descriptions to be more informative and action-oriented - Update title from "Letta Cookbooks" to "Examples & Tutorials" for clarity - Fix internal tutorial links to use correct /examples/ and /cookbooks/ paths - Better connect page to rest of documentation and community resources
…T-5800] (#5687) * base * revert openapi * union * simplify * stainless * stainless * fix * fix test * generate --------- Co-authored-by: Letta Bot <[email protected]>
make server use logger
…rate limiting (#5731) hotfix lol
* refactor not to use warnings.warn * temp circular import fix maybe unecessary/bnad * fix Deprecation warning * fix deprecation warning and mcp thing? * revert changes to mcp server test * fix deprecation warning
just the easy ones Co-authored-by: Ari Webb <[email protected]>
* base * generatE --------- Co-authored-by: Letta Bot <[email protected]>
* update leaderboard pointer * use raw yaml * update cost cap
copy over Jake's PR from OSS
* feat: add special approval request otid for openai streaming * fix import
fa23f91 to
13273b4
Compare
|
📦 Dependencies Alert:
Please review these changes carefully to ensure they are intended (cc @sarahwooders @cpacker). |
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.
Please describe the purpose of this pull request.
Is it to add a new feature? Is it to fix a bug?
How to test
How can we test your PR during review? What commands should we run? What outcomes should we expect?
Have you tested this PR?
Have you tested the latest commit on the PR? If so please provide outputs from your tests.
Related issues or PRs
Please link any related GitHub issues or PRs.
Is your PR over 500 lines of code?
If so, please break up your PR into multiple smaller PRs so that we can review them quickly, or provide justification for its length.
Additional context
Add any other context or screenshots about the PR here.