* Add log probabilities support for RL training
This enables Letta server to request and return log probabilities from
OpenAI-compatible providers (including SGLang) for use in RL training.
Changes:
- LLMConfig: Add return_logprobs and top_logprobs fields
- OpenAIClient: Set logprobs in ChatCompletionRequest when enabled
- LettaLLMAdapter: Add logprobs field and extract from response
- LettaResponse: Add logprobs field to return log probs to client
- LettaRequest: Add return_logprobs/top_logprobs for per-request override
- LettaAgentV3: Store and pass logprobs through to response
- agents.py: Handle request-level logprobs override
Usage:
response = client.agents.messages.create(
agent_id=agent_id,
messages=[...],
return_logprobs=True,
top_logprobs=5,
)
print(response.logprobs) # Per-token log probabilities
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* Add multi-turn token tracking for RL training via SGLang native endpoint
- Add TurnTokenData schema to track token IDs and logprobs per turn
- Add return_token_ids flag to LettaRequest and LLMConfig
- Create SGLangNativeClient for /generate endpoint (returns output_ids)
- Create SGLangNativeAdapter that uses native endpoint
- Modify LettaAgentV3 to accumulate turns across LLM calls
- Include turns in LettaResponse when return_token_ids=True
* Fix: Add SGLang native adapter to step() method, not just stream()
* Fix: Handle Pydantic Message objects in SGLang native adapter
* Fix: Remove api_key reference from LLMConfig (not present)
* Fix: Add missing 'created' field to ChatCompletionResponse
* Add full tool support to SGLang native adapter
- Format tools into prompt in Qwen-style format
- Parse tool calls from <tool_call> tags in response
- Format tool results as <tool_response> in user messages
- Set finish_reason to 'tool_calls' when tools are called
* Use tokenizer.apply_chat_template for proper tool formatting
- Add tokenizer caching in SGLang native adapter
- Use apply_chat_template when tokenizer available
- Fall back to manual formatting if not
- Convert Letta messages to OpenAI format for tokenizer
* Fix: Use func_response instead of tool_return for ToolReturn content
* Fix: Get output_token_logprobs from meta_info in SGLang response
* Fix: Allow None in output_token_logprobs (SGLang format includes null)
* chore: remove unrelated files from logprobs branch
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix: add missing call_type param to adapter constructors in letta_agent_v3
The SGLang refactor dropped call_type=LLMCallType.agent_step when extracting
adapter creation into conditional blocks. Restores it for all 3 spots (SGLang
in step, SimpleLLM in step, SGLang in stream).
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* just stage-api && just publish-api
* fix: update expected LLMConfig fields in schema test for logprobs support
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* chore: remove rllm provider references
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* just stage-api && just publish-api
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
---------
Co-authored-by: Ubuntu <ubuntu@ip-172-31-65-206.ec2.internal>
Co-authored-by: Letta <noreply@letta.com>
* refactor: extract compact logic to shared function
Extract the compaction logic from LettaAgentV3.compact() into a
standalone compact_messages() function that can be shared between
the agent and temporal workflows.
Changes:
- Create apps/core/letta/services/summarizer/compact.py with:
- compact_messages(): Core compaction logic
- build_summarizer_llm_config(): LLM config builder for summarization
- CompactResult: Dataclass for compaction results
- Update LettaAgentV3.compact() to use compact_messages()
- Update temporal summarize_conversation_history activity to use
compact_messages() instead of the old Summarizer class
- Add use_summary_role parameter to SummarizeParams
This ensures consistent summarization behavior across different
execution paths and prevents drift as we improve the implementation.
* chore: clean up verbose comments
* fix: correct CompactionSettings import path
* fix: correct count_tokens import from summarizer_sliding_window
* fix: update test patch path for count_tokens_with_tools
After extracting compact logic to compact.py, the test was patching
the old location. Update the patch path to the new module location.
* fix: update test to use build_summarizer_llm_config from compact.py
The function was moved from LettaAgentV3._build_summarizer_llm_config
to compact.py as a standalone function.
* fix: add early check for system prompt size in compact_messages
Check if the system prompt alone exceeds the context window before
attempting summarization. The system prompt cannot be compacted,
so fail fast with SystemPromptTokenExceededError.
* fix: properly propagate SystemPromptTokenExceededError from compact
The exception handler in _step() was not setting the correct stop_reason
for SystemPromptTokenExceededError, which caused the finally block to
return early and swallow the exception.
Add special handling to set stop_reason to context_window_overflow_in_system_prompt
when SystemPromptTokenExceededError is caught.
* revert: remove redundant SystemPromptTokenExceededError handling
The special handling in the outer exception handler is redundant because
stop_reason is already set in the inner handler at line 943. The actual
fix for the test was the early check in compact_messages(), not this
redundant handling.
* fix: correctly re-raise SystemPromptTokenExceededError
The inner exception handler was using 'raise e' which re-raised the outer
ContextWindowExceededError instead of the current SystemPromptTokenExceededError.
Changed to 'raise' to correctly re-raise the current exception. This bug
was pre-existing but masked because _check_for_system_prompt_overflow was
only called as a fallback. The new early check in compact_messages() exposed it.
* revert: remove early check and restore raise e to match main behavior
* fix: set should_continue=False and correctly re-raise exception
- Add should_continue=False in SystemPromptTokenExceededError handler (matching main's _check_for_system_prompt_overflow behavior)
- Fix raise e -> raise to correctly propagate SystemPromptTokenExceededError
Note: test_large_system_prompt_summarization still fails locally but passes on main.
Need to investigate why exception isn't propagating correctly on refactored branch.
* fix: add SystemPromptTokenExceededError handler for post-step compaction
The post-step compaction (line 1066) was missing a SystemPromptTokenExceededError
exception handler. When compact_messages() raised this error, it would be caught
by the outer exception handler which would:
1. Set stop_reason to "error" instead of "context_window_overflow_in_system_prompt"
2. Not set should_continue = False
3. Get swallowed by the finally block (line 1126) which returns early
This caused test_large_system_prompt_summarization to fail because the exception
never propagated to the test.
The fix adds the same exception handler pattern used in the retry compaction flow
(line 941-946), ensuring proper state is set before re-raising.
This issue only affected the refactored code because on main, _check_for_system_prompt_overflow()
was an instance method that set should_continue/stop_reason BEFORE raising. In the refactor,
compact_messages() is a standalone function that cannot set instance state, so the caller
must handle the exception and set the state.
* feat: add ID format validation to agent and user schemas
Reuse existing validator types (ToolId, SourceId, BlockId, MessageId,
IdentityId, UserId) from letta.validators to enforce ID format validation
at the schema level. This ensures malformed IDs are rejected with a 422
validation error instead of causing 500 database errors.
Changes:
- CreateAgent: validate tool_ids, source_ids, folder_ids, block_ids, identity_ids
- UpdateAgent: validate tool_ids, source_ids, folder_ids, block_ids, message_ids, identity_ids
- UserUpdate: validate id
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* chore: regenerate API spec and SDK
* fix: override ID validation in AgentSchema for agent file portability
AgentSchema extends CreateAgent but needs to allow arbitrary short IDs
(e.g., tool-0, block-0) for portable agent files. Override the validated
ID fields to use plain List[str] instead of the validated types.
Also fix test_agent.af to use proper UUID-format IDs.
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* chore: regenerate API spec and SDK
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix: revert test_agent.af - short IDs are valid for agent files
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix openapi schema
---------
Co-authored-by: Letta <noreply@letta.com>
fix: load default provider config when summarizer uses different provider
**Problem:**
Summarization failed when agent used one provider (e.g., Google AI) but
summarizer config specified a different provider (e.g., Anthropic):
```python
# Agent LLM config
model_endpoint_type='google_ai', handle='gemini-something/gemini-2.5-pro',
context_window=100000
# Summarizer config
model='anthropic/claude-haiku-4-5-20251001'
# Bug: Resulting summarizer_llm_config mixed Google + Anthropic settings
model='claude-haiku-4-5-20251001', model_endpoint_type='google_ai', # ❌ Wrong endpoint!
context_window=100000 # ❌ Google's context window, not Anthropic's default!
```
This sent Claude requests to Google AI endpoints with incorrect parameters.
**Root Cause:**
`_build_summarizer_llm_config()` always copied the agent's LLM config as base,
then patched model/provider fields. But this kept all provider-specific settings
(endpoint, context_window, etc.) from the wrong provider.
**Fix:**
1. Parse provider_name from summarizer handle
2. Check if it matches agent's model_endpoint_type (or provider_name for custom)
3. **If YES** → Use agent config as base, override model/handle (same provider)
4. **If NO** → Load default config via `provider_manager.get_llm_config_from_handle()` (new provider)
**Example Flow:**
```python
# Agent: google_ai/gemini-2.5-pro
# Summarizer: anthropic/claude-haiku
provider_name = "anthropic" # Parsed from handle
provider_matches = ("anthropic" == "google_ai") # False ❌
# Different provider → load default Anthropic config
base = await provider_manager.get_llm_config_from_handle(
handle="anthropic/claude-haiku",
actor=self.actor
)
# Returns: model_endpoint_type='anthropic', endpoint='https://api.anthropic.com', etc. ✅
```
**Result:**
- Summarizer with different provider gets correct default config
- No more mixing Google endpoints with Anthropic models
- Same-provider summarizers still inherit agent settings efficiently
👾 Generated with [Letta Code](https://letta.com)
Co-authored-by: Letta <noreply@letta.com>
* feat: add conversation_id parameter to context endpoint [LET-6989]
Add optional conversation_id query parameter to retrieve_agent_context_window.
When provided, the endpoint uses messages from the specific conversation
instead of the agent's default message_ids.
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* chore: regenerate SDK after context endpoint update [LET-6989]
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* feat: add isolated blocks support for conversations
Allows conversations to have their own copies of specific memory blocks (e.g., todo_list) that override agent defaults, enabling conversation-specific state isolation.
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* undo
* update apis
* test
* cleanup
* fix tests
* simplify
* move override logic
* patch
---------
Co-authored-by: Letta <noreply@letta.com>
* feat: add tags support to blocks
* fix: add timestamps and org scoping to blocks_tags
Addresses PR feedback:
1. Migration: Added timestamps (created_at, updated_at), soft delete
(is_deleted), audit fields (_created_by_id, _last_updated_by_id),
and organization_id to blocks_tags table for filtering support.
Follows SQLite baseline pattern (composite PK of block_id+tag, no
separate id column) to avoid insert failures.
2. ORM: Relationship already correct with lazy="raise" to prevent
implicit joins and passive_deletes=True for efficient CASCADE deletes.
3. Schema: Changed normalize_tags() from Any to dict for type safety.
4. SQLite: Added blocks_tags to SQLite baseline schema to prevent
table-not-found errors.
5. Code: Updated all tag row inserts to include organization_id.
🐾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix: add ORM columns and update SQLite baseline for blocks_tags
Fixes test failures (CompileError: Unconsumed column names: organization_id):
1. ORM: Added organization_id, timestamps, audit fields to BlocksTags
ORM model to match database schema from migrations.
2. SQLite baseline: Added full column set to blocks_tags (organization_id,
timestamps, audit fields) to match PostgreSQL schema.
3. Test: Added 'tags' to expected Block schema fields.
This ensures SQLite and PostgreSQL have matching schemas and the ORM
can consume all columns that the code inserts.
🐾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* revert change to existing alembic migration
* fix: remove passive_deletes and SQLite support for blocks_tags
1. Removed passive_deletes=True from Block.tags relationship to match
AgentsTags pattern (neither have ondelete CASCADE in DB schema).
2. Removed SQLite branch from _replace_block_pivot_rows_async since
blocks_tags table is PostgreSQL-only (migration skips SQLite).
🐾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* api sync
---------
Co-authored-by: Letta <noreply@letta.com>
* feat: Add conversation_id filtering to message list and search endpoints
Add optional conversation_id parameter to filter messages by conversation:
- client.agents.messages.list
- client.messages.list
- client.messages.search
Changes:
- Added conversation_id field to MessageSearchRequest and SearchAllMessagesRequest schemas
- Added conversation_id filtering to list_messages in message_manager.py
- Updated get_agent_recall_async and get_all_messages_recall_async in server.py
- Added conversation_id query parameter to router endpoints
- Updated Turbopuffer client to support conversation_id filtering in searches
Fixes#8320🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Charles Packer <cpacker@users.noreply.github.com>
* add conversation_id to message and tpuf
* default messages filter for backward compatibility
* add test and auto gen
* fix integration test
* fix test
* update test
---------
Co-authored-by: letta-code <248085862+letta-code@users.noreply.github.com>
Co-authored-by: Charles Packer <cpacker@users.noreply.github.com>
Co-authored-by: christinatong01 <christina@letta.com>
* feat: add message_types filter to list messages endpoint
Add the ability to filter messages by type when listing message history
via GET /v1/agents/{agent_id}/messages. This brings parity with the
create message endpoint which already supports include_return_message_types.
Changes:
- Add message_types query parameter to list_messages endpoint in agents.py
- Add message_types parameter to get_agent_recall_async in server.py
- Filter messages by message_type after LettaMessage conversion
- Add test for message_types filtering
Closes#8277
Written by Cameron ◯ Letta Code
> "Simplicity is the ultimate sophistication." - Leonardo da Vinci
🐙 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* chore: regenerate OpenAPI spec and SDK for message_types filter
🐧 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
Written by Cameron ◯ Letta Code
"The only way to do great work is to love what you do." - Steve Jobs
---------
Co-authored-by: Letta <noreply@letta.com>
* fix: prevent human block overwrite when skills block missing
**Bug**: When connecting to agents created before skills blocks were
standard, the human block gets overwritten with skills directory content.
**Root cause**: agent_manager.py:1893-1898 had `block = block` (no-op).
When skills block doesn't exist, loop variable ends as last block in
core_memory (often "human"), then updates that wrong block.
**Fix**: Use `matched_block` variable to properly track found block.
Now correctly raises NoResultFound when block label doesn't exist.
**Impact**: Affects pre-December 2025 agents missing skills blocks.
Written by Cameron ◯ Letta Code
"The best error message is the one that never shows up." - Thomas Fuchs
Co-Authored-By: Letta <noreply@letta.com>
* fix: use correct method name in block update test
Change get_block_by_label_async to get_block_with_label_async in test.
Written by Cameron ◯ Letta Code
Co-Authored-By: Letta <noreply@letta.com>
---------
Co-authored-by: Letta <noreply@letta.com>
* refactor: migrate mcp_servers and mcp_oauth to encrypted-only columns
Complete migration to encrypted-only storage for sensitive fields:
- Remove dual-write to plaintext columns (token, custom_headers,
authorization_code, access_token, refresh_token, client_secret)
- Read only from _enc columns, not from plaintext fallback
- Remove helper methods (get_token_secret, set_token_secret, etc.)
- Remove Secret.from_db() and Secret.to_dict() methods
- Update tests to verify encrypted-only behavior
After this change, plaintext columns can be set to NULL manually
since they are no longer read from or written to.
* fix test
* rename
* update
* union
* fix test
* initial commit
* Add database migration for compaction_settings field
This migration adds the compaction_settings column to the agents table
to support customized summarization configuration for each agent.
🐾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix
* rename
* update apis
* fix tests
* update web test
---------
Co-authored-by: Letta <noreply@letta.com>
Co-authored-by: Kian Jones <kian@letta.com>
Add tests to verify that providers work correctly when no encryption key
is configured. The Secret class stores values as plaintext in _enc columns
and retrieves them successfully, but this code path had no test coverage.
Co-authored-by: Letta Bot <noreply@letta.com>
* fix: replace all 'PRODUCTION' references with 'prod' for consistency
Problem: Codebase had 11 references to 'PRODUCTION' (uppercase) that should
use 'prod' (lowercase) for consistency with the deployment workflows and
environment normalization.
Changes across 8 files:
1. Source files (using settings.environment):
- letta/functions/function_sets/multi_agent.py
- letta/services/tool_manager.py
- letta/services/tool_executor/multi_agent_tool_executor.py
- letta/services/helpers/agent_manager_helper.py
All checks changed from: settings.environment == "PRODUCTION"
To: settings.environment == "prod"
2. OTEL resource configuration:
- letta/otel/resource.py
- Updated _normalize_environment_tag() to handle 'prod' directly
- Removed 'PRODUCTION' -> 'prod' mapping (no longer needed)
- Updated device.id check from _env != "PRODUCTION" to _env != "prod"
3. Test files:
- tests/managers/conftest.py
- Fixture parameter changed from "PRODUCTION" to "prod"
- tests/managers/test_agent_manager.py (3 occurrences)
- tests/managers/test_tool_manager.py (2 occurrences)
All test checks changed to use "prod"
Result: Complete consistency across the codebase:
- All environment checks use "prod" instead of "PRODUCTION"
- Normalization function simplified (no special case for PRODUCTION)
- Tests use correct "prod" value
- Matches deployment workflow configuration from PR #6626
This completes the environment naming standardization effort.
* fix: update settings.py environment description to use 'prod' instead of 'PRODUCTION'
The field description still referenced PRODUCTION as an example value.
Updated to use lowercase 'prod' for consistency with actual usage.
Before: "Application environment (PRODUCTION, DEV, CANARY, etc. - normalized to lowercase for OTEL tags)"
After: "Application environment (prod, dev, canary, etc. - lowercase values used for OTEL tags)"
* Revert "fix test"
This reverts commit 5126815f23cefb4edad3e3bf9e7083209dcc7bf1.
* fix server and better test
* test fix, get api key for base and byok?
* set letta default endpoint
* try to fix timeout for test
* fix for letta api key
* Delete apps/core/tests/sdk_v1/conftest.py
* Update utils.py
* clean up a few issues
* fix filterning on list_llm_models
* soft delete models with provider
* add one more test
* fix ci
* add timeout
* band aid for letta embedding provider
* info instead of error logs when creating models
* add regression test for dict content in AssistantMessage
Tests the fix for pydantic validation error when send_message tool
returns dict content like {'tofu': 1, 'mofu': 1, 'bofu': 1}.
The test verifies that dict content is properly serialized to JSON
string before creating AssistantMessage.
* improve type annotation for validate_function_response
Changed return type from Any to str | dict[str, Any] to match actual
behavior. This enables static type checkers (pyright, mypy) to catch
type mismatches like the AssistantMessage bug.
With proper type annotations, pyright would have caught:
error: Argument of type "str | dict[str, Any]" cannot be assigned
to parameter "content" of type "str"
This prevents future bugs where dict is passed to string-only fields.
* add regression test for dict content in AssistantMessage
Moved test into existing test_message_manager.py suite alongside other
message conversion tests.
Tests the fix for pydantic validation error when send_message tool
returns dict content like {'tofu': 1, 'mofu': 1, 'bofu': 1}.
The test verifies that dict content is properly serialized to JSON
string before creating AssistantMessage.
* fix: clear message history no longer deletes messages
* toast and make it stay for 8 secs
* fix test
---------
Co-authored-by: Ari Webb <ari@letta.com>
* first hack with test
* remove changes integration test
* Delete apps/core/tests/sdk_v1/integration/integration_test_send_message_v2.py
* add test
* remove comment
* stage and publish api
* deprecate base level response_schema
* add param to llm_config test
---------
Co-authored-by: Ari Webb <ari@letta.com>
