@miller-tech/uap 1.20.33 → 1.20.35

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (41) hide show
  1. package/config/model-profiles/qwen35.json +6 -5
  2. package/dist/.tsbuildinfo +1 -1
  3. package/dist/bin/cli.js +6 -1
  4. package/dist/bin/cli.js.map +1 -1
  5. package/dist/cli/hooks.js +30 -7
  6. package/dist/cli/hooks.js.map +1 -1
  7. package/dist/cli/policy.d.ts.map +1 -1
  8. package/dist/cli/policy.js +26 -0
  9. package/dist/cli/policy.js.map +1 -1
  10. package/dist/index.d.ts +15 -1
  11. package/dist/index.d.ts.map +1 -1
  12. package/dist/index.js +14 -0
  13. package/dist/index.js.map +1 -1
  14. package/dist/types/index.d.ts +20 -0
  15. package/dist/types/index.d.ts.map +1 -1
  16. package/dist/types/index.js +20 -0
  17. package/dist/types/index.js.map +1 -1
  18. package/docs/AGENTS.md +423 -0
  19. package/docs/AGENTS.md</path>CLAUDE.md</path>/home/cogtek/dev/miller-tech/universal-agent-protocol/docs/INDEX.md</path>/home/cogtek/dev/miller-tech/universal-agent-protocol/docs/reference/API_REFERENCE.md</path>/home/cogtek/dev/miller-tech/universal-agent-protocol/docs/reference/UAP_CLI_REFERENCE.md</path>src/index.ts</path>/src/cli/worktree.ts</path>/src/coordination/deploy-batcher.ts</path>/src/policies/policy-gate.ts</path>/src/memory/model-router.ts</path>/src/memory/embeddings.ts</path>/src/models/types.ts</path>/src/types/coordination.ts</path>/src/utils/logger.ts</path>/src/utils/config-loader.ts</path>/src/utils/performance-monitor.ts</path>/src/utils/concurrency.ts</path>/src/utils/concurrency-pool.ts</path>/src/utils/string-similarity.ts</path>/src/utils/rate-limiter.ts</path>/src/utils/system-resources.ts</path>/src/utils/adaptive-cache.ts</path>/src/utils/lazy-imports.ts</path>/src/utils/merge-claude-md.ts</path>/src/utils/stopwords.ts</path>/src/utils/config-loader.ts</path>/src/utils/performance-monitor.ts</path>/src/utils/concurrency.ts</path>/src/utils/concurrency-pool.ts</path>/src/utils/string-similarity.ts</path>/src/utils/rate-limiter.ts</path>/src/utils/system-resources.ts</path>/src/utils/adaptive-cache.ts</path>/src/utils/lazy-imports.ts</path>/src/utils/merge-claude-md.ts</path>/src/utils/stopwords.ts</path> +433 -0
  20. package/docs/DOCUMENTATION_AUDIT_REPORT.md +131 -0
  21. package/docs/GETTING_STARTED.md +288 -0
  22. package/docs/INDEX.md +272 -42
  23. package/docs/PROJECT_ANALYSIS_REPORT.md +510 -0
  24. package/docs/architecture/SYSTEM_ANALYSIS.md +220 -1003
  25. package/docs/blog/local-coding-agents.md +266 -0
  26. package/docs/blog/x-thread.md +254 -0
  27. package/docs/deployment/DEPLOY_BATCHER_ANALYSIS.md +15 -647
  28. package/docs/getting-started/OVERVIEW.md +10 -30
  29. package/docs/getting-started/SETUP.md +183 -9
  30. package/docs/pr/UPSTREAM_PRS.md +424 -0
  31. package/docs/reference/CONFIGURATION.md +208 -0
  32. package/docs/reference/DATABASE_SCHEMA.md +344 -0
  33. package/docs/reference/PATTERN_LIBRARY.md +636 -0
  34. package/package.json +1 -1
  35. package/templates/hooks/uap-policy-gate.sh +36 -0
  36. package/tools/agents/claude_local_agent.py +92 -0
  37. package/tools/agents/config/qwen3.5-enhanced.jinja +187 -0
  38. package/tools/agents/opencode_uap_agent.py +3 -0
  39. package/tools/agents/scripts/anthropic_proxy.py +1748 -76
  40. package/tools/agents/tests/test_anthropic_proxy_streaming.py +64 -8
  41. package/tools/agents/uap_agent.py +1 -1
package/config/model-profiles/qwen35.json CHANGED
@@ -47,11 +47,12 @@
47
47
  },
48
48
  "speculative_decoding": {
49
49
  "enabled": true,
50
- "draft_model": "Qwen3.5-0.8B-Q8_0",
51
- "draft_max": 16,
52
- "draft_min": 3,
53
- "draft_p_min": 0.75,
54
- "_comment": "Enable for 2-3x speedup in tokens/sec. Uses Qwen3.5-0.8B-Q8_0 as draft model to propose tokens. Set enabled=true and provide draft model GGUF path. Current setup: main model 17GB, draft model 0.8GB, KV cache ~2-3GB."
50
+ "type": "ngram-mod",
51
+ "ngram_size_n": 3,
52
+ "draft_max": 3,
53
+ "draft_min": 1,
54
+ "draft_p_min": 0.80,
55
+ "_comment": "ngram-mod self-speculation (no draft model). Draft-model spec crashes on Qwen3.5 due to hybrid memory (GDN) seq_add incompatibility. ngram-mod avoids this and gives stable ~33 tok/s."
55
56
  },
56
57
  "_comment": "KV q8/q4 split saves ~60% KV VRAM. Flash attn gives 1.5-2x speed on long context."
57
58
  },