fleet-memory/hindsight-api-slim/hindsight_api/config_resolver.py
Nicolò Boschi e4f8a157c2
feat(retain): verbatim, chunks modes and named retain strategies (#593)
* feat(retain): add verbatim extraction mode

Adds retain_extraction_mode="verbatim" that stores each chunk as-is
without LLM summarization. The LLM still runs to extract entities,
temporal info, and location for full indexability — only the fact text
is replaced with the original chunk content (one memory per chunk).

Useful for RAG-style indexing and benchmarks where original text
must be preserved in memory.

- Add "verbatim" to RETAIN_EXTRACTION_MODES in config.py
- Add VERBATIM_FACT_EXTRACTION_PROMPT with instructions to preserve text
- Add _collapse_to_verbatim() post-processing to enforce 1 fact/chunk
- Expose in bank config UI dropdown with updated description
- Update configuration.md docs with verbatim mode description
- Add unit test for _collapse_to_verbatim and integration test via LLM
- Fix pre-existing main.py CLI override missing new reranker fields
- Fix pre-existing cross_encoder.py ty type error via setattr

* refactor(retain): verbatim mode skips 'what' field entirely

Instead of asking the LLM to echo the chunk text back into 'what' and
then discarding it, verbatim mode now uses a dedicated schema
(VerbatimExtractedFact) that omits the 'what' field altogether.
The LLM only returns metadata (entities, temporal info, location, who),
saving output tokens and avoiding any risk of paraphrasing before the
backfill.

- Add VerbatimExtractedFact / VerbatimFactExtractionResponse models
- Verbatim mode skips causal-relations section (nothing to relate causally)
- _extract_facts_from_chunk: allow missing 'what' in verbatim mode,
  set combined_text="" (backfilled by _collapse_to_verbatim)
- Update verbatim prompt to say DO NOT include 'what'

* feat(retain): add index_only extraction mode

Zero-LLM retain mode: chunks are stored as-is with no LLM call, no
entity extraction, and no temporal indexing. Embeddings still run for
semantic search. User-provided entities via RetainContent.entities
are the sole source of entity data.

Early return placed before the batch-API check so no LLM queue or
concurrency locks are acquired.

- Add "index_only" to RETAIN_EXTRACTION_MODES
- Add _extract_facts_index_only() with pure Python chunking path
- Add to UI dropdown and update description
- Update configuration.md with index_only docs and table entry
- Add unit test asserting zero token usage and exact text preservation

* feat(retain): add named retain strategies

Allows mixing extraction modes in a single bank via named strategies.
Each strategy is a set of hierarchical config overrides (extraction_mode,
chunk_size, entity_labels, entities_allow_free_form, etc.) applied on
top of the resolved bank config at retain time.

- retain_strategies: dict of strategy_name → config overrides (bank config)
- retain_default_strategy: default strategy when none specified (bank config)
- strategy field on /retain request: per-call override
- apply_strategy() in config_resolver applies overrides via dataclasses.replace()
- strategy propagates through retain_batch_async → _retain_batch_async_internal
  and through the async worker task payload
- Any hierarchical field is overridable per strategy, including entity_labels
  and entities_allow_free_form
- Docs updated with strategy configuration example and RRF fairness note
- Unit test for apply_strategy covering overrides, unknown strategy, and
  non-hierarchical field filtering

* feat(retain): add per-item strategy and strategy tests

- Add `strategy` field to `MemoryItem` so individual items in a retain
  request can override the request-level strategy
- Add `strategy` field to `FileRetainMetadata` for per-file strategy
  override in file retain requests
- Group memory items by effective strategy in `api_retain`; each group
  is processed as a separate batch, results are aggregated
- Thread strategy through `submit_async_file_retain` →
  `_handle_file_convert_retain` → retain task payload
- Add `operation_ids` to `RetainResponse` for async requests with
  mixed per-item strategies
- Add `test_strategy_overrides_extraction_mode_for_index_only`: unit
  test verifying a named strategy with index_only bypasses the LLM
- Add `test_retain_request_per_item_strategy_field`: unit test for
  per-item strategy grouping logic

* feat(ui): add retain strategies and default strategy to bank config UI

- Add StrategiesEditor component: per-strategy cards with name input and
  JSON overrides textarea; supports add/remove; validates JSON inline
- Add Default Strategy text input (retain_default_strategy)
- Update RetainEdits type and retainSlice() to include both new fields
- Regenerate OpenAPI spec (retain_strategies, retain_default_strategy,
  per-item strategy on MemoryItem/FileRetainMetadata, operation_ids on
  RetainResponse)

* refactor(ui): move retain strategies into its own dedicated config section

* feat(ui): improve retain strategies UX and add strategy to document dialog

- Strategy form now includes entity section (free form toggle + entity labels editor)
- Default strategy selector moved outside tab panel, above strategy chips
- Strategy tabs redesigned with underline indicator style for clarity
- Remove strategy confirms with AlertDialog
- Fix tab re-render bug when typing strategy name (skipSyncRef)
- Add strategy field to Add New Document dialog (text + per-file for uploads)
- File upload collapsible uses same Document/Tags/Source tabbed layout
- API: validate empty strategy names in config_resolver
- api.ts: add strategy field to retain and uploadFiles types

* fix: forward strategy through HTTP layer and SDK; add integration test

- route.ts: extract and forward `strategy` from request body to retainBatch
- TypeScript SDK: accept and forward `strategy` in retainBatch options and per-item
- config_resolver.py: validate empty strategy name keys on update
- bank-config-view.tsx: merge entity fields into RetainStrategyForm, redesign strategy tabs with underline style, add confirmation dialog for removal, fix tab-reset-on-typing with skipSyncRef, move default strategy selector outside panel
- bank-selector.tsx: add strategy field to Add Document dialog (per-file in tabbed collapsible)
- test_retain.py: add end-to-end integration test verifying named strategy application (index_only = 0 LLM tokens)

* fix: regenerate TypeScript client with strategy field in RetainRequest/MemoryItem

- Regenerate OpenAPI spec to include strategy field in RetainRequest and MemoryItem
- Regenerate TypeScript client from updated spec
- Add strategy to MemoryItemInput interface
- Remove (item as any) cast now that strategy is properly typed

* rename: index_only extraction mode → chunks

* remove top-level strategy from RetainRequest; strategy is per-item only

* fix(clients): update Go and Python generated clients with strategy/operation_ids fields

* fix(ci): update hierarchical field count, add strategy to Rust MemoryItem initializers

* fix(go-client): minimal targeted YAML updates for strategy/operation_ids fields
2026-03-17 18:08:25 +01:00

315 lines
13 KiB
Python

"""
Configuration resolution with hierarchical overrides.
Resolves config values through the hierarchy:
Global (env vars) → Tenant config (via extension) → Bank config (database)
Config values are resolved on every request to ensure consistency across
multiple API servers.
"""
import json
import logging
from dataclasses import asdict, replace
from typing import Any
import asyncpg
from hindsight_api.config import HindsightConfig, _get_raw_config, normalize_config_dict
from hindsight_api.engine.memory_engine import fq_table
from hindsight_api.extensions.tenant import TenantExtension
from hindsight_api.models import RequestContext
logger = logging.getLogger(__name__)
class ConfigResolver:
"""Resolves hierarchical configuration with tenant/bank overrides."""
def __init__(self, pool: asyncpg.Pool, tenant_extension: TenantExtension | None = None):
"""
Initialize config resolver.
Args:
pool: Database connection pool
tenant_extension: Optional tenant extension for tenant-level config and permissions
"""
self.pool = pool
self.tenant_extension = tenant_extension
self._global_config = _get_raw_config()
self._configurable_fields = HindsightConfig.get_configurable_fields()
self._credential_fields = HindsightConfig.get_credential_fields()
async def resolve_full_config(self, bank_id: str, context: RequestContext | None = None) -> HindsightConfig:
"""
Resolve full HindsightConfig for a bank with hierarchical overrides applied.
This is for INTERNAL USE ONLY. Returns the complete config object with all fields
including credentials and static fields. Use get_bank_config() for API responses.
Resolution order:
1. Global config (from environment variables)
2. Tenant config overrides (from TenantExtension.get_tenant_config())
3. Bank config overrides (from banks.config JSONB)
Args:
bank_id: Bank identifier
context: Request context for tenant config resolution
Returns:
Complete HindsightConfig with hierarchical overrides applied
"""
# Start with global config (all fields)
config_dict = asdict(self._global_config)
# Load tenant config overrides (if tenant extension available)
if self.tenant_extension and context:
try:
tenant_overrides = await self.tenant_extension.get_tenant_config(context)
if tenant_overrides:
# Normalize keys and filter to configurable fields only
normalized_tenant = normalize_config_dict(tenant_overrides)
configurable_tenant = {k: v for k, v in normalized_tenant.items() if k in self._configurable_fields}
config_dict.update(configurable_tenant)
logger.debug(
f"Applied tenant config overrides for bank {bank_id}: {list(configurable_tenant.keys())}"
)
except Exception as e:
logger.warning(f"Failed to load tenant config for bank {bank_id}: {e}")
# Load bank config overrides
bank_overrides = await self._load_bank_config(bank_id)
if bank_overrides:
config_dict.update(bank_overrides)
logger.debug(f"Applied bank config overrides for bank {bank_id}: {list(bank_overrides.keys())}")
# Return full config object (dataclass doesn't have __init__ that accepts kwargs, so we update the object)
# Create a new config instance by copying the global config and updating fields
resolved_config = HindsightConfig(**config_dict)
return resolved_config
async def get_bank_config(self, bank_id: str, context: RequestContext | None = None) -> dict[str, Any]:
"""
Get fully resolved config for a bank (filtered by permissions).
Resolution order:
1. Global config (from environment variables)
2. Tenant config overrides (from TenantExtension.get_tenant_config())
3. Bank config overrides (from banks.config JSONB)
Note: Config is resolved on every call (not cached) to ensure consistency
across multiple API servers.
SECURITY:
- Only returns configurable fields (excludes static/infrastructure fields)
- Filters out ALL credential fields (API keys, base URLs, etc.)
- Further filtered by tenant/bank permissions if extension provides them
Args:
bank_id: Bank identifier
context: Request context for tenant config resolution and permissions
Returns:
Dict of allowed configurable fields only (never includes credentials or static fields)
"""
# Resolve full config with all hierarchical overrides
resolved_config = await self.resolve_full_config(bank_id, context)
config_dict = asdict(resolved_config)
# SECURITY: Filter to only configurable fields (exclude static/infrastructure)
filtered = {k: v for k, v in config_dict.items() if k in self._configurable_fields}
# SECURITY: Remove ALL credential fields (API keys, base URLs, etc.)
filtered = {k: v for k, v in filtered.items() if k not in self._credential_fields}
# PERMISSIONS: Further filter based on tenant/bank permissions
if self.tenant_extension and context:
try:
allowed_fields = await self.tenant_extension.get_allowed_config_fields(context, bank_id)
if allowed_fields is not None: # None means "allow all"
filtered = {k: v for k, v in filtered.items() if k in allowed_fields}
logger.debug(
f"Applied permission filter for bank {bank_id}: allowed={len(allowed_fields)} fields, "
f"returned={len(filtered)} fields"
)
except Exception as e:
logger.warning(f"Failed to load permissions for bank {bank_id}: {e}")
return filtered
async def _load_bank_config(self, bank_id: str) -> dict[str, Any]:
"""
Load bank config overrides from banks.config JSONB column.
Args:
bank_id: Bank identifier
Returns:
Dict of config overrides (only configurable fields, normalized keys)
"""
try:
async with self.pool.acquire() as conn:
row = await conn.fetchrow(
f"""
SELECT config FROM {fq_table("banks")} WHERE bank_id = $1
""",
bank_id,
)
if row and row["config"]:
config_data = row["config"]
# Handle case where JSONB is returned as JSON string
if isinstance(config_data, str):
config_data = json.loads(config_data)
# Normalize keys (handle both env var format and Python field format)
normalized = normalize_config_dict(config_data)
# Only return overrides for configurable fields
return {k: v for k, v in normalized.items() if k in self._configurable_fields}
except Exception as e:
logger.error(f"Failed to load bank config for {bank_id}: {e}")
return {}
async def update_bank_config(
self, bank_id: str, updates: dict[str, Any], context: RequestContext | None = None
) -> None:
"""
Update bank configuration overrides (with permission checking).
Args:
bank_id: Bank identifier
updates: Dict of config field names to new values.
Keys can be in env var format (HINDSIGHT_API_LLM_PROVIDER)
or Python field format (llm_provider).
Only configurable fields are allowed.
context: Request context for permission checking
Raises:
ValueError: If attempting to override invalid/disallowed fields
"""
# Normalize keys
normalized_updates = normalize_config_dict(updates)
# SECURITY: Reject credential fields explicitly
credential_attempts = set(normalized_updates.keys()) & self._credential_fields
if credential_attempts:
raise ValueError(
f"Cannot set credential fields via API: {sorted(credential_attempts)}. "
f"Credentials (API keys, base URLs) must be set at server level only."
)
# Validate all fields are configurable
invalid_fields = set(normalized_updates.keys()) - self._configurable_fields
if invalid_fields:
static_fields = HindsightConfig.get_static_fields()
invalid_static = invalid_fields & static_fields
if invalid_static:
raise ValueError(
f"Cannot override static (server-level) fields: {sorted(invalid_static)}. "
f"Only configurable fields can be overridden per-bank. "
f"Configurable fields include: {sorted(list(self._configurable_fields)[:10])}... "
f"(total: {len(self._configurable_fields)} fields)"
)
else:
raise ValueError(
f"Unknown configuration fields: {sorted(invalid_fields)}. "
f"Valid configurable fields: {sorted(list(self._configurable_fields)[:10])}..."
)
# PERMISSIONS: Check tenant/bank permissions
if self.tenant_extension and context:
try:
allowed_fields = await self.tenant_extension.get_allowed_config_fields(context, bank_id)
if allowed_fields is not None: # None means "allow all"
disallowed = set(normalized_updates.keys()) - allowed_fields
if disallowed:
raise ValueError(
f"Not allowed to modify fields: {sorted(disallowed)}. "
f"Your permissions allow: {sorted(list(allowed_fields)[:10])}..."
if allowed_fields
else "Not allowed to modify fields: {sorted(disallowed)}. "
"Your permissions do not allow any config modifications."
)
except ValueError:
raise # Re-raise permission errors
except Exception as e:
logger.warning(f"Failed to check permissions for bank {bank_id}: {e}")
# Continue without permission check (fail open for backward compatibility)
# Validate retain_strategies: reject empty string keys
if "retain_strategies" in normalized_updates and normalized_updates["retain_strategies"]:
empty_keys = [k for k in normalized_updates["retain_strategies"] if not str(k).strip()]
if empty_keys:
raise ValueError(
"Strategy names must not be empty strings. Remove entries with empty names before saving."
)
# Merge with existing config (JSONB || operator)
async with self.pool.acquire() as conn:
await conn.execute(
f"""
UPDATE {fq_table("banks")}
SET config = config || $1::jsonb,
updated_at = now()
WHERE bank_id = $2
""",
json.dumps(normalized_updates),
bank_id,
)
logger.info(f"Updated bank config for {bank_id}: {list(normalized_updates.keys())}")
async def reset_bank_config(self, bank_id: str) -> None:
"""
Reset bank configuration to defaults (remove all overrides).
Args:
bank_id: Bank identifier
"""
async with self.pool.acquire() as conn:
await conn.execute(
f"""
UPDATE {fq_table("banks")}
SET config = '{{}}'::jsonb,
updated_at = now()
WHERE bank_id = $1
""",
bank_id,
)
logger.info(f"Reset bank config for {bank_id} to defaults")
def apply_strategy(config: HindsightConfig, strategy_name: str) -> HindsightConfig:
"""
Apply a named retain strategy's overrides on top of a resolved config.
A strategy is a named set of hierarchical field overrides stored in
config.retain_strategies. Any field in _HIERARCHICAL_FIELDS can be
overridden, including retain_extraction_mode, retain_chunk_size,
entity_labels, entities_allow_free_form, etc.
Unknown strategy names log a warning and return config unchanged.
Unknown or non-hierarchical fields in the strategy are silently ignored.
"""
strategies = config.retain_strategies or {}
if strategy_name not in strategies:
logger.warning(f"Unknown retain strategy '{strategy_name}', using resolved config as-is")
return config
overrides = strategies[strategy_name]
if not isinstance(overrides, dict):
logger.warning(f"Retain strategy '{strategy_name}' is not a dict, skipping")
return config
configurable = HindsightConfig.get_configurable_fields()
filtered = {k: v for k, v in overrides.items() if k in configurable}
if not filtered:
return config
logger.debug(f"Applying retain strategy '{strategy_name}': {list(filtered.keys())}")
return replace(config, **filtered)