Conversation
🛡️ Jit Security Scan Results✅ No security findings were detected in this PR
Security scan by Jit
|
dwdougherty
left a comment
There was a problem hiding this comment.
So far, so good. Just a few SG-related nitpicks. I can have a look at other pages as you add them if you wish.
| The promotion from short term memory to long-term memory is automatic. When you store a conversation event in session memory, the Agent Memory Server asynchronously extracts important information using the configured extraction strategy (discrete, summary, preferences, or custom). These extracted memories are then stored as long-term memory entries with vector embeddings and metadata. | ||
|
|
||
| This process is non-blocking: the extraction and promotion happen in the background via a task worker, so the main agent interaction remains responsive. Users do not need to explicitly trigger promotion; it happens as a natural byproduct of storing conversation events in working memory. | ||
| Users can also create long-term memories directly via the API.This is useful for bulk memory creation or for importing knowledge from external sources. |
There was a problem hiding this comment.
| Users can also create long-term memories directly via the API.This is useful for bulk memory creation or for importing knowledge from external sources. | |
| Users can also create long-term memories directly using the API.This is useful for bulk memory creation or for importing knowledge from external sources. |
mich-elle-luna
left a comment
There was a problem hiding this comment.
just a few typos, also I think that the agent-memory-service-key.png seems too large on the page.
|
thank you, looking great so far! |
Co-authored-by: David Dougherty <david.dougherty@redis.com> Co-authored-by: mich-elle-luna <153109578+mich-elle-luna@users.noreply.github.com> Co-authored-by: Cameron Bates <102550101+cmilesb@users.noreply.github.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
dwdougherty
left a comment
There was a problem hiding this comment.
Latest commit looks good, but the API page links need to be more granular: I think you're still working on that content, right?
I forgot to update the tags 🤦 That's what I get for pushing things at 6PM. Thanks for the catch. |
mich-elle-luna
left a comment
There was a problem hiding this comment.
one comment from a reviewer in devrel team
| When you call the API, you need to pass the Agent Memory API key in the `Authorization` header as a Bearer token and the store ID as the `storeId` path parameter. | ||
|
|
||
| For example: | ||
|
|
There was a problem hiding this comment.
One question from devrel team was if you plan to include a drop-down menu to show programming-language examples, in addition to REST API calls? Just like we have with LangCache? In case of RAM, the Python SDK client?
There was a problem hiding this comment.
It's possible to have that, but I haven't had time and I figured I would prioritize getting something out rather than getting something perfect out. I can add that after release (or after I have something for context retriever).
| ### Add session event | ||
|
|
||
| Use [`POST /v1/stores/{storeId}/session-memory`]({{< relref "/develop/ai/context-engine/agent-memory/api-reference#tag/session-memory/operation/AddSessionEvent" >}}) to add an event to a session in short-term memory. If a session doesn't exist yet, it will be created. | ||
|
|
There was a problem hiding this comment.
Something Ricardo noticed: It uses cache_id instead of store_id. And the REST API example does the same.
curl -s -X GET "https://$HOST/v1/caches/$CACHE_ID/session-memory/"
-H "accept: application/json"
-H "Authorization: Bearer $API_KEY"
It may be worth double-checking with the API Spec from Agent Memory.
- Add Data Integration as a fourth Context Engine service on the index page - Create develop/ai/context-engine/data-integration/ overview page with get started tabs for Redis Cloud and Redis Enterprise - Remove em dashes and rewrite both pages in Google developer style Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Fix 8 inconsistencies between the hand-written documentation and the
Agent Memory OpenAPI spec (MemoryDataPlaneServer):
api-examples.md:
- Fix curl path: /v1/caches/ -> /v1/stores/ (wrong path segment)
- Fix Store ID description typo ("Store ID ID of your cache")
- Fix AddSessionEvent endpoint: /session-memory -> /session-memory/events
- Fix createdAt format: Unix ms -> ISO 8601 date-time (per MOD-15623)
- Fix duplicate namespace row in filter table (second should be topics)
- Add missing memoryType filter to the table
- Fix createdAt filter data type: integer -> string (ISO 8601)
create-service.md:
- Fix Long-term TTL description (was copy-pasted from database selector)
Verified against the Smithy-generated OpenAPI spec from langcache main
(commit fd8b6c2b).
Co-authored-by: Cursor <cursoragent@cursor.com>
…s-consistency fix: align Agent Memory docs with current API spec
Still working on API examples page and service monitoring, but should be updated soon.
Note
Low Risk
Documentation-only changes introducing new sections and large OpenAPI spec content; main risk is broken links/navigation due to path and weight reorganization.
Overview
Adds a new Context Engine documentation section under
develop/ai/context-engineandoperate/rc/context-engine, including new pages for Redis Agent Memory (overview, API examples, and a full OpenAPI-based API reference) plus a Data Integration overview.Migrates LangCache docs and Redis Cloud guides to the new
.../context-engine/langcachepaths, addingaliasesfor backward compatibility and updating cross-links in “What’s new”, the homepage, embeds, and the Redis Cloud changelog. Also adjusts several Redis Cloud left-navweightvalues to accommodate the new Context Engine entries.Reviewed by Cursor Bugbot for commit 8a5ed39. Bugbot is set up for automated code reviews on this repo. Configure here.