Fimeg/letta-server
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix: warning (#9179)

Browse Source 
* fix: warning

* just stage publish api

* note

* api
This commit is contained in:
Ari Webb
2026-01-29 14:17:20 -08:00
committed by Caren Thomas
parent 65dbd7fd89
commit 7b0b1f2531
2 changed files with 15 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
fern/openapi.json
View File

@@ -7635,7 +7635,7 @@
"post": {
"tags": ["agents"],
"summary": "Send Message",
"description": "Process a user message and return the agent's response.\nThis endpoint accepts a message from a user and processes it through the agent.\n\nThe response format is controlled by the `streaming` field in the request body:\n- If `streaming=false` (default): Returns a complete LettaResponse with all messages\n- If `streaming=true`: Returns a Server-Sent Events (SSE) stream\n\nAdditional streaming options (only used when streaming=true):\n- `stream_tokens`: Stream individual tokens instead of complete steps\n- `include_pings`: Include keepalive pings to prevent connection timeouts\n- `background`: Process the request in the background",
"description": "Process a user message and return the agent's response.\nThis endpoint accepts a message from a user and processes it through the agent.\n\n**Note:** Sending multiple concurrent requests to the same agent can lead to undefined behavior.\nEach agent processes messages sequentially, and concurrent requests may interleave in unexpected ways.\nWait for each request to complete before sending the next one. Use separate agents or conversations for parallel processing.\n\nThe response format is controlled by the `streaming` field in the request body:\n- If `streaming=false` (default): Returns a complete LettaResponse with all messages\n- If `streaming=true`: Returns a Server-Sent Events (SSE) stream\n\nAdditional streaming options (only used when streaming=true):\n- `stream_tokens`: Stream individual tokens instead of complete steps\n- `include_pings`: Include keepalive pings to prevent connection timeouts\n- `background`: Process the request in the background",
"operationId": "send_message",
"parameters": [
{
@@ -7832,7 +7832,7 @@
"post": {
"tags": ["agents"],
"summary": "Send Message Streaming",
"description": "Process a user message and return the agent's response.\n\nDeprecated: Use the `POST /{agent_id}/messages` endpoint with `streaming=true` in the request body instead.\n\nThis endpoint accepts a message from a user and processes it through the agent.\nIt will stream the steps of the response always, and stream the tokens if 'stream_tokens' is set to True.",
"description": "Process a user message and return the agent's response.\n\nDeprecated: Use the `POST /{agent_id}/messages` endpoint with `streaming=true` in the request body instead.\n\n**Note:** Sending multiple concurrent requests to the same agent can lead to undefined behavior.\nEach agent processes messages sequentially, and concurrent requests may interleave in unexpected ways.\nWait for each request to complete before sending the next one. Use separate agents or conversations for parallel processing.\n\nThis endpoint accepts a message from a user and processes it through the agent.\nIt will stream the steps of the response always, and stream the tokens if 'stream_tokens' is set to True.",
"operationId": "create_agent_message_stream",
"deprecated": true,
"parameters": [
@@ -7996,7 +7996,7 @@
"post": {
"tags": ["agents"],
"summary": "Send Message Async",
"description": "Asynchronously process a user message and return a run object.\nThe actual processing happens in the background, and the status can be checked using the run ID.\n\nThis is \"asynchronous\" in the sense that it's a background run and explicitly must be fetched by the run ID.",
"description": "Asynchronously process a user message and return a run object.\nThe actual processing happens in the background, and the status can be checked using the run ID.\n\nThis is \"asynchronous\" in the sense that it's a background run and explicitly must be fetched by the run ID.\n\n**Note:** Sending multiple concurrent requests to the same agent can lead to undefined behavior.\nEach agent processes messages sequentially, and concurrent requests may interleave in unexpected ways.\nWait for each request to complete before sending the next one. Use separate agents or conversations for parallel processing.",
"operationId": "create_agent_message_async",
"parameters": [
{