fleet-memory/hindsight-docs/docs/developer
Nicolò Boschi b32767caa8
feat: add max_observations_per_scope bank config (#729)
* feat: add max_observations_per_scope bank config

Adds a configurable limit on the number of observations per tag scope.
When the limit is reached, consolidation only updates/deletes existing
observations — no new ones are created. Enforcement is done via a
constrained Pydantic response model (max_length on creates list) so the
LLM structurally cannot exceed the limit, plus prompt guidance.

- Config: HINDSIGHT_API_MAX_OBSERVATIONS_PER_SCOPE (-1 = unlimited)
- Reorder action execution: deletes → updates → creates
- Dynamic _ConsolidationBatchResponse with max_length constraint
- Prompt CAPACITY CONSTRAINT section when near/at limit
- Observations with no tags skip the limit entirely
- Control plane UI field + docs

* fix: strengthen max_observations tests with mock LLM + defensive truncation

- Rewrite integration tests to use MockLLM with deterministic responses
  (one observation per fact) instead of relying on real LLM behavior
- Add defensive truncation in _consolidate_batch_with_llm as belt-and-
  suspenders — catches LLM providers that ignore JSON schema max_length
- Tests now assert exact counts, not just upper bounds
2026-03-30 10:29:56 +02:00
..
api feat(docs): Integrations Hub + unified page hero (#620) 2026-03-19 20:29:55 +01:00
admin-cli.md Fix run-db-migration for all-tenant upgrades (#530) 2026-03-10 10:10:03 +01:00
configuration.md feat: add max_observations_per_scope bank config (#729) 2026-03-30 10:29:56 +02:00
development.md rename to hindsight (#2) 2025-11-25 19:28:26 +01:00
extensions.md feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
index.mdx feat(docs): Integrations Hub + unified page hero (#620) 2026-03-19 20:29:55 +01:00
installation.md docs: add supported platforms and Windows installation guide (#700) 2026-03-26 12:01:30 +01:00
mcp-server.md feat: expand MCP tool surface area with 18 new tools and enhanced parameters (#435) 2026-02-25 10:26:46 +01:00
models.mdx docs: add Volcano Engine as supported LLM provider (#715) 2026-03-26 18:21:34 +01:00
monitoring.md feat: add LiteLLM LLM provider for Bedrock and 100+ providers (#679) 2026-03-25 14:17:38 +01:00
multilingual.md chore: internal renames (#204) 2026-01-27 09:53:28 +01:00
observations.mdx feat: observation_scopes field to drive observations granularity (#447) 2026-02-28 10:46:21 +01:00
performance.md doc: changelog for 0.4.12 (#397) 2026-02-18 14:55:19 +01:00
rag-vs-hindsight.md doc: mental models (#199) 2026-01-26 14:27:08 +01:00
reflect.mdx feat: increase customization for reflect, retain and consolidation (#419) 2026-02-23 20:35:32 +01:00
retain.md docs: entities vs tags vs metadata (#466) 2026-03-02 14:47:40 +01:00
retrieval.md chore: internal renames (#204) 2026-01-27 09:53:28 +01:00
services.md doc: mental models (#199) 2026-01-26 14:27:08 +01:00
storage.md bump pg0 0.11.x and improve documentation (#33) 2025-12-16 13:33:01 +01:00