2.4 KiB
2.4 KiB
1. Run State Primitives
- 1.1 Implement structurally immutable RunContext with explicit identity, deadline, cancellation, budget, retry policy, and lifecycle handles.
- 1.2 Implement first-reason-wins cancellation with resource callbacks and first-terminal-wins Run lifecycle.
- 1.3 Add Run identity, cancellation, and terminal race tests with a controlled Clock.
2. Budget and Capacity
- 2.1 Implement validated caller-supplied RunBudgetLimits and thread-safe Model/Tool/per-Tool/Token accounting.
- 2.2 Implement atomic single-Run byte capacity reservation with no partial update on rejection.
- 2.3 Add budget tests for consistent counters, actual Token recording, concurrent reservations, and exhaustion details.
3. Harness Core
- 3.1 Implement DiagnosisHarnessCore Run creation, active/deadline checks, budget gates, explicit cancellation, and success/failure completion.
- 3.2 Add Fake Model/Tool tests proving explicit synchronous/asynchronous RunContext propagation and cancellation/deadline/budget terminal outcomes.
4. Retry Boundary
- 4.1 Implement typed RetryFailure, bounded RetryPolicy, strict HarnessRetryPolicies, RetryAttempt, and RetryExecutionException.
- 4.2 Implement HarnessRetryExecutor with per-attempt active checks and attempt recording, without backoff, recursion, or hidden loops.
- 4.3 Add Fake Router/Tool/SemanticGuard retry tests for allowed technical retry, one-attempt policies, cancellation between attempts, and non-retryable outcomes.
5. Tool Store Foundations
- 5.1 Implement configurable ToolCallKeyFactory with exact framework ID preservation and safe-segment validation.
- 5.2 Add key factory tests covering exact key format, blank/unsafe/oversized segments, and no generated fallback ID.
6. Hidden Retry Configuration
- 6.1 Set
spring.ai.retry.max-attemptsto 1 without changing Model routing or provider configuration. - 6.2 Add a focused YAML configuration test proving the hidden Spring AI retry override.
7. Verification
- 7.1 Run focused Harness Core, retry, budget, key/capacity, and retry configuration tests.
- 7.2 Run stage 0/1 Harness and ACI contract tests plus existing ChatController test as regression coverage.
- 7.3 Verify new production code has no ThreadLocal/current-holder usage and current Chat/AIOps/Controller/JPA/Redis call sites remain unchanged.