Kian Jones 630c147b13 fix: truncate oversized text in embedding requests (#9196) ...

fix: handle oversized text in embedding requests with recursive chunking

When message text exceeds the embedding model's context length, recursively
split it until all chunks can be embedded successfully.

Changes:
- `tpuf_client.py`: Add `_split_text_in_half()` helper for recursive splitting
- `tpuf_client.py`: Add `_generate_embeddings_with_chunking()` that retries
  with splits on context length errors
- `tpuf_client.py`: Store `message_id` and `chunk_index` columns in Turbopuffer
- `tpuf_client.py`: Deduplicate query results by `message_id`
- `tpuf_client.py`: Use `LettaInvalidArgumentError` instead of `ValueError`
- `tpuf_client.py`: Move LLMClient import to top of file
- `openai_client.py`: Remove fixed truncation (chunking handles this now)
- Add tests for `_split_text_in_half` and chunked query deduplication

🤖 Generated with [Letta Code](https://letta.com)

Co-authored-by: Letta <noreply@letta.com>

2026-02-24 10:52:06 -08:00

..

adapters

fix: handle httpx.ReadError, WriteError, and ConnectError in LLM streaming clients (#8243)

2026-01-12 10:57:49 -08:00

configs

feat: add SGLang support (#8838)

2026-01-29 12:43:51 -08:00

data

feat(core): add image support in tool returns [LET-7140] (#8985)

2026-01-29 12:43:53 -08:00

helpers

fix: remove letta-free embeddings from testing (#6870)

2025-12-15 12:03:09 -08:00

managers

fix: load default provider config when summarizer uses different prov… (#9051)

2026-01-29 12:44:04 -08:00

mcp_tests

test: skip deepwiki SSE MCP server test (#9218)

2026-02-24 10:52:06 -08:00

model_settings

feat: add MiniMax provider support (#9095)

2026-01-29 12:44:04 -08:00

performance_tests

merge this (#4759)

2025-09-17 15:47:40 -07:00

sdk

feat: set default temperature to 1.0 [LET-6920] (#8618)

2026-01-19 15:54:43 -08:00

test_agent_files

feat: set default temperature to 1.0 [LET-6920] (#8618)

2026-01-19 15:54:43 -08:00

test_tool_sandbox

merge this (#4759)

2025-09-17 15:47:40 -07:00

test_tool_schema_parsing_files

merge this (#4759)

2025-09-17 15:47:40 -07:00

__init__.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

clear_postgres_db.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

config.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

conftest.py

chore: bump wait_for_server from 30 to 60 seconds (#8435)

2026-01-12 10:57:49 -08:00

constants.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

integration_test_agent_tool_graph.py

feat: Implement child tool rules args override [LET-4570] (#5060)

2025-10-07 17:50:48 -07:00

integration_test_async_tool_sandbox.py

chore: bump wait_for_server from 30 to 60 seconds (#8435)

2026-01-12 10:57:49 -08:00

integration_test_batch_api_cron_jobs.py

fix: duplicate session commit in step logging (#7512)

2026-01-12 10:57:19 -08:00

integration_test_batch_sdk.py

feat: Fix test batch sdkpy [LET-4507] (#4917)

2025-10-07 17:50:46 -07:00

integration_test_builtin_tools.py

chore: bump wait_for_server from 30 to 60 seconds (#8435)

2026-01-12 10:57:49 -08:00

integration_test_cancellation.py

fix: use shared event + .athrow() to properly set stream_was_cancelle… (#9019)

2026-01-29 12:44:04 -08:00

integration_test_chat_completions.py

feat: Implement streaming chat completions endpoint [LET-5485] (#5446)

2025-10-24 15:12:11 -07:00

integration_test_client_side_tools.py

fix: override with client-side tools is overlapping (#8232)

2026-01-12 10:57:48 -08:00

integration_test_composio.py

chore: Remove test composio (#4914)

2025-10-07 17:50:46 -07:00

integration_test_conversations_sdk.py

feat: update compact endpoint to store summary message (#9215)

2026-02-24 10:52:06 -08:00

integration_test_human_in_the_loop.py

feat: dedupe approval response retries on server (#9038)

2026-01-29 12:44:04 -08:00

integration_test_mcp.py

chore: bump wait_for_server from 30 to 60 seconds (#8435)

2026-01-12 10:57:49 -08:00

integration_test_modal_sandbox_v2.py

feat: pass in LETTA_TOOL_ID, LETTA_AGENT_ID, LETTA_PROJECT_ID into tool env (#6439)

2025-12-15 12:02:18 -08:00

integration_test_modal.py

fix: duplicate session commit in step logging (#7512)

2026-01-12 10:57:19 -08:00

integration_test_multi_agent.py

chore: bump wait_for_server from 30 to 60 seconds (#8435)

2026-01-12 10:57:49 -08:00

integration_test_multi_modal_tool_returns.py

feat(core): add image support in tool returns [LET-7140] (#8985)

2026-01-29 12:43:53 -08:00

integration_test_override_model.py

feat: add override_model to message endpoints (#8763)

2026-01-19 15:54:42 -08:00

integration_test_send_message_v2.py

fix: revert test comments (#9161)

2026-01-29 12:44:04 -08:00

integration_test_send_message.py

feat: add MiniMax provider support (#9095)

2026-01-29 12:44:04 -08:00

integration_test_sleeptime_agent.py

chore: bump wait_for_server from 30 to 60 seconds (#8435)

2026-01-12 10:57:49 -08:00

integration_test_summarizer.py

feat: add compaction stats (#9219)

2026-02-24 10:52:06 -08:00

integration_test_token_counters.py

fix: duplicate session commit in step logging (#7512)

2026-01-12 10:57:19 -08:00

integration_test_tool_execution_sandbox.py

fix: duplicate session commit in step logging (#7512)

2026-01-12 10:57:19 -08:00

integration_test_turbopuffer.py

fix: conversation id not found in tpuf (#8469)

2026-01-12 10:57:49 -08:00

integration_test_typescript_tool_execution_sandbox.py

feat: add TypeScript tool support for E2B sandbox execution (#8796)

2026-01-19 15:54:43 -08:00

integration_test_usage_tracking.py

feat: add tracking of advanced usage data (eg caching) [LET-6372] (#6449)

2025-12-15 12:02:19 -08:00

integration_test_voice_agent.py

feat: patch model listing to actually match handle [LET-5888] (#5754)

2025-11-13 15:35:34 -08:00

locust_test.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

manual_test_many_messages.py

fix: remove letta-free embeddings from testing (#6870)

2025-12-15 12:03:09 -08:00

manual_test_multi_agent_broadcast_large.py

fix: remove letta-free embeddings from testing (#6870)

2025-12-15 12:03:09 -08:00

mcp_test.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

mock_mcp_server.py

fix: fix mcp for complex schemas and add tests (#5063)

2025-10-07 17:50:48 -07:00

pytest.ini

feat: modal tool execution - NO FEATURE FLAGS USES MODAL [LET-4357] (#5120)

2025-11-13 15:36:56 -08:00

test_agent_serialization_v2.py

feat: add override_model support for agent file import (#9058)

2026-01-29 12:44:04 -08:00

test_agent_serialization.py

chore: bump wait_for_server from 30 to 60 seconds (#8435)

2026-01-12 10:57:49 -08:00

test_cli.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

test_client.py

Shelley/let 7155 favorites tagged should be user scoped [LET-7155] (#9003)

2026-01-29 12:43:53 -08:00

test_crypto_utils.py

chore: add comment and test for changing PBKDF2 iteration count (#8366)

2026-01-12 10:57:48 -08:00

test_embedding_optional.py

fix: don't need embedding model for self hosted [LET-7009] (#8935)

2026-01-29 12:44:04 -08:00

test_embeddings.py

fix: truncate oversized text in embedding requests (#9196)

2026-02-24 10:52:06 -08:00

test_exception_logging.py

feat: global exception middleware (#6017)

2025-11-13 15:36:55 -08:00

test_file_processor.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

test_google_embeddings.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

test_internal_agents_count.py

Shub/let 6339 add endpoint for counting non hidden agents [LET-6339] (#6406)

2025-11-26 14:39:40 -08:00

test_letta_agent_batch.py

fix: remove letta-free embeddings from testing (#6870)

2025-12-15 12:03:09 -08:00

test_letta_request_schema.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

test_llm_clients.py

fix: anthropic message packing bugs (#9017)

2026-01-29 12:44:04 -08:00

test_log_context_middleware.py

feat: global exception middleware (#6017)

2025-11-13 15:36:55 -08:00

test_log_context.py

feat(logs): Enrich logs with context-aware primtive types (#5949)

2025-11-13 15:36:55 -08:00

test_long_running_agents.py

chore: bump wait_for_server from 30 to 60 seconds (#8435)

2026-01-12 10:57:49 -08:00

test_managers.py

chore: Remove test managers (#4926)

2025-10-07 17:50:46 -07:00

test_mcp_encryption.py

fix: duplicate session commit in step logging (#7512)

2026-01-12 10:57:19 -08:00

test_memory.py

feat: match line number rendering to Anthropic / OAI defaults (#5492)

2025-10-24 15:13:15 -07:00

test_message_serialization.py

Revert "fix: filter orphaned approval_request messages to prevent Anthropic API errors" (#8721)

2026-01-19 15:54:39 -08:00

test_minimax_client.py

feat: add MiniMax provider support (#9095)

2026-01-29 12:44:04 -08:00

test_modal_sandbox_v2.py

feat: pass in LETTA_TOOL_ID, LETTA_AGENT_ID, LETTA_PROJECT_ID into tool env (#6439)

2025-12-15 12:02:18 -08:00

test_multi_agent.py

fix: Fix multi agent test (#4947)

2025-10-07 17:50:46 -07:00

test_optimistic_json_parser.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

test_otel_tracing.py

fix: prevent huge otel spans causing pods to be OOMKilled (#5871)

2025-11-13 15:36:20 -08:00

test_plugins.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

test_prompt_caching.py

fix: patch counting of tokens for anthropic (#6458)

2025-12-15 12:02:19 -08:00

test_provider_api.py

feat: allow suers to test their own key [LET-5312] (#5257)

2025-10-09 13:20:53 -07:00

test_provider_trace_agents.py

feat(tests): add crouton telemetry tests (#9000)

2026-01-29 12:43:53 -08:00

test_provider_trace_backends.py

feat(crouton): add orgId, userId, Compaction_Settings and LLM_Config (#9022)

2026-01-29 12:44:04 -08:00

test_provider_trace_summarization.py

feat(tests): add crouton telemetry tests (#9000)

2026-01-29 12:43:53 -08:00

test_provider_trace.py

feat(tests): add crouton telemetry tests (#9000)

2026-01-29 12:43:53 -08:00

test_providers.py

feat: add minimax byok to ui (#9101)

2026-01-29 12:44:04 -08:00

test_redis_client.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

test_run_status_conversion.py

feat: add status to runs api [PRO-1529] (#5214)

2025-10-07 17:50:50 -07:00

test_schema_validator.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

test_sdk_client.py

Revert "Revert "feat: enable provider models persistence" (#6590)" (#6595)

2026-01-12 10:57:48 -08:00

test_secret.py

fix: asyncify encrypt on write (#8339)

2026-01-12 10:57:48 -08:00

test_server_providers.py

fix(sec): first pass of ensuring actor id is required everywhere (#9126)

2026-01-29 12:44:04 -08:00

test_server.py

chore: add back test_server.py (#5783)

2025-11-13 15:36:00 -08:00

test_sonnet_nonnative_reasoning_buffering.py

fix: remove letta-free embeddings from testing (#6870)

2025-12-15 12:03:09 -08:00

test_sources.py

fix: don't need embedding model for self hosted [LET-7009] (#8935)

2026-01-29 12:44:04 -08:00

test_static_buffer_summarize.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

test_stream_buffer_readers.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

test_temporal_metrics_local.py

feat(metrics): Surface custom metrics for temporal workflows and workers (#5951)

2025-11-13 15:36:55 -08:00

test_timezone_formatting.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

test_tool_rule_solver.py

feat: Implement child tool rules args override [LET-4570] (#5060)

2025-10-07 17:50:48 -07:00

test_tool_schema_parsing.py

fix: refactor enable strict mode for structured output (#8840)

2026-01-19 15:54:42 -08:00

test_usage_parsing.py

refactor: add extract_usage_statistics returning LettaUsageStatistics (#9065)

2026-01-29 12:44:04 -08:00

test_utils.py

feat: add user id validation (#9128)

2026-01-29 12:44:04 -08:00

utils.py

feat: cutover repo to 1.0 sdk client LET-6256 (#6361)

2025-11-24 19:11:18 -08:00