What's new in Hindsight 1.2.0

Hindsight 1.2.0 adds support for the Hindsight models — the hs-decide-1-flash decision model, hs-rerank-1 reranker and hs-embed-1 embedding model — and makes hs-rerank-1 the default reranker in place of cross-encoder/ms-marco-MiniLM-L-6-v2, the release notes state. The release also adds per-request and per-bank prune and dedup controls for decision-model recall, routes reflect's tool calls through a response schema so they work on OpenAI-compatible servers such as vLLM that ignore forced tool choice, and ships reliability fixes across retain, consolidation, reflect, refresh and the worker. The release notes tell everyone on 1.1.x to upgrade.

What's new in Hindsight 1.2.0 Support for the Hindsight models, a new default reranker, prune and dedup controls for decision-model recall, images on knowledge pages, a better LLM request view, and a long round of reliability fixes Hindsight 1.2.0 adds support for the Hindsight models, makes hs-rerank-1 the default reranker, gives recall finer control over what the decision model keeps, shows the images behind knowledge pages, and makes the LLM request view easier to read. Tool calls now go through a response schema on every provider, which makes reflect far more reliable on self-hosted models. Most of the release is reliability work across retain, consolidation, reflect, refresh and the worker. Everyone on 1.1.x should upgrade — see the changelog https://hindsight.vectorize.io/changelog for the full list. - Hindsight models hindsight-models : A decision model, a reranker and an embedding model built for agent memory; hs-rerank-1 is the new default reranker. - Decision-model recall: prune and dedup decision-model-recall-prune-and-dedup : Drop irrelevant and duplicate memories, per request or per bank. - Tool calls through a response schema tool-calls-through-a-response-schema : Reflect works on servers that ignore forced tool choice. - Images on knowledge pages images-on-knowledge-pages : See the images behind a page's evidence. - A better LLM request view a-better-llm-request-view : Retention, an hourly chart, and a split by model or operation. - More settings more-settings : Vision call settings, embedding extra body, a default time zone. - Helm helm : Optional API command, startup probe, strategy and token mounting. Hindsight models 1.2.0 supports the Hindsight models: hs-decide-1-flash , a decision model that takes over the small judgments in consolidation, reflect and knowledge pages, plus hs-rerank-1 and hs-embed-1 . They're off until you set them up: run hindsight-admin cloud login and set HINDSIGHT API DECISION MODEL PROVIDER=hindsight . See Decision Models https://hindsight.vectorize.io/developer/decision-models for every setting. The default reranker changes. The local and ONNX rerankers now use hindsight-ai/hs-rerank-1 , multilingual eight languages and trained for Hindsight recall, instead of cross-encoder/ms-marco-MiniLM-L-6-v2 . It downloads on first start. To keep the old model on the local provider, set HINDSIGHT API RERANKER LOCAL MODEL=cross-encoder/ms-marco-MiniLM-L-6-v2 . The typesafe reranker provider is deprecated in favour of the shared decision model. Decision-model recall: prune and dedup When the decision model reranks recall, it can now also drop memories that don't help answer the query prune and memories that repeat one already returned dedup . Turn them on per request HTTP and MCP recall , or per bank with HINDSIGHT API RECALL DECISION MODEL PRUNE and HINDSIGHT API RECALL DECISION MODEL DEDUP . The decision model now also sees each memory's date, so time-sensitive questions rank better. Tool calls through a response schema Reflect's tool calls now go through a response schema instead of the provider's native tool calling. Some OpenAI-compatible servers for example vLLM with some open models accept tools but don't honour a forced tool choice, so reflect's forced steps were often skipped. Those servers do honour a response schema, so reflect now behaves the same on every provider. Images on knowledge pages When a knowledge page's evidence comes from retained images, the page now shows them next to that evidence in the control plane. A better LLM request view The LLM request view says how many days of history are kept, adds an hourly chart for the last 24 hours, and splits usage by model or by operation. It now also records embedding, rerank and decision-model calls, not only LLM calls. Set HINDSIGHT API LLM TRACE DELETE WITH DOCUMENT=true to delete a document's request history when the document is deleted; deleting a bank always deletes its history. More settings - Vision calls get their own reasoning effort, timeout, retries and extra body HINDSIGHT API VLM . - OpenAI-compatible embeddings can send an extra request body HINDSIGHT API EMBEDDINGS OPENAI EXTRA BODY . - Default time zone HINDSIGHT API DEFAULT TIMEZONE : retain timestamps without a UTC offset are read in this zone. Helm The chart adds an optional API command , a startupProbe , a deployment strategy , and control over automountServiceAccountToken . Docker and Helm give the API 60 seconds to finish in-flight work on shutdown. Breaking changes: no provider is sent native tools any more, so an OpenAI-compatible server must support a response schema structured output . HINDSIGHT API LLM SUPPORTS MAX ITEMS , HINDSIGHT API LLM STRUCTURED OUTPUT FORCED TOOL and HINDSIGHT API REFLECT PROMPT CACHE ENABLED are removed; remove them from your configuration. On the LiteLLM-backed providers litellm , litellmrouter , bedrock , set HINDSIGHT API LLM STRUCTURED OUTPUT IN PROMPT=true to give the schema in the prompt instead.