fleet-memory/hindsight-docs/examples/api
Nicolò Boschi 9b96becc5c
feat: entity labels — optional, free_values, multi_value, UI polish (#450)
* feat: entity labels

* feat: entity labels — optional, free_values, multi_value, UI polish

Completes the entity labels system:

**Schema & extraction**
- Dynamic Pydantic Labels model per fact: each group becomes a typed
  field (Literal | None, list[Literal], str | None, or list[str])
- `optional: bool` flag per group — non-optional enum fields appear in
  JSON schema required array so structured-output providers enforce them
- `free_values: bool` flag per group — accepts any LLM-generated string
  instead of a predefined enum; example values shown as hints in prompt
- New `is_label_entity()` helper for labels-only mode filtering that
  handles both enum lookup and free_values key-prefix matching
- Sentinel rejection: "None"/"null"/"n/a" strings dropped in post-processing

**BM25 / dense retrieval**
- `text_signals` column on memory_units: entity names + date tokens for
  enriched BM25 indexing without polluting stored fact text
- Dense embedding includes occurred_end when it differs from occurred_start
- Alembic migration z1u2v3w4x5y6 (merge revision fixing two heads)

**UI (bank-config-view)**
- Shadcn Switch replaces custom Toggle for both entity-labels and observations
- Shadcn Checkbox for multi/optional/free_values per group
- Input heights bumped to h-8 throughout the editor
- "Label Groups" → "Entity Labels", "Free-form entities" → "Entities"
- Free-text groups show "Example hints" banner in values section

**Tests (45 unit + 3 LLM integration)**
- build_labels_model: single, multi, mixed, free_values optional/required/multi
- is_label_entity: enum match, free_values prefix match, no false positives
- Post-processing: null/absent/string-None/free_values/sentinels/multi-value
- Schema: labels in required, structured object, no labels when unconfigured
- LLM integration: single-value enum, multi-value enum, free_values retain

**Docs**
- retain.md: new Entity Labels section covering groups, flags, examples
- configuration.md: retain_free_form_entities env var + entity_labels note

* fix(tests): update hierarchical fields count for entity_labels additions

entity_labels and retain_free_form_entities are hierarchical fields,
bumping the expected count from 11 to 13.

* fix(migration): rename text_signals revision to avoid collision with main

Main branch claimed z1u2v3w4x5y6 for observation_scopes. Rename our
text_signals migration to a2b3c4d5e6f7, chaining after z1u2v3w4x5y6.

* refactor(entity-labels): simplify free_values — always str|None, no multi

- free_values groups always produce str | None (multi_value and optional
  flags are ignored for free text groups — always optional, never multi)
- Prompt section for free_values groups shows only key + description,
  no values list (users put examples in the description instead)
- UI: section title "Entities", toggle "Free Form Entities", replace
  per-group checkboxes with a type dropdown (Enum / Free text); only
  show multi checkbox and values list when type is Enum
- Update tests to reflect new behaviour

* refactor(entity-labels): replace free_values/multi_value booleans with type field

- LabelGroup now uses type: "value" | "multi-values" | "text" instead of
  free_values/multi_value boolean pair
- Backward-compat migration converts legacy dicts automatically
- Rename retain_free_form_entities → entities_allow_free_form throughout
- Update UI dropdown to show Single value / Multi-values / Free text
- Remove separate multi checkbox (captured by type selection)
- Update docs examples and configuration.md
- Update all tests to use new field names

* fix(migration): backfill observation_scopes column for DBs with swapped z1u2v3w4x5y6

Local DBs that had z1u2v3w4x5y6 applied when it referred to the old
text_signals migration (before it was renamed to a2b3c4d5e6f7) won't have
observation_scopes in their memory_units table. This migration adds the
column with IF NOT EXISTS so it's a no-op on clean installs.

* feat(entity-labels): add tag field to auto-populate memory unit tags from labels

When a LabelGroup has tag=True, extracted key:value entities for that group
are automatically written to the memory unit's tags array. This lets entity
labels double as tags, enabling immediate filtering via the existing
tags/tags_match API params with no extra infrastructure.

- Add tag: bool = False to LabelGroup
- _inject_label_tags() helper called in both sync and batch extraction paths
- UI: add Tag checkbox per label group row
- Docs: document the new tag field
- Tests: 4 new unit tests covering all tag injection paths

* style: ruff format migration file

* fix(migration): fix multiple alembic heads after rebase — point text_signals after nullable_event_date

* fix(clients): update timestamp field to use Timestamp wrapper type after timestamp=unset feature

* style: ruff format agent.py

* fix(docs): update Go quickstart example to use NullableTimestamp for timestamp field
2026-03-02 13:05:25 +01:00
..
legacy doc: add blog (#201) 2026-01-28 15:42:14 +01:00
cli-reference.sh ci: finalize test for the documentation code (#57) 2025-12-19 12:17:59 -07:00
directives.mjs fix: misc fixes for observations and mental models (#209) 2026-01-27 15:37:57 +01:00
directives.py fix: misc fixes for observations and mental models (#209) 2026-01-27 15:37:57 +01:00
documents.mjs doc: add go client examples (#380) 2026-02-16 14:43:03 +01:00
documents.py fix: improve async batch retain with large payloads (#366) 2026-02-16 12:51:42 +01:00
main-methods.mjs ci: finalize test for the documentation code (#57) 2025-12-19 12:17:59 -07:00
main-methods.py doc: improve api explanation (#415) 2026-02-20 17:02:01 +01:00
memory-banks.mjs doc: fix build 2026-02-25 16:58:06 +01:00
memory-banks.py doc: fix build 2026-02-25 16:58:06 +01:00
mental-models.py fix: misc fixes for observations and mental models (#209) 2026-01-27 15:37:57 +01:00
quickstart.go feat: entity labels — optional, free_values, multi_value, UI polish (#450) 2026-03-02 13:05:25 +01:00
quickstart.mjs Add documentation code validation system (#43) 2025-12-18 10:21:38 +01:00
quickstart.py Add documentation code validation system (#43) 2025-12-18 10:21:38 +01:00
quickstart.sh Add documentation code validation system (#43) 2025-12-18 10:21:38 +01:00
README.md doc: mental models (#199) 2026-01-26 14:27:08 +01:00
recall.mjs doc: improve api explanation (#415) 2026-02-20 17:02:01 +01:00
recall.py feat: filter graph memories with tags (#431) 2026-02-25 10:31:40 +01:00
recall.sh chore: internal renames (#204) 2026-01-27 09:53:28 +01:00
reflect.mjs chore: internal renames (#204) 2026-01-27 09:53:28 +01:00
reflect.py doc: improve api explanation (#415) 2026-02-20 17:02:01 +01:00
reflect.sh chore: internal renames (#204) 2026-01-27 09:53:28 +01:00
retain.mjs doc: improve api explanation (#415) 2026-02-20 17:02:01 +01:00
retain.py doc: improve api explanation (#415) 2026-02-20 17:02:01 +01:00
retain.sh misc: fix vertex/gemini errors and use it for ci tests (#414) 2026-02-20 22:35:38 +01:00
sample.pdf feat: accept pdf, images and office files (#390) 2026-02-17 18:15:03 +01:00

API Documentation Examples

This directory contains runnable example scripts that serve as the source of truth for code samples in the documentation.

How It Works

  1. Scripts are runnable - Each file can be executed as a smoke test
  2. Markers define sections - Code between # [docs:section-name] and # [/docs:section-name] markers is extracted
  3. Docs import at build time - MDX files use raw-loader to import scripts, then CodeSnippet extracts marked sections

File Structure

File Documentation Description
quickstart.py/mjs/sh quickstart.md Getting started examples
retain.py/mjs/sh retain.md Memory ingestion examples
recall.py/mjs/sh recall.md Memory retrieval examples
reflect.py/mjs/sh reflect.md AI reflection examples
memory-banks.py/mjs memory-banks.md Bank management examples
documents.py/mjs documents.md Document CRUD examples
reflections.py reflections.md Reflections CRUD examples
main-methods.py main-methods.md Core method examples
cli-reference.sh cli.md CLI command examples

Running Examples

# Run all Python examples
for f in *.py; do python "$f"; done

# Run all Node.js examples
for f in *.mjs; do node "$f"; done

# Run all CLI examples
for f in *.sh; do bash "$f"; done

Requires a running Hindsight server at http://localhost:8888 (or set HINDSIGHT_API_URL).

Legacy Examples

The legacy/ folder contains deprecated example files kept only for backward compatibility with older documentation versions. These files are not runnable and are skipped by CI tests.

What's NOT Covered

1. OpenAPI Auto-Generated Docs (/api-reference/*)

These pages are generated directly from the OpenAPI specification. The spec itself is the source of truth, and the generated docs reflect it automatically. No manual code examples to validate.

2. Interactive CLI Commands

Command Reason
hindsight configure Requires interactive user input (prompts for API URL, credentials)
hindsight configure --show Displays sensitive configuration, not suitable for automated tests

3. Installation/Setup Instructions

Documentation sections covering pip install, npm install, or system setup are instructions, not executable code samples. These are validated by the CI environment setup itself.

4. Error Handling Examples

Some docs show error responses (e.g., "what happens when bank doesn't exist"). These require intentionally broken states that would fail smoke tests. Error behavior is covered by unit tests instead.

Adding New Examples

  1. Create or edit the appropriate script file
  2. Add markers around the new code section:
    # [docs:my-new-section]
    client.some_method(...)
    # [/docs:my-new-section]
    
  3. Reference in the MDX file:
    import myScript from '!!raw-loader!@site/examples/api/my-script.py';
    <CodeSnippet code={myScript} section="my-new-section" language="python" />
    
  4. Run the script locally to verify it works

Marker Format

  • Python/Bash: # [docs:section-name] / # [/docs:section-name]
  • JavaScript: // [docs:section-name] / // [/docs:section-name]

Section names should be kebab-case and descriptive (e.g., retain-with-context, recall-basic).