docs: changelog and blog post for v0.8.2 (#2172)

* docs: changelog and blog post for v0.8.2

* docs: clarify per-bank cost attribution is opt-in via env flag

Author: nicoloboschi

hindsight-docs/blog/2026-06-12-version-0-8-2.md

@@ -0,0 +1,64 @@
+---
+title: "What's new in Hindsight 0.8.2"
+description: Reversible memory curation, observation scopes, a local Control Center for embedded deployments, new providers and embedding models, plus operational and data-integrity fixes in Hindsight 0.8.2
+authors: [nicoloboschi]
+date: 2026-06-12
+hide_table_of_contents: true
+tags: [release]
+---
+
+Hindsight 0.8.2 builds on [0.8.1](/blog/2026/06/09/version-0-8-1) with a much bigger release: you can now **edit, invalidate, and revert individual memories**, organize and cap memories with **observation scopes**, and run a **local Control Center** alongside an embedded deployment. It also adds new LLM providers and embedding models, and ships several operational and data-integrity fixes. **Anyone self-managing Hindsight should upgrade** — this release includes concurrency and data-storage fixes that affect long-running deployments.
+
+<!-- truncate -->
+
+- [**Reversible Memory Curation**](#reversible-memory-curation): Edit, invalidate, and revert memory units without losing history.
+- [**Observation Scopes**](#observation-scopes): List, filter, visualize, and cap memories per scope.
+- [**Local Control Center**](#local-control-center): A built-in web app for embedded deployments.
+- [**More Providers and Models**](#more-providers-and-models): Native Nous Portal, Gemini Batch retain, Gemini embedding-2, per-bank cost attribution, and a connectivity probe.
+- [**Operational and Data-Integrity Fixes**](#operational-and-data-integrity-fixes): Why you should upgrade.
+
+## Reversible Memory Curation
+
+Memories are no longer write-only. 0.8.2 lets you correct what an agent has learned and undo mistakes:
+
+- **Edit** a memory's text, dates, fact type, or context.
+- **Invalidate** a memory so it stops surfacing in recall, without deleting it.
+- **Revert** an edit or an invalidation to restore the previous state.
+
+Invalidated memories are moved aside rather than purged, so the recall hot path stays clean while nothing is permanently lost. Edited memories are marked so you can see at a glance what's been changed. This makes it practical to keep a bank accurate over time — fixing a wrong fact or retiring a stale one is now a reversible action instead of a destructive one.
+
+## Observation Scopes
+
+As banks grow, observations accumulate across many contexts. 0.8.2 makes them manageable:
+
+- **Enumerate and filter** observations by scope to see what's been learned where.
+- **Visualize** scopes in the Control Plane.
+- **Set per-scope limits** to cap how many observations a scope keeps — including a limit of `0` to stop new observations in a scope entirely.
+
+This gives you direct control over how much memory each context retains, instead of a single global setting.
+
+## Local Control Center
+
+Embedded deployments now ship with a local **Control Center** web app. It gives you a UI to manage and inspect an embedded Hindsight instance without standing up the full control plane separately — useful for local and single-node setups.
+
+## More Providers and Models
+
+0.8.2 expands provider and model coverage:
+
+- **Native Nous Portal provider** with built-in OAuth authentication — no external CLI dependency required.
+- **Gemini Batch API for retain**, so fact extraction can run through Gemini's batch path.
+- **Gemini embedding-2 model family** support, with per-input embeddings.
+- **Per-bank provider cost attribution.** Set `HINDSIGHT_API_LLM_SEND_BANK_AS_USER=true` to tag outbound OpenAI-compatible LLM and embedding calls with the bank ID in the `user` field, so cost gateways (OpenRouter, LiteLLM, Helicone) can key provider spend per bank. Off by default.
+- **Per-bank LLM connectivity probe** to verify a bank's provider configuration before relying on it.
+- **Amazon Bedrock service-tier selection** for tuning Bedrock request handling.
+
+## Operational and Data-Integrity Fixes
+
+Several fixes make self-managed and long-running deployments more robust — the reason to upgrade:
+
+- **Torch dtype under concurrency.** Concurrent model initialization could change the global Torch default dtype; it's now normalized back to `float32` so behavior stays consistent.
+- **Recall/reflect cancellation.** Abandoned recall and reflect operations are now reliably cancelled when the client disconnects, instead of running to completion and wasting work.
+- **Wider history IDs on PostgreSQL.** The history `bank_id` column is widened to `TEXT`, preventing failures with longer bank identifiers.
+- **Reflect synthesis fidelity.** Final reflect output now respects directives and language rules more consistently.
+- **JSONL retain chunking.** JSONL files are chunked on line boundaries so records are never split mid-line during ingestion.
+- **Control Plane graph view.** The bank graph view no longer double-loads its data, cutting redundant requests.