v0.1.0

What's Changed

• feat: add logprobs comparison tool (M2) by @hlin99 in #2
• chore: mark M2 as complete in ROADMAP.md by @hlin99 in #3
• feat: add KV cache comparison tool (M3) by @hlin99 in #5
• chore: mark M3 as complete in ROADMAP.md by @hlin99 in #6
• feat: add automated diagnostic pipeline (M4) by @hlin99 in #8
• feat: add output comparison utilities (M5) by @hlin99 in #10
• feat: add batch dataset comparison (M6) by @hlin99 in #13
• feat: add xPyD ecosystem integration (M7) by @hlin99 in #15
• docs: mark M7 as complete by @hlin99 in #16
• feat: HTML report generation (M8) by @hlin99 in #18
• docs: mark M8 complete in ROADMAP.md by @hlin99 in #19
• feat: add TOML configuration file support by @hlin99 in #21
• feat: add CLI config integration tests, mark M9 complete by @hlin99 in #23
• feat: add --json export for batch-compare and --version flag by @hlin99 in #25
• docs: mark M10 as complete by @hlin99 in #26
• feat: HTTP retry with exponential backoff for endpoint requests by @hlin99 in #28
• feat: add Rich progress bars for batch comparison by @hlin99 in #30
• feat: add streaming output comparison (M13) by @hlin99 in #32
• feat: add endpoint health check (M14) by @hlin99 in #34
• feat: M15 - CSV Export with truncated prompt column by @hlin99 in #36
• feat: Token Timing Analysis (M16) by @hlin99 in #38
• docs: mark M16 complete, add M17 milestone by @hlin99 in #39
• feat: Prompt Template Support (M17) by @hlin99 in #41
• docs: mark M17 complete by @hlin99 in #42
• feat: environment variable support for credentials and endpoints by @hlin99 in #44
• feat: add Markdown report export for batch-compare (M19) by @hlin99 in #46
• feat: add dry run mode for batch-compare by @hlin99 in #48
• feat: add regression detection for batch comparison runs by @hlin99 in #50
• feat: tolerance-based matching for batch comparison (M22) by @hlin99 in #52
• feat: selective sample rerun for batch comparison (M23) by @hlin99 in #54
• feat: M24 - Sampling Parameter Support (temperature, top_p, seed) by @hlin99 in #56
• feat: M25 - Named Profiles (Presets) by @hlin99 in #58
• feat: M26 - Multi-run aggregation for persistent vs flaky divergence detection by @hlin99 in #60
• feat: configurable HTTP timeout for batch-compare by @hlin99 in #62
• feat: add logging & verbosity control (--verbose / --quiet) by @hlin99 in #64
• feat: Watch Mode — Continuous Divergence Monitoring by @hlin99 in #66
• feat: snapshot baseline capture & replay (M30) by @hlin99 in #68
• feat: CI-friendly fail threshold for batch-compare by @hlin99 in #70
• feat: Multi-Target Comparison (M32) by @hlin99 in #72
• feat: request ID tracking for API call correlation by @hlin99 in #74
• feat: prompt deduplication for batch comparison by @hlin99 in #76
• feat: wire --no-request-id CLI flag to run_batch enable_request_ids by @hlin99 in #78
• feat: shell completion generation for bash/zsh/fish by @hlin99 in #80
• feat: response caching for batch comparison by @hlin99 in #82
• feat: M37 — Result History & Trend Tracking by @hlin99 in #84
• feat(benchmark): add endpoint latency benchmarking (M38) by @hlin99 in #86
• feat(config): Configuration Validation & Init Command (M39) by @hlin99 in #88
• feat(dataset): CSV and JSON Array Format Support (M40) by @hlin99 in #90
• feat: M41 — Webhook Notifications for Divergence Alerts by @hlin99 in #92
• feat: M42 — Sample Filtering for Batch Reports by @hlin99 in #94
• feat: M43 Report Diff — Side-by-Side Batch Report Comparison by @hlin99 in #96
• feat: request rate limiting with token bucket algorithm (M44) by @hlin99 in #98
• feat: custom output normalizers for batch comparison (M45) by @hlin99 in #100
• feat: Top-K Logprob Distribution Analysis (M46) by @hlin99 in #102
• feat: auto-bisect divergence by context length (M47) by @hlin99 in #104
• feat(summary): add compact summary command (M48) by @hlin99 in #106
• feat: divergence pattern clustering for batch reports (M49) by @hlin99 in #108
• feat: JUnit XML export for batch-compare (M50) by @hlin99 in #110
• feat: add history purge command (M51) by @hlin99 in #112
• feat: Sample Deep-Dive Explain Command (M52) by @hlin99 in #114
• feat: confidence intervals for divergence rate (M53) by @hlin99 in #116
• feat: add sample annotation for batch reports (M54) by @hlin99 in #118
• feat: Model Fingerprinting via Deterministic Probes (M55) by @hlin99 in #120
• feat(batch_compare): report schema versioning and load_report() by @hlin99 in #122
• feat: M57 — Endpoint Response Validation (Schema Check) by @hlin99 in #124
• feat: M58 — Dataset Statistics Command by @hlin99 in #126
• feat: M59 — Cost Estimation from API Usage by @hlin99 in #128
• feat: M60 — Cost Tracking Integration into Batch Compare by @hlin99 in #130
• feat: add output truncation detection (M61) by @hlin99 in #132
• feat: add reproducibility score for multi-run consistency measurement (M62) by @hlin99 in #134
• feat(env): add XPYD_ACC_MAX_TOKENS and XPYD_ACC_CONCURRENCY env vars by @hlin99 in #136
• feat: M64 — Checkpoint Resume for Batch Comparison by @hlin99 in #138
• feat: M65 — Checkpoint Integration into Batch Compare by @hlin99 in #140
• feat(retry): add retry statistics reporting (M66) by @hlin99 in #142
• feat(headers): add custom HTTP headers for API requests (M67) by @hlin99 in #144
• feat: M68 — Endpoint A/B Testing with Statistical Significance by @hlin99 in #146
• feat: M69 — Concurrency Scaling Analysis by @hlin99 in #148
• feat: M70 — Output Entropy Analysis by @hlin99 in #150
• feat: M71 — Output Length Bias Detection by @hlin99 in #152
• feat: add prompt sensitivity analysis (M72) by @hlin99 in #154
• docs: add deliverables — guide, iteration record, diagnostic script by @hlin99 in #156
• setup: add review policy and auto-assign reviewers by @hlin99 in #157
• feat(M73): Multi-Model Comparison in Single Batch Run by @hlin99 in #159
• refactor: split cli.py into cli/ package (#155) by @hlin99 in #160
• feat(M74): divergence root cause heuristics (#161) by @hlin99 in #162
• feat(M75): side-by-side token diff viewer (#163) by @hlin99 in #164
• feat(M76): report dashboard server (#165) by @hlin99 in #166
• feat(M77): Prometheus metrics export (#167) by @hlin99 in #168
• feat(M78): Grafana Dashboard Template Export (#169) by @hlin99 in #170
• feat(M79): Parallel Multi-Dataset Batch Run (#171) by @hlin99 in https://github.com/xPy...