Releases: letta-ai/letta
v0.6.13
What's Changed
- docs: update README.md by @cpacker in #2365
- docs(contrib): Add steps to prepare PostgreSQL environment by @kk-src in #2366
- chore: update workflows by @cpacker in #2367
- fix: patch api routes by @carenthomas in #2374
- chore: bump version 0.6.13 by @carenthomas in #2375
New Contributors
Full Changelog: 0.6.12...0.6.13
0.6.12
What's Changed
- fix: patch
use_assistant_message
flag on the server by @sarahwooders in #2363 - chore: bump version 0.6.12 by @sarahwooders in #2364
Full Changelog: 0.6.11...0.6.12
0.6.11
What's Changed
- chore: add
colorama
dependency and bump version by @sarahwooders in #2362
Full Changelog: 0.6.10...0.6.11
0.6.10
What's Changed
- chore: Various bug fixes by @mattzh72 in #2356
- fix: fix types in azure provider and add steps table by @sarahwooders in #2359
- chore: bump to version 0.6.10 by @sarahwooders in #2360
- fix: update authorization header to use X-BARE-PASSWORD format by @theocnrds in #2338
- fix: upgrade dependencies with security warnings by @nrox in #2319
- fix: allow no headers for
RESTClient
by @sarahwooders in #2361
New Contributors
- @theocnrds made their first contribution in #2338
- @nrox made their first contribution in #2319
Full Changelog: 0.6.9...0.6.10
0.6.9
🪲 Bugfix release, including fixes to work with gemini-pro
models
What's Changed
- feat: add support for matching all tags in client by @sarahwooders in #2345
- feat: Add new types and other changes by @mattzh72 in #2348
- feat: update
Tool
schemas and improve provider integration by @sarahwooders in #2349 - feat: bump version to 0.6.9 by @sarahwooders in #2350
Full Changelog: 0.6.8...0.6.9
v0.6.8
🐛 Bugfix release
What's Changed
- chore: Improved sandboxing support by @mattzh72 in #2333
- chore: remove web compat checker by @4shub in #2336
- fix: validate after limit assignment in
create_block
by @thelonejordan in #2310 - feat: provider persistence + various fixes by @sarahwooders in #2340
- chore: bump version 0.6.8 by @sarahwooders in #2342
New Contributors
- @thelonejordan made their first contribution in #2310
- @knowsuchagency made their first contribution in #2337
Full Changelog: 0.6.7...0.6.8
v0.6.7
🐞 Bugfix release
What's Changed
- feat: add error codes to composio errors by @4shub in #2290
- fix: Remove in-memory
_messages
field on Agent by @mattzh72 in #2295 - fix: propagate error on tool failure by @carenthomas in #2281
- chore: Clean up
.load_agent
usage by @mattzh72 in #2298 - feat: add back template id field for create agent req by @carenthomas in #2300
- feat: add message type literal to usage stats by @carenthomas in #2297
- fix: Fix limit for get_messages_by_ids by @mattzh72 in #2301
- feat: store handle in configs by @carenthomas in #2299
- fix: hotfix by @cpacker in #2302
- fix: add underlying error message for Retries Exhausted error by @carenthomas in #2308
- fix: deprecate function return in new test by @carenthomas in #2309
- feat: Make composio error catching more verbose and granular by @mattzh72 in #2303
- fix: patch bug in inner thoughts unpacker by @cpacker in #2311
- fix: record the external memory summary inside of the context viewer by @cpacker in #2306
- Bugfix: fix attribute error in
_repr_html_
method forLettaResponse
by @dboyliao in #2313 - feat: various fixes by @sarahwooders in #2320
- chore: bump version to 0.6.7 by @sarahwooders in #2321
Full Changelog: 0.6.6...0.6.7
v0.6.6
🐜 Bugfix release (fix issue with disappearing messages in ADE)
What's Changed
- chore: bump composio packages by @mattzh72 in #2278
- fix: Add index to messages table by @mattzh72 in #2280
- chore: Clean up upserting base tools by @mattzh72 in #2274
- feat: add new RateLimitExceededError by @carenthomas in #2277
- chore: Add temporary telemetry logs by @mattzh72 in #2284
- fix: Remove load agent in recall cursor by @mattzh72 in #2286
- chore: Remove debugging logs by @mattzh72 in #2287
- feat: rename function to tool in sdk by @carenthomas in #2288
- Add support for non pro models by @SwastikGorai in #2285
- feat: Add ConditionalToolRules by @mlong93 in #2279
- feat: rename internal monologue by @carenthomas in #2289
- feat: add new ContextWindowExceededError by @carenthomas in #2272
- Fix bug: add required argument
actor
(load_file_to_source
). by @dboyliao in #2292 - chore: bump version to 0.6.6 by @sarahwooders in #2293
New Contributors
- @SwastikGorai made their first contribution in #2285
- @dboyliao made their first contribution in #2292
Full Changelog: 0.6.5...0.6.6
v0.6.5
This release includes bug fixes for Ollama embeddings, improved error handling for streaming, improvements in debugging tool callings and agent creation.
⚙️ Providing tool call logs (stdout
and stderr
)
We now pass back the logs from tool execution in the FunctionResponse
object. You can view these logs in the ADE in addition to the tool response:
👾 Simplification of agent creation API
We now allow for simply specifying the LLM and embedding configuration of an agent by specifying the model in the format <provider>/<model>
:
curl --request POST \
--url http://localhost:8283/v1/agents/ \
--header 'Content-Type: application/json' \
--data '{
"memory_blocks": [
{
"value": "Name: Sarah",
"label": "human"
},
{
"value": "I am a helpful assistant",
"label": "persona"
}
],
"llm": "anthropic/claude-3-5-sonnet-20241022",
"embedding": "openai/text-embedding-ada-002"
}'
You can also provide the context window, and specify the character limit of memory blocks (e.g. human/persona):
curl --request POST \
--url http://localhost:8283/v1/agents/ \
--header 'Content-Type: application/json' \
--data '{
"memory_blocks": [
{
"value": "Name: Sarah",
"limit": 5000,
"label": "human"
},
{
"value": "I am a helpful assistant",
"label": "persona"
}
],
"llm": "anthropic/claude-3-5-sonnet-20241022",
"embedding": "openai/text-embedding-ada-002",
"context_window_limit": 15000
}'
What's Changed
- feat: Catch composio errors and return informative errors in the endpoint by @mattzh72 in #2247
- feat: Rewrite agents by @mattzh72 in #2232
- Fix: Move orm metadata out of write-only Agent pydantic objects by @mattzh72 in #2249
- fix: Changing e2b template id as an env var reflects immediately by @mattzh72 in #2250
- fix: Remove
created_by_id
check by @mattzh72 in #2252 - chore: Delete metadata.py by @mattzh72 in #2253
- docs: fix typo in prompt by @keenranger in #2256
- chore: Catch orm specific issues in agents v1 routes and simplify tool add/remove from agent by @mattzh72 in #2259
- feat: separate Passages tables by @mlong93 in #2245
- fix: add error logging on stream fails by @cpacker in #2261
- docs: Feature/update docs by @keithf123r in #2257
- fix: Make
embedding_endpoint_type
an enum by @mattzh72 in #2251 - fix: Fix update agent by @mattzh72 in #2265
- chore: Add comprehensive unit test for adding/removing tools via update agent by @mattzh72 in #2267
- fix: Scale up database by @mattzh72 in #2263
- feat: Adding init tool rule for Anthropic endpoint by @mlong93 in #2262
- fix: fix ollama embeddings by @sarahwooders in #2264
- Create multiplatform docker images by @AliSayyah in #2254
- feat: Add optional llm and embedding handle args to CreateAgent request by @carenthomas in #2260
- fix: refactor sandbox run logic to add status field by @carenthomas in #2248
- chore: Add testing around base tools by @mattzh72 in #2268
- fix: Deprecate in memory function stores in agent.py by @mattzh72 in #2271
- fix: Allow
ChildToolRule
to work without support for structured outputs by @mlong93 in #2270 - chore: bump version to 0.6.5 by @sarahwooders in #2275
New Contributors
- @keenranger made their first contribution in #2256
- @keithf123r made their first contribution in #2257
Full Changelog: 0.6.4...0.6.5
v0.6.4
🐛 Bugfix release - This release fixes the issue in the ADE that cause uploaded files to not be properly inserted in agents' archival memory
What's Changed
- feat: fix message create/update schemas to simply schema by @sarahwooders in #2223
- fix: Update README.md asset URLs to be absolute by @cpacker in #2227
- chore: removed agent_store, storage connectors by @mlong93 in #2229
- ignore extra variables in env files by @AliSayyah in #2226
- feat: catch error with providers in model listing by @sarahwooders in #2231
- feat: archival memory file upload by @mlong93 in #2228
- chore: raising errors for passages, adding new passage test by @mlong93 in #2234
- feat: route all sandbox errors to stderr by @carenthomas in #2222
- fix: make sandboxrunresult rv not optional by @carenthomas in #2244
- chore: bump version 0.6.4 by @sarahwooders in #2246
New Contributors
- @AliSayyah made their first contribution in #2226
Full Changelog: 0.6.3...0.6.4