harness-everything 0.22.1 → 0.24.0

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 (38) hide show
  1. package/.claude-plugin/marketplace.json +1 -1
  2. package/.claude-plugin/plugin.json +1 -1
  3. package/CHANGELOG.md +19 -0
  4. package/benchmarks/fixtures/system-one-holdout-draft.json +2039 -0
  5. package/benchmarks/fixtures/system-one-holdout-reviews.json +1587 -0
  6. package/benchmarks/fixtures/system-one-holdout.json +7315 -0
  7. package/benchmarks/results/system-one/labeler-holdout-check-2026-09-23/README.md +55 -0
  8. package/benchmarks/results/system-one/labeler-holdout-check-2026-09-23/report.json +1104 -0
  9. package/benchmarks/results/system-one/lexical-baseline-reviewed-holdout-2026-09-23/README.md +47 -0
  10. package/benchmarks/results/system-one/lexical-baseline-reviewed-holdout-2026-09-23/report.json +5222 -0
  11. package/ci/fixtures/system-one-resident-stub.py +3 -0
  12. package/ci/mechanism-system-one-collect.test.js +129 -0
  13. package/ci/mechanism-system-one-corpus.test.js +154 -0
  14. package/ci/mechanism-system-one-label.test.js +101 -0
  15. package/ci/mechanism-system-one-resident.test.js +36 -2
  16. package/ci/mechanism-system-one-router.test.js +13 -0
  17. package/ci/mechanism-system-one-train.test.js +82 -0
  18. package/ci/system-one-train-test.py +55 -0
  19. package/docs/system-one-corpus.md +103 -0
  20. package/docs/system-one-routing.md +10 -2
  21. package/docs/system-one-training.md +121 -0
  22. package/harness-everything/SKILL.md +1 -1
  23. package/harness-everything/scripts/system-one/provider.js +12 -5
  24. package/harness-everything/scripts/system-one/router.js +1 -1
  25. package/opencode-plugin/plugin.json +1 -1
  26. package/package.json +1 -1
  27. package/plugins/harness-everything/.codex-plugin/plugin.json +1 -1
  28. package/plugins/harness-everything/plugin.json +1 -1
  29. package/plugins/harness-everything/skills/harness-everything/SKILL.md +1 -1
  30. package/plugins/harness-everything/skills/harness-everything/scripts/system-one/provider.js +12 -5
  31. package/plugins/harness-everything/skills/harness-everything/scripts/system-one/router.js +1 -1
  32. package/sbom.cdx.json +7 -7
  33. package/scripts/evaluate-system-one.js +1 -1
  34. package/scripts/system-one-calibrate.js +44 -0
  35. package/scripts/system-one-collect.js +196 -0
  36. package/scripts/system-one-corpus.js +99 -0
  37. package/scripts/system-one-label.js +144 -0
  38. package/scripts/system-one-train.py +168 -0
package/.claude-plugin/marketplace.json CHANGED
@@ -10,7 +10,7 @@
10
10
  "name": "harness-everything",
11
11
  "source": "./",
12
12
  "description": "Harness OS: an orchestrated agent operating system — tier routing, circuit breaker guardrails, verification gates, WAL session memory, and self-evolving workspace rules.",
13
- "version": "0.22.1",
13
+ "version": "0.24.0",
14
14
  "author": {
15
15
  "name": "Miya Daniel"
16
16
  },
package/.claude-plugin/plugin.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "harness-everything",
3
3
  "description": "Harness OS: an orchestrated agent operating system — tier routing, circuit breaker guardrails, verification gates, WAL session memory, and self-evolving workspace rules.",
4
- "version": "0.22.1",
4
+ "version": "0.24.0",
5
5
  "author": {
6
6
  "name": "Miya Daniel"
7
7
  },
package/CHANGELOG.md CHANGED
@@ -2,6 +2,25 @@
2
2
 
3
3
  All notable changes to this project are documented in this file.
4
4
 
5
+ ## [0.24.0](https://github.com/dyphn1/Harness-everything/compare/v0.23.0...v0.24.0) (2026-09-23)
6
+
7
+ ### Features
8
+
9
+ * **router:** apply calibrated system one acceptance thresholds ([61841a2](https://github.com/dyphn1/Harness-everything/commit/61841a28afc0c8ba0163625b28974962f0cf78f7)), closes [#233](https://github.com/dyphn1/Harness-everything/issues/233)
10
+ * **router:** collect local owner prompts for system one training ([c84d543](https://github.com/dyphn1/Harness-everything/commit/c84d5433e2d152fd57618b24691c75a50e1fc3c8)), closes [#233](https://github.com/dyphn1/Harness-everything/issues/233)
11
+ * **router:** label system one training prompts with a checked llm ([5056a9a](https://github.com/dyphn1/Harness-everything/commit/5056a9a7abc2820dc6b9eedf8266bd39082afd8f)), closes [#233](https://github.com/dyphn1/Harness-everything/issues/233)
12
+ * **router:** train and calibrate the system one tier scorer ([cc26296](https://github.com/dyphn1/Harness-everything/commit/cc26296cd128cc75a74a5fbe2d3c8637068781b1)), closes [#233](https://github.com/dyphn1/Harness-everything/issues/233)
13
+
14
+ ### Bug Fixes
15
+
16
+ * **router:** record why system one labeling batches fail ([c6dd6f6](https://github.com/dyphn1/Harness-everything/commit/c6dd6f61b19020a95ccf0fbef30ac9d5113a69f4)), closes [#233](https://github.com/dyphn1/Harness-everything/issues/233)
17
+
18
+ ## [0.23.0](https://github.com/dyphn1/Harness-everything/compare/v0.22.1...v0.23.0) (2026-09-23)
19
+
20
+ ### Features
21
+
22
+ * **router:** assemble the system one holdout from human review ([c877e9f](https://github.com/dyphn1/Harness-everything/commit/c877e9f5248ea413ce8252f98f672376c83ef534)), closes [#233](https://github.com/dyphn1/Harness-everything/issues/233)
23
+
5
24
  ## [0.22.1](https://github.com/dyphn1/Harness-everything/compare/v0.22.0...v0.22.1) (2026-09-23)
6
25
 
7
26
  ### Performance Improvements