Refactor for multi-provider architecture (#49)

Refactor for multi-provider architecture (#49)

Reorganizes the codebase to support multiple LLM providers with a clean,
extensible architecture. This is a preparatory refactor that improves
code organization without adding new provider support.

Architecture changes:
- Move masking utilities to src/masking/ (conflict-resolver, placeholders, context)
- Add provider-specific directories: src/providers/openai/
- Create shared provider utilities: src/providers/errors.ts, src/routes/utils.ts
- Extract OpenAI-specific code to src/masking/extractors/openai.ts
- Add service layer: src/services/pii.ts, src/services/secrets.ts
- Move stream transformer to provider directory

New patterns:
- Provider-agnostic text extraction with TextExtractor interface
- Shared error handling with ProviderError class
- Centralized timeout constants in src/constants/timeouts.ts
- Unified logging helpers in src/routes/utils.ts

Removed:
- src/services/decision.ts (logic moved to service layer)
- src/providers/openai-client.ts (replaced by src/providers/openai/client.ts)

All 219 tests pass.