feat(context): enhance timeout handling, tenant isolation, and budget management

- Added timeout enforcement for token counting, scoring, and compression with detailed error handling.
- Introduced tenant isolation in context caching using project and agent identifiers.
- Enhanced budget management with stricter checks for critical context overspending and buffer limitations.
- Optimized per-context locking with cleanup to prevent memory leaks in concurrent environments.
- Updated default assembly timeout settings for improved performance and reliability.
- Improved XML escaping in Claude adapter for safety against injection attacks.
- Standardized token estimation using model-specific ratios.
This commit is contained in:
2026-01-04 15:52:50 +01:00
parent 2bea057fb1
commit 1628eacf2b
10 changed files with 271 additions and 175 deletions

View File

@@ -212,7 +212,10 @@ class ContextEngine:
# Check cache if enabled
fingerprint: str | None = None
if use_cache and self._cache.is_enabled:
fingerprint = self._cache.compute_fingerprint(contexts, query, model)
# Include project_id and agent_id for tenant isolation
fingerprint = self._cache.compute_fingerprint(
contexts, query, model, project_id=project_id, agent_id=agent_id
)
cached = await self._cache.get_assembled(fingerprint)
if cached:
logger.debug(f"Cache hit for context assembly: {fingerprint}")