v0.7.51: hybrid search for knowledgebases, ui improvements, db perf improvements, claude managed agents tools, realtime files and tables

.devcontainer/docker-compose.yml

@@ -19,6 +19,7 @@ services:
       - BETTER_AUTH_SECRET=${BETTER_AUTH_SECRET:-your_auth_secret_here}
       - ENCRYPTION_KEY=${ENCRYPTION_KEY:-your_encryption_key_here}
       - COPILOT_API_KEY=${COPILOT_API_KEY}
+      - NEXT_PUBLIC_CHAT_DISABLED=${NEXT_PUBLIC_CHAT_DISABLED:-}
       - SIM_AGENT_API_URL=${SIM_AGENT_API_URL}
       - OLLAMA_URL=${OLLAMA_URL:-http://localhost:11434}
       - NEXT_PUBLIC_SOCKET_URL=${NEXT_PUBLIC_SOCKET_URL:-}

.github/workflows/ci.yml

@@ -252,7 +252,7 @@ jobs:
             echo "ERROR: DEV_TRIGGER_ACCESS_TOKEN and TRIGGER_PROJECT_ID repo secrets must both be set" >&2
             exit 1
           fi
-          bunx trigger.dev@4.4.3 deploy --env preview --branch dev-sim
+          bunx trigger.dev@4.5.7 deploy --env preview --branch dev-sim
 
   # Main/staging: build AMD64 images and push sha-tagged images to ECR + GHCR.
   # Runs in parallel with tests — only immutable sha tags are pushed here, and

apps/docs/content/docs/en/integrations/knowledge.mdx

@@ -43,6 +43,7 @@ Search for similar content in a knowledge base using vector similarity
 | `query` | string | No | Search query text \(optional when using tag filters\) |
 | `topK` | number | No | Number of most similar results to return \(1-100\) |
 | `tagFilters` | array | No | Array of tag filters with tagName and tagValue properties |
+| `searchMode` | string | No | Retrieval mode: 'vector' \(default\) uses semantic similarity only, 'hybrid' also runs a full-text leg and fuses both |
 | `rerankerEnabled` | boolean | No | Whether to apply Cohere reranking to vector search results |
 | `rerankerModel` | string | No | Cohere rerank model to use \(one of: rerank-v4.0-pro, rerank-v4.0-fast, rerank-v3.5\) |
 | `rerankerInputCount` | number | No | Number of vector results sent to the Cohere reranker \(1–100\). Defaults to topK × 4 capped at 100. |

apps/docs/content/docs/en/integrations/managed_agent.mdx

@@ -64,4 +64,200 @@ Open a Claude Platform Managed Agent session and return the assistant response a
 | `inputTokens` | number | Cumulative input tokens for the session. |
 | `outputTokens` | number | Cumulative output tokens for the session. |
 
+### `managed_agent_create_session`
+
+Create a Claude Platform Managed Agent session and return its id without waiting for a reply.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+| `agent` | string | Yes | Managed-agent id inside the linked Claude workspace. |
+| `environment` | string | Yes | Environment id inside the linked Claude workspace. |
+| `environmentType` | string | No | Environment execution model hint \('cloud' \| 'self_hosted'\). |
+| `userMessage` | string | No | Optional first message; seeds initial_events and starts the agent immediately. |
+| `vaults` | array | No | Zero or more vault ids for MCP tool auth. |
+| `vaultsAck` | boolean | No | Acknowledgement that the author may use the attached vaults. |
+| `memoryStoreId` | string | No | Optional Agent Memory Store id. |
+| `memoryAccess` | string | No | Memory store access mode: 'read_write' \(default\) or 'read_only'. |
+| `memoryInstructions` | string | No | Per-attachment guidance for how the agent should use the memory store. |
+| `files` | array | No | File attachments \(cloud envs only\), as \[\{fileId, mountPath?\}\]. |
+| `sessionParameters` | object | No | Key/value session metadata forwarded to the session. |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | Anthropic session id \(sesn_...\). |
+| `started` | boolean | True when a first message was seeded, so the agent is already running. |
+
+### `managed_agent_send_message`
+
+Send a user message to an existing Claude Platform Managed Agent session.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+| `userMessage` | string | Yes | The user message to send to the session. |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session the message was sent to. |
+| `sent` | boolean | True when the event was accepted by the API. |
+
+### `managed_agent_get_session`
+
+Read a Managed Agent session: status, stop reason, token usage, metadata, and any tool calls awaiting approval.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session that was read. |
+| `status` | string | Session status — 'idle', 'running', 'rescheduling', or 'terminated'. |
+| `stopReason` | string | Why the session last stopped, e.g. 'end_turn' or 'requires_action'. |
+| `requiresAction` | boolean | True when the session is waiting on a tool confirmation or custom tool result. If this is true while pendingTools is empty, the session is blocked but the API named no blocking events — surface it rather than treating the session as done. |
+| `pendingTools` | json | Blocking tool calls — \[\{id, eventType, kind, name, input\}\]. Route by kind: 'confirmation' ids go to Respond To Tool Confirmation, 'custom_tool_result' ids go to Respond To Custom Tool. |
+| `metadata` | json | Session metadata. |
+| `title` | string | Session title. |
+| `inputTokens` | number | Cumulative input tokens. |
+| `outputTokens` | number | Cumulative output tokens. |
+
+### `managed_agent_list_events`
+
+Read a Managed Agent session's event history and the agent's reply text.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+| `eventTypes` | array | No | Optional event-type filter, e.g. \['agent.message'\]. Omit to return every event. |
+| `limit` | number | No | Maximum events to return, keeping the most recent \(default 500\). |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session that was read. |
+| `events` | json | Session events, oldest first. |
+| `count` | number | Number of events returned. |
+| `assistantText` | string | Concatenated text of every persisted agent.message, in order. |
+| `truncated` | boolean | True when the limit was hit and older events were dropped. |
+
+### `managed_agent_update_session`
+
+Update a Managed Agent session's title or metadata.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+| `title` | string | No | New session title. |
+| `sessionParameters` | object | No | Replacement metadata map \(replaces all stored metadata, not merged\). Leaving it empty leaves the stored metadata unchanged — use clearMetadata to remove it. |
+| `clearMetadata` | boolean | No | Removes all of the session's stored metadata. Overrides any map supplied above. |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session that was updated. |
+| `updated` | boolean | True when the update was accepted. |
+| `metadata` | json | Metadata after the update. |
+| `title` | string | Title after the update. |
+
+### `managed_agent_interrupt_session`
+
+Stop a running Managed Agent session; it stays usable afterwards.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session that was interrupted. |
+| `interrupted` | boolean | True when the interrupt was accepted. |
+
+### `managed_agent_respond_tool_confirmation`
+
+Allow or deny the tool calls a Managed Agent session is waiting on before it can continue.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+| `toolUseIds` | array | Yes | Blocking tool-use EVENT ids, from Get Session pendingTools\[\].id where kind is 'confirmation' \(not toolu_ ids\). |
+| `decision` | string | Yes | 'allow' to let the tools run, or 'deny' to reject them. |
+| `denyMessage` | string | No | Reason surfaced to the agent. Only sent when the decision is deny. |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session that was answered. |
+| `decision` | string | The decision applied — 'allow' or 'deny'. |
+| `confirmedToolUseIds` | json | The tool-use event ids that were answered. |
+
+### `managed_agent_respond_custom_tool`
+
+Return the result of a custom tool a Managed Agent session is waiting on so it can continue.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+| `customToolUseId` | string | Yes | The custom tool-use EVENT id being answered, from Get Session pendingTools\[\].id where kind is 'custom_tool_result'. |
+| `result` | string | Yes | The tool's output, returned to the agent as text. |
+| `isError` | boolean | No | Mark the result as a failure so the agent can adjust its approach. |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session that was answered. |
+| `answeredToolUseId` | string | The custom tool-use event id that was answered. |
+
+### `managed_agent_archive_session`
+
+Archive a Managed Agent session, preserving its history. Not reversible.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session that was archived. |
+| `archived` | boolean | True when the archive was accepted. |
+
+### `managed_agent_delete_session`
+
+Permanently delete a Managed Agent session, its events, and its sandbox. Not reversible.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session that was deleted. |
+| `deleted` | boolean | True when the delete was accepted. |
+
 

apps/docs/content/docs/en/knowledgebase/using-in-workflows.mdx

@@ -37,6 +37,19 @@ In our example, adding `Department equals "Billing"` makes the search consider o
 
 Filters run before the vector comparison, so they make a search both more precise and cheaper. See [Tags and filtering](/knowledgebase/tags) for the full operator list by tag type.
 
+## Retrieval Mode
+
+**Retrieval Mode** is an advanced setting that chooses how matches are found.
+
+| Mode | What it does |
+| --- | --- |
+| Vector only | The default. Ranks purely on meaning, as described above. |
+| Hybrid | Also runs a keyword search over the same chunks and blends the two rankings. |
+
+Semantic search is strong on paraphrase and weak on literal strings: an error code, a ticket key like `PROJ-1234`, a SKU, or a rare product name carries little meaning for the model, so the chunk containing it may not rank near the top. Hybrid adds a keyword pass that matches those tokens exactly, then merges the two lists so a chunk found by either signal can surface.
+
+Turn it on when your documents are full of identifiers, codes, or names people search for verbatim. Leave it off for prose-heavy bases where questions are asked in natural language. Hybrid costs no extra API calls — the keyword pass runs entirely in the database.
+
 ## Rerank Results
 
 **Rerank Results** is an optional second pass. Vector search ranks by raw similarity; reranking re-scores the top matches with a dedicated relevance model (Cohere's rerank models) and reorders them, which sharpens the ordering when the best answer isn't the literal closest vector.
@@ -95,6 +108,7 @@ When the agent's answer is off, the cause is usually in retrieval, not the agent
 - **No results, or wrong documents.** A tag filter may be excluding what you want, or the documents may not be indexed yet. A document is only searchable once its processing status is `completed`; while it is `pending`, `processing`, or `failed`, its chunks won't appear.
 - **Low similarity scores across the board.** The query is too vague, or the information simply isn't in the base. Rewrite the query to match how the documents phrase things.
 - **Right documents, wrong order.** Turn on Rerank Results, or raise Number of Results so the relevant chunk is included.
+- **An exact code, ID, or name isn't found.** Switch Retrieval Mode to Hybrid so a keyword pass runs alongside the semantic one.
 
 See [debugging retrieval](/knowledgebase/debugging-retrieval) for the full diagnostic path, and [chunking strategies](/knowledgebase/chunking-strategies) for how chunk boundaries shape what a search can return.
 

apps/docs/content/docs/en/platform/self-hosting/environment-variables.mdx

@@ -64,7 +64,8 @@ import { Callout } from 'fumadocs-ui/components/callout'
 | Variable | Description |
 |----------|-------------|
 | `API_ENCRYPTION_KEY` | Encrypts stored API keys (32 hex chars): `openssl rand -hex 32` |
-| `COPILOT_API_KEY` | API key for copilot features |
+| `COPILOT_API_KEY` | API key for Chat. Without it the Sim Chat block, scheduled prompt jobs, and Inbox cannot run |
+| `NEXT_PUBLIC_CHAT_DISABLED` | Set to `true` to hide the Chat module: the workspace lands on your first workflow, with no chats list, scheduled tasks, or editor Chat panel. Chat is shown when unset; `bun run setup` sets it for you if you skip the chat key |
 | `ADMIN_API_KEY` | Admin API key for GitOps operations |
 | `ALLOWED_LOGIN_DOMAINS` | Restrict signups to domains (comma-separated) |
 | `ALLOWED_LOGIN_EMAILS` | Restrict signups to specific emails (comma-separated) |

apps/docs/content/docs/en/workflows/blocks/pi.mdx

@@ -211,7 +211,7 @@ The one case neither layer can rescue is a *first* prompt that already exceeds t
 
 ### Create PR [#setup-cloud-pr]
 
-Create PR runs in a sandbox image with the Pi CLI and git baked in.
+Create PR runs in a sandbox image with the Pi CLI, Git, Node.js, and Bun baked in. Repository dependencies are not preinstalled; Pi can run `bun install` when a repository needs them.
 
 1. **Enable sandbox execution.** On self-hosted Sim, set `E2B_ENABLED=true`, `E2B_API_KEY`, `E2B_PI_TEMPLATE_ID` (the Pi template id), and `NEXT_PUBLIC_E2B_ENABLED=true` (this reveals Create PR, Update PR, and Review Code in the UI). Build the template with `bun run apps/sim/scripts/build-pi-e2b-template.ts`. These modes stay hidden until `NEXT_PUBLIC_E2B_ENABLED` is set.
 

apps/docs/openapi.json

@@ -6040,7 +6040,7 @@
       "post": {
         "operationId": "searchKnowledgeBase",
         "summary": "Search Knowledge Base",
-        "description": "Perform vector similarity search across one or more knowledge bases. Supports semantic search via query text, tag-based filtering, or a combination of both.",
+        "description": "Search across one or more knowledge bases. Supports semantic search via query text, tag-based filtering, or a combination of both. Set `searchMode` to `hybrid` to additionally run a full-text keyword leg and fuse it with the semantic results.",
         "tags": ["Knowledge Bases"],
         "x-codeSamples": [
           {
@@ -6095,14 +6095,21 @@
                     "items": {
                       "$ref": "#/components/schemas/TagFilter"
                     }
+                  },
+                  "searchMode": {
+                    "type": "string",
+                    "enum": ["vector", "hybrid"],
+                    "default": "vector",
+                    "description": "Retrieval strategy. `vector` ranks purely on embedding similarity. `hybrid` also runs a full-text keyword search and fuses the two rankings by reciprocal rank, which retrieves exact tokens — error codes, ticket keys, identifiers, rare product names — that embeddings alone rank poorly. Ignored when only tagFilters are provided."
                   }
                 }
               },
               "example": {
                 "workspaceId": "wsp_abc123",
                 "knowledgeBaseIds": ["d2c8f4a6-1b3e-4c5d-9e7f-8a0b2c4d6e1f"],
                 "query": "How do I reset my password?",
-                "topK": 5
+                "topK": 5,
+                "searchMode": "hybrid"
               }
             }
           }

apps/realtime/package.json

@@ -33,9 +33,12 @@
     "@sim/workflow-types": "workspace:*",
     "@socket.io/redis-adapter": "8.3.0",
     "drizzle-orm": "^0.45.2",
+    "lib0": "0.2.117",
     "postgres": "^3.4.5",
     "redis": "5.10.0",
     "socket.io": "^4.8.1",
+    "y-protocols": "1.0.7",
+    "yjs": "13.6.31",
     "zod": "4.3.6"
   },
   "devDependencies": {