Build continuity across calls

Preserve useful evidence and constraints so later Adapt-1 calls can reason with them.

Store useful evidence or constraints, query with that state, and correct the record when the information changes. Use the State gateway when the integration does not need a task-specific Domain contract.

This example keeps an operating constraint available across calls. Use the API key from the quickstart.

Record, query, and correct

1. Store a useful constraint

   Store evidence

   curl -fsS --max-time 60 \
     "https://rei-neuroadapt-api.reilabs.org/api/v1/memory/store" \
     -H "Authorization: Bearer $ADAPT1_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
       "session_id": "ignored",
       "user_message": "Line A must remain below 80 degrees Celsius.",
       "ai_message": "",
       "context": {"source": "operating-constraint"}
     }'
   

   Keep the returned storage_result.memory_id. It identifies the record you can later correct or remove.

2. Query with the retained evidence

   Read relevant context

   curl -fsS --max-time 60 \
     "https://rei-neuroadapt-api.reilabs.org/api/v1/memory/query" \
     -H "Authorization: Bearer $ADAPT1_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
       "session_id": "ignored",
       "user_message": "What temperature constraint applies to Line A?",
       "top_k": 5,
       "include_reasoning": true,
       "update_memory_state": false
     }'
   

   Inspect memory_context, confidence_score, and the optional reasoning. Check that the evidence supports the constraint your application will use.

3. Correct the record and query again

   Save this as correction.json, replacing MEMORY_ID_FROM_STORE with the returned ID:

   correction.json

   {
     "session_id": "ignored",
     "memory_id": "MEMORY_ID_FROM_STORE",
     "user_message": "Line A must remain below 75 degrees Celsius.",
     "ai_message": "",
     "context": {"source": "operator-correction"}
   }
   

   Apply the correction

   curl -fsS --max-time 60 \
     "https://rei-neuroadapt-api.reilabs.org/api/v1/memory/correct" \
     -H "Authorization: Bearer $ADAPT1_API_KEY" \
     -H "Content-Type: application/json" \
     --data-binary @correction.json
   

   Repeat the query and inspect how the corrected evidence affects the result. Keep both responses when validating the integration.

Choose a read operation

Need	Route	Returned information
Ranked supporting records	POST /api/v1/memory/search	Evidence items and ranking support
Context with reasoning	POST /api/v1/memory/query	memory_context, confidence_score, optional reasoning
Expanded explanation	POST /api/v1/memory/explain	Evidence, concepts, connections, conflicts, and resolution
Current state	POST /api/v1/memory/state	State and diagnostics for the authenticated scope
Bounded capacity summary	POST /api/v1/memory/state/summary	Memory-capacity summary
Stored records	POST /api/v1/memory/list	Records in the current scope

Query, search, and explain default to update_memory_state: true. Set it to false for a read-only comparison. Explain a result describes the response fields and their limits.

Manage the record lifecycle

Operation	Route	Behavior
Correct one record	/api/v1/memory/correct	Replace content while retaining its ID
Store 1–50 records	/api/v1/memory/batch_store	Synchronous, input-ordered, non-transactional
Preview or apply pruning	/api/v1/memory/prune	Start with dry_run: true; unique memories are protected by default
Remove one record	/api/v1/memory/delete	Address the stored memory ID
Clear the scope	/api/v1/memory/clear	Explicitly start a new State history

All operations above use POST. Inspect each batch result before retrying: records stored before a later failure remain stored. The compatibility alias /api/v1/batch_store remains available.

Scope, summaries, and pruning options

Hosted identity follows the bearer token. The body value session_id: ignored satisfies the compatibility contract; changing it does not select another tenant.

/memory/state also accepts summary_only: true. When pruning, set max_records, optional max_bytes, and include_unique deliberately. Inspect the dry-run candidates before applying them with dry_run: false.

A Domain is useful when events, relations, targets, or action outcomes need a stable task contract. State and Domain histories have different reset boundaries; see Operations and retries.

Explain the result

Inspect evidence, support, and unresolved information.

Create a task-scoped learner

Move from continuing evidence to a Domain with an observable target.