Get chat history for a conversation

One conversation with all its messages, plus the model, tokens, cost and the memory or compaction events it went through. 404 when the conversation does not exist or belongs to another assistant.

GET /v1/assistants/{identifier}/chats/{chatUid}

Get chat history for a conversation

cURL

curl --request GET \
  --url https://api.devic.ai/v1/assistants/{identifier}/chats/{chatUid} \
  --header 'Authorization: Bearer <token>'

200

{
  "chatUID": "550e8400-e29b-41d4-a716-446655440000",
  "clientUID": "f9a44905-3193-4bd2-a81a-71156aa7eb66",
  "userUID": "7a735eda-69e7-420b-9507-6abf80ad2e34",
  "name": "Solar panel recommendations",
  "archived": true,
  "assistantSpecializationIdentifier": "550e8400-e29b-41d4-a716-446655440000",
  "chatContent": [
    {
      "uid": "75ecbcfc-a3be-43ba-8da6-b3e16e8d7280",
      "chatUid": "550e8400-e29b-41d4-a716-446655440000",
      "role": "user",
      "content": {
        "message": "I would recommend a 450 W monocrystalline panel.",
        "data": {},
        "files": [
          {
            "name": "invoice.pdf",
            "donwloadUrl": "https://files.devic.ai/uploads/invoice.pdf",
            "fileType": "DOCUMENT"
          }
        ]
      },
      "timestamp": 1706000000000,
      "userUID": "api-key:42",
      "summary": "The user asks which panels to install on a 60 m2 roof.",
      "contentSource": "finish_tool",
      "tool_calls": [
        {
          "id": "call_abc123",
          "type": "function",
          "function": {
            "name": "get_user_location",
            "arguments": "{}"
          }
        }
      ],
      "tool_call_id": "call_abc123",
      "latencyMs": 1045,
      "messageTokenUsage": {
        "inputTokens": 123,
        "outputTokens": 123,
        "inputCachedTokens": 123,
        "inputCacheWriteTokens": 123,
        "outputCachedTokens": 123,
        "reasoningOutputTokens": 123,
        "totalTokens": 123,
        "provider": "<string>",
        "model": "<string>",
        "reasoningEffort": "none"
      },
      "messageCost": {
        "inputCost": 123,
        "outputCost": 123,
        "inputCachedCost": 123,
        "inputCacheWriteCost": 123,
        "outputCachedCost": 123,
        "reasoningOutputCost": 123,
        "totalCost": 123,
        "currency": "USD",
        "calculatedAt": 123
      }
    }
  ],
  "creationTimestampMs": 1789630543006,
  "lastEditTimestampMs": 1789630572077,
  "llm": "gpt-4.1",
  "provider": "open-ai",
  "contextWindow": 1050000,
  "inputTokens": 6380,
  "outputTokens": 372,
  "tokenUsage": {
    "model": "<string>",
    "provider": "<string>",
    "inputTokens": 123,
    "outputTokens": 123,
    "inputCachedTokens": 123,
    "inputCacheWriteTokens": 123,
    "outputCachedTokens": 123,
    "reasoningOutputTokens": 123,
    "totalCachedTokens": 123,
    "cost": {
      "inputCost": 123,
      "outputCost": 123,
      "inputCachedCost": 123,
      "inputCacheWriteCost": 123,
      "outputCachedCost": 123,
      "reasoningOutputCost": 123,
      "totalCost": 123
    },
    "secondaryCost": 123,
    "secondaryInputTokens": 123,
    "secondaryOutputTokens": 123,
    "secondaryByOperation": {},
    "pricingTimestamp": 123
  },
  "metadata": {},
  "tenantId": "tenant_12345",
  "tags": [
    "support",
    "onboarding"
  ],
  "stopReason": "max_chat_messages_reached",
  "triggerSource": {},
  "guardrailResults": {},
  "handedOff": true,
  "handedOffSubThreadId": "64f5a5b8c123456789abcdef",
  "pausedUntil": 123,
  "pausedReason": "<string>",
  "recalledMemories": [
    {}
  ],
  "coreMemories": [
    {}
  ],
  "compactions": [
    {}
  ],
  "reasoningEffort": "none",
  "effectiveReasoningEffort": "none"
}

Authorizations

Authorization · string · header · required

An API key from your Devic console, sent as Authorization: Bearer <key>. An embedded front end sends a tenant-session token instead, so no API key reaches the browser, and an OAuth integration sends its access token. Missing, invalid or expired credentials get a 401. See Authentication.

Path Parameters

identifier · string · required

Identifier of the assistant that holds the conversation

chatUid · string · required

Identifier of the conversation

Response

200

application/json

The conversation

A conversation with an assistant: its messages and everything the platform recorded about the run — model, tokens, cost, tags and the memory or compaction events it went through.

chatUID · string

Unique identifier of the conversation. This is the chatUid you send to continue it.

Example:

"550e8400-e29b-41d4-a716-446655440000"

clientUID · string

Account the conversation belongs to

Example:

"f9a44905-3193-4bd2-a81a-71156aa7eb66"

userUID · string

Identity that opened the conversation

Example:

"7a735eda-69e7-420b-9507-6abf80ad2e34"

name · string | null

Title of the conversation, when one was given or generated

Example:

"Solar panel recommendations"

archived · boolean

Archived conversations stay readable but are kept out of the default listings

assistantSpecializationIdentifier · string

Assistant that holds the conversation

Example:

"550e8400-e29b-41d4-a716-446655440000"

chatContent · object[]

The messages, oldest first. Omitted when the request asked for omitContent=true.

Show child attributes

creationTimestampMs · number

When the conversation was created, Unix milliseconds

Example:

1789630543006

lastEditTimestampMs · number

When it last changed, Unix milliseconds

Example:

1789630572077

llm · string

Model that answered

Example:

"gpt-4.1"

provider · string

Provider of that model

Example:

"open-ai"

contextWindow · number

Context capacity of the model in tokens. Absent for models the platform does not know the capacity of.

Example:

1050000

inputTokens · number

Input tokens of the whole conversation

Example:

6380

outputTokens · number

Output tokens of the whole conversation

Example:

372

tokenUsage · object

Full accounting of the conversation: the model's own tokens and cost, plus what the secondary calls (summarisation, compaction, evaluations) added, broken down by operation.

Show child attributes

metadata · object | null

The metadata the conversation was opened with, including the canonical subtenantId

tenantId · string | null

Tenant the conversation is attributed to, in multi-tenant setups

Example:

"tenant_12345"

tags · string[] | null

Tags stored on the conversation

Example:

["support", "onboarding"]

stopReason · string

Why the platform stopped the conversation, when it did (max_chat_messages_reached, error, ...)

Example:

"max_chat_messages_reached"

triggerSource · object

Set when an app-integration trigger opened the conversation instead of a person

guardrailResults · object

What the guardrails decided on this conversation

handedOff · boolean

The conversation is paused waiting for a subagent to finish

handedOffSubThreadId · string

Thread of the subagent it is waiting on

Example:

"64f5a5b8c123456789abcdef"

pausedUntil · number

When a self-paused assistant resumes, Unix milliseconds

pausedReason · string

Reason the assistant gave for pausing

recalledMemories · object[]

Long-term-memory recalls of this conversation, each with the facts or entities it surfaced and the messageUid of the message that brought it in, so a client can interleave them with the messages. Only for assistants with memory enabled.

coreMemories · object[]

Snapshots of the core-memory block the conversation was given, recorded whenever its revision changed. The block itself is re-rendered into the prompt on every call and never persisted with it. Only for assistants with core memory enabled.

compactions · object[]

Compaction checkpoints. Each folds the messages before its boundary into a summary plus the identifiers, paths and urls kept verbatim; from then on the model receives the checkpoint instead of those messages, which stay in chatContent. Only the newest one is in force.

reasoningEffort · enum<string> | null

Saved conversation effort; null/omission inherits the assistant.

Available options: none, minimal, low, medium, high, xhigh, max

effectiveReasoningEffort · enum<string>

Resolved effort for the last recorded model call; absent when using the adapter default.

Available options: none, minimal, low, medium, high, xhigh, max