v0.8.0

## What's Changed
* docs(guides): add Hermes memory guide batch by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1932
* docs: changelog and blog post for v0.7.2 by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1933
* feat: upgrade MiniMax default model to M3 by @octo-patch in https://github.com/vectorize-io/hindsight/pull/1914
* chore(control-plane): bump next back to ^16.2.6 (undo 16.2.5 pin) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1934
* fix(retain): pre-extraction freshness recheck + serialize concurrent same-doc writers by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1930
* blog: Using Entity Labels to Automatically Tag Memories in Hindsight by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1935
* feat(api): per-bank LLM request tracing via OTel GenAI recorder by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1922
* fix(recall): gate VectorChord BM25 + add per-source candidate cap (#1707) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1947
* fix(config): persist bank config PATCH for never-retained banks (#1940) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1945
* fix(control-plane): localize operations and graph legends by @MapleEve in https://github.com/vectorize-io/hindsight/pull/1946
* fix(retain): stop bank_id routing key polluting fact attribution (#1680) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1948
* feat(transfer): export/import documents between banks without re-running the LLM by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1909
* blog: Voice Agents That Remember — Adding Memory to Vapi with Hindsight by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1949
* feat(control-plane): "not enabled" splash for disabled audit logs & LLM requests (+ bank name fix) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1950
* fix(consolidation): eliminate duplicate observations (interleave dedup recall + tool & benchmark) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1907
* fix(retain): make document lock/upsert dialect-aware for Oracle (#1944) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1952
* fix(test): use current default model in Vertex AI integration test by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1972
* feat(transfer): whole-bank export/import for cross-instance migration (#1884) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1953
* fix(search): escape pgroonga BM25 query text by @xmh1011 in https://github.com/vectorize-io/hindsight/pull/1966
* feat(recall): per-strategy retrieval boost via env config by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1974
* feat(llm): provider prompt-prefix caching — retain + consolidation + reflect (bank-agnostic, default-on) by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/1936
* fix(autogen): default to Cloud + gated E2E + bucketing + ADD missing CI job by @DK09876 in https://github.com/vectorize-io/hindsight/pull/1868
* refactor(engine): cheaper bank stats — drop unused join, add freshness helper, result cache by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/1859
* blog: Long-Term Memory for Google ADK Agents with Hindsight by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1979
* blog(google-adk): update cover image by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1985
* fix(llamaindex): default to Cloud + replace dead manual test with gated E2E + requires_real_llm bucketing by @DK09876 in https://github.com/vectorize-io/hindsight/pull/1867
* feat(consolidation): semantic dedup of near-duplicate observations (create + update) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1977
* fix(clients): expose reflect tool_calls/llm_calls trace in python + typescript wrappers by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1997
* fix(claude-code): default enableKnowledgeTools to true; keep MCP server alive when disabled by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1999
* feat(api): enable LLM request tracing by default with 1-day retention by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1996
* docs(configuration): document HINDSIGHT_API_BANK_STATS_CACHE_TTL_SECONDS + _MAX_ENTRIES from #1859 by @r266-tech in https://github.com/vectorize-io/hindsight/pull/1993
* fix: raise _check_health default timeout 2s→10s to stop busy-daemon kill loop by @21Felix04 in https://github.com/vectorize-io/hindsight/pull/1992
* docs(retrieval): correct "no per-strategy weight multipliers" after RECALL_STRATEGY_BOOSTS (#1974) by @r266-tech in https://github.com/vectorize-io/hindsight/pull/1991
* docs(configuration): document HINDSIGHT_API_LLM_PROMPT_CACHE_ENABLED in the LLM Provider table by @r266-tech in https://github.com/vectorize-io/hindsight/pull/1990
* docs(models): vertexai default model gemini-2.0-flash-001 is retired — sync to gemini-2.5-flash-lite by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2001
* docs(api/bank-templates): fix entity_labels manifest example — label-group objects, not string[] by @r266-tech in https://github.com/vectorize-io/hindsight/pull/1984
* chore(deps): bump the uv group across 18 directories with 2 updates by @dependabot[bot] in https://github.com/vectorize-io/hindsight/pull/1982
* fix(mental-models): create bank before insert by @oldschoola in https://github.com/vectorize-io/hindsight/pull/1994
* docs(configuration): document HINDSIGHT_API_WORKER_IMPORT_DOCUMENTS_MAX_SLOTS worker slot reservation by @r266-tech in https://github.com/vectorize-io/hindsight/pull/1978
* docs(admin-cli): document decommission-worker --yes/-y confirmation-skip flag by @r266-tech in https://github.com/vectorize-io/hindsight/pull/1957
* fix(recall): bound temporal entry-point scan to top-50-per-fact_type (alternative to #1958) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1983
* feat(consolidation): enable observation dedup by default (0.97), skip on Oracle by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2000
* fix: validate embedding dimensions before pgvector writes by @ai-ag2026 in https://github.com/vectorize-io/hindsight/pull/1670
* chore: update gemini embedding model from preview to GA by @dcbouius in https://github.com/vectorize-io/hindsight/pull/1780
* chore: update Gemini model recommendations to 3.x series by @dcbouius in https://github.com/vectorize-io/hindsight/pull/1787
* hindsight-docs: Added OutSystems community integration by @stefan-d-p in https://github.com/vectorize-io/hindsight/pull/1873
* docs(models): register `fireworks` so the Models grid + default-models table list it (#1860) by @r266-tech in https://github.com/vectorize-io/hindsight/pull/1911
* docs(cli): replace removed `opinion` fact-type with `observation` in recall example by @r266-tech in https://github.com/vectorize-io/hindsight/pull/1917
* docs(admin-cli): document full backup table coverage from #1903 by @r266-tech in https://github.com/vectorize-io/hindsight/pull/1929
* chore(deps): bump the npm_and_yarn group across 1 directory with 2 updates by @dependabot[bot] in https://github.com/vectorize-io/hindsight/pull/1938
* feat(embeddings): add ONNX local provider by @shoveller in https://github.com/vectorize-io/hindsight/pull/1970
* fix(oracle): make recall and mental-model history work on the Oracle backend by @DK09876 in https://github.com/vectorize-io/hindsight/pull/1980
* docs(performance): expand local-LLM concurrency guidance into a Local & Small Environments tuning section by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2002
* feat(llm): apply HINDSIGHT_API_LLM_EXTRA_BODY across all API providers by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2006
* feat(llm): opt-in strict json_schema across json_schema-capable providers (not just OpenAI) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2003
* fix(api): add vchord catalogs to search_path for external Postgres (#1351) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2008
* refactor(api): unify lazy bank-create into _ensure_bank_exists, couple to caller txn by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2004
* fix(ci): repair zeroentropy embedding tests and regenerate drifted clients by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2009
* fix(docker): clear diagnostic for pg0 bind-mount permission failure (#1483) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2010
* feat(history): move mental-model & observation history into dedicated tables by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2007
* fix(reflect): let a fresh mental model short-circuit forced retrieval (no extra LLM call) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2011
* docs(models): note Groq free tier (8k TPM) is unsuitable for Hindsight by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2015
* fix(init): fail fast when model init blocks instead of hanging forever by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2014
* fix(llm): downgrade tool_choice="required" for servers that silently drop it (vLLM/LM Studio/Ollama) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2016
* feat(operations): durable progress snapshot for consolidation and batch retain by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2013
* blog: How Hindsight Learns — A Deep Dive Into Mental Models by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2021
* LangGraph: add memory_instructions, fix nodes, remove BaseStore by @DK09876 in https://github.com/vectorize-io/hindsight/pull/1673
* feat(claude-agent-sdk): add Claude Agent SDK integration by @DK09876 in https://github.com/vectorize-io/hindsight/pull/1582
* fix(litellm): injection_mode, context manager restore, validation, error consistency by @DK09876 in https://github.com/vectorize-io/hindsight/pull/1711
* fix(openai-agents): default to Cloud + gated E2E + requires_real_llm bucketing by @DK09876 in https://github.com/vectorize-io/hindsight/pull/1866
* fix(opencode): default to Hindsight Cloud + gated live E2E by @DK09876 in https://github.com/vectorize-io/hindsight/pull/1915
* feat(integrations): add Superagent safety middleware by @DK09876 in https://github.com/vectorize-io/hindsight/pull/1128
* docs(api): document the operation progress snapshot + include_payload on the status endpoint by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2037
* docs(claude-code): correct enableKnowledgeTools default (false→true) and disabled-behavior after #1999 by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2044
* fix(reranker): make litellm-sdk reranker api_key optional for Bedrock IAM auth by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2043
* fix(opencode): drop non-function export from plugin entry so it loads under OpenCode 1.16 (#2028) by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2038
* fix(trace): preserve RRF source ranks by @zwcf5200 in https://github.com/vectorize-io/hindsight/pull/2040
* fix(transfer): include mental_model_history count in import-bank CLI summary by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2032
* docs(models): flag Fireworks AI Batch API support in the provider capabilities table by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2036
* docs(configuration): document shared cohere/litellm fallback API-key aliases by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2031
* docs(models): sync gemini + vertexai default models to 3.x matching config.py by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2030
* fix: remove Markdown bold formatting from fact extraction prompt by @Oxygen56 in https://github.com/vectorize-io/hindsight/pull/2029
* chore(deps): bump the uv group across 4 directories with 6 updates by @dependabot[bot] in https://github.com/vectorize-io/hindsight/pull/2027
* docs(models): document the onnx embeddings provider by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2020
* fix(retain): expose retain outcome metadata by @xmh1011 in https://github.com/vectorize-io/hindsight/pull/2041
* docs(configuration): document HINDSIGHT_API_DATABASE_BACKEND (postgresql|oracle) by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2024
* feat(recall): add configurable HINDSIGHT_API_SEMANTIC_MIN_SIMILARITY by @zwcf5200 in https://github.com/vectorize-io/hindsight/pull/2039
* feat(consolidation): periodic reconcile + cross-tenant retention via maintenance loop (#1969) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2019
* fix(opencode): observable logging — config-only debug, resolved-endpoint log, surfaced errors by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2047
* perf(recall): add recall-temporal suite that forces the temporal arm by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2046
* test(ci): de-flake TEI parallelism timing + disposition judge reruns by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2045
* fix(opencode): call OpenCode app.log as a method so logging actually works by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2049
* test(ci): harden LLM-as-judge against single-call verdict flips by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2050
* docs(integrations): single source of truth (integrations.json) for gallery + sidebars by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2048
* test(entity-labels): reproduce paired id/name extraction from [[...]] tags by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2051
* fix(consolidation): set output token budget by @xmh1011 in https://github.com/vectorize-io/hindsight/pull/1967

## New Contributors
* @21Felix04 made their first contribution in https://github.com/vectorize-io/hindsight/pull/1992
* @oldschoola made their first contribution in https://github.com/vectorize-io/hindsight/pull/1994
* @stefan-d-p made their first contribution in https://github.com/vectorize-io/hindsight/pull/1873
* @shoveller made their first contribution in https://github.com/vectorize-io/hindsight/pull/1970
* @Oxygen56 made their first contribution in https://github.com/vectorize-io/hindsight/pull/2029

**Full Changelog**: https://github.com/vectorize-io/hindsight/compare/v0.7.2...v0.8.0