hmharness 自进化证据

本页由 scripts/export-evidence.cjs 从 HMH_HOME 的真实日志生成,数字只来自文件,缺席标注为 absent。协议见 docs/SELFFEED.md;原始数据在 raw/。

窗口:2026-08-26T17:42:17.903Z → 2026-09-14T07:04:05.750Z · 生成于 2026-09-14T08:44:53.339Z

⚠ 外推性声明:当前数据全部来自自设任务(scripts/selffeed-tasks.json,作者编写),bench 用例同源。进化系统在此人造适应度景观上的表现不代表其在真实外部开发者任务上的效果。外推性待第一批外部用户数据验证。

每日进化轮次

日期	轮次
2026-08-26	2
2026-08-27	1
2026-08-29	1
2026-09-02	2
2026-09-03	1
2026-09-04	2
2026-09-05	1
2026-09-07	11
2026-09-08	22
2026-09-09	13
2026-09-10	12
2026-09-11	10
2026-09-12	5
2026-09-13	7
2026-09-14	4

技能判例(晋升/拒绝,含理由——诚实优先)

日期	技能	判定	理由
2026-09-14	harmony-feature-module-shell-completion	promoted	no regression (train 100% vs 100%, holdout 58%; floor ≥60%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-14	harmony-schema-check-restore-verification	promoted	no regression (train 100% vs 100%, holdout 58%; floor ≥60%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-14	harmony-project-multipage-router-scaffold	rejected	below quality floor: pass rate 0.5 < min 0.6 (non-regression vs a weak baseline 0.5 is not good enough)
2026-09-14	harmony-emulator-state-verification	rejected	below quality floor: pass rate 0.5 < min 0.6 (non-regression vs a weak baseline 0.5 is not good enough)
2026-09-14	harmony-build-doctor-windows-invocation	promoted	no regression (train 100% vs 100%, holdout 58%; floor ≥60%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-14	harmony-project-create-page-baseline	promoted	no regression (train 100% vs 100%, holdout 58%; floor ≥60%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-14	harmony-local-ui-baseline-check	promoted	no regression (train 100% vs 100%, holdout 50%; floor ≥60%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-14	harmony-emulator-state-ground-truth	promoted	no regression (train 100% vs 100%, holdout 50%; floor ≥60%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-13	(budget)	error	daily cycle limit reached (6/4 today) - skipped
2026-09-13	(budget)	error	daily cycle limit reached (5/4 today) - skipped
2026-09-13	(budget)	error	daily cycle limit reached (4/4 today) - skipped
2026-09-13	hmharness-session-log-search	promoted	no regression (train 100% vs 100%, holdout 50%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-13	harmony-codelinter-preflight	promoted	no regression (train 100% vs 100%, holdout 50%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-13	windows-codelinter-direct-invocation	promoted	no regression (train 100% vs 100%, holdout 46%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-13	deveco-studio-windows-major-upgrade-migration	promoted	no regression (train 100% vs 100%, holdout 46%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-13	kaihongos-vmware-vmx-pci-fix	promoted	no regression (train 100% vs 100%, holdout 50%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-13	windows-git-gh-shim-proxy-fix	promoted	no regression (train 100% vs 100%, holdout 50%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-12	harmony-api-lookup-disk-crosscheck	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-12	harmony-emulator-ui-regression-evidence-loop	promoted	no regression (train 50% vs 50%, holdout 0%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-12	harmony-api-sdk-declaration-crosscheck	promoted	no regression (train 50% vs 50%, holdout 0%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-12	harmony-api-lookup-blindspot-workaround	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-11	continue-hmharness-workflow	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-11	windows-installer-hash-signature-verification-fallback	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-11	harmony-failure-environment-triage	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-11	harmony-vision-provider-capability-marking	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-11	harmony-emulator-ui-regression-loop	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-11	windows-self-media-publishing-toolbox	promoted	no regression (train 50% vs 50%, holdout 0%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-11	continue-hmharness-conversation-workflow	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-11	windows-large-vision-request-payload-file	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-11	harmony-vision-false-negative-triage	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-11	harmony-vision-ui-regression-fallback	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-11	harmony-vision-provider-routing-fix	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-11	harmony-uitest-layout-ground-truth	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-10	continue-hmharness-conversation-workflow	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-10	windows-browser-publish-preflight	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-10	browser-automation-preflight	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-10	read-verify-file-workflow	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion); previous version archived
2026-09-10	harmony-worktree-runtime-reverify	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-10	harmony-runtime-log-verification	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-10	harmony-device-screenshot-verification	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-10	read-verify-file-workflow	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion); previous version archived
2026-09-10	read-verify-file-workflow	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion); previous version archived
2026-09-10	harmony-worktree-resume-reverify	promoted	no regression (train 50% vs 50%, holdout 0%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-10	serialize-same-file-edits	promoted	no regression (train 50% vs 50%, holdout 0%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-10	read-verify-file-workflow	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion); previous version archived
2026-09-10	harmony-device-test-explicit-bundle	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-10	truncated-verify-path-resolution	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-10	turn-budget-aware-verification	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-09	network-preflight-for-harmony-tools	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-09	windows-file-path-verification	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-09	read-verify-file-workflow	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-09	arkui-scroll-verify-pattern	promoted	no regression (train 100% vs 50%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-09	verify-task-turn-budget-gating	promoted	no regression (train 100% vs 50%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-09	continue-hmharness-conversation-workflow	promoted	no regression (train 50% vs 50%, holdout 0%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-09	continue-hmharness-conversation-workflow	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-09	windows-worktree-path-preflight	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-09	verify-staged-task-runner	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-09	codexhost-bridge-stuck-thinking	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-09	continue-hmharness-conversation-workflow	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)
2026-09-09	harmony-staged-task-executor	promoted	no regression (train 100% vs 100%, holdout 100%) - promoted to CANARY (20% sessions, impact-gated full promotion)

被拒候选存档(Pareto 池)

日期	候选	拒因
	harmony-sdk-version-build-failure-triage	below quality floor (0.50 < 0.6)
	harmony-hap-page-registry-verification	below quality floor (0.50 < 0.6)
	harmony-project-multipage-router-scaffold	below quality floor (0.50 < 0.6)
	harmony-emulator-state-verification	below quality floor (0.50 < 0.6)

最近洞察

日期	洞察
2026-09-14	{"time":"2026-09-14T08:40:47.415Z","session":"2026-09-14T08-39-33-zpmljc","task":"Use harmony_api_lookup for five symbols YOU are least sure about (pick genuine
2026-09-14	{"time":"2026-09-14T07:41:50.062Z","session":"2026-09-14T07-40-00-a3kjo3","task":"knowledge refresh","outcome":"ok","turns":20,"toolUses":36,"toolsUsed":["run_c
2026-09-14	{"time":"2026-09-14T07:04:05.745Z","session":"2026-09-14T07-01-03-n9h6we","task":"Refresh the static knowledge pipeline (hmh knowledge refresh - check 'hmh help
2026-09-14	{"time":"2026-09-14T05:24:31.720Z","session":"2026-09-14T05-23-49-r8ov1x","task":"On SelfFeedN (G:/hmharness-selffeed/SelfFeedN): backup build-profile.json5, th
2026-09-14	{"time":"2026-09-14T05:20:31.297Z","session":"2026-09-14T05-19-52-i08sss","task":"Scaffold a HarmonyOS app SelfFeedM in G:/hmharness-selffeed with a home page p
2026-09-14	{"time":"2026-09-14T03:19:22.203Z","session":"2026-09-14T03-18-52-m6gshi","task":"On SelfFeedN (G:/hmharness-selffeed/SelfFeedN): copy entry/src/main/module.jso
2026-09-14	{"time":"2026-09-14T03:05:49.224Z","session":"2026-09-14T03-05-17-86134d","task":"Run harmony_project_profile on SelfFeedN (G:/hmharness-selffeed/SelfFeedN) and
2026-09-14	{"time":"2026-09-14T03:00:46.493Z","session":"2026-09-14T02-59-15-brs4pw","task":"Scaffold a fresh HarmonyOS app named SelfFeedN in G:/hmharness-selffeed with t

技能清单

active:

• browser-harness
• cangjie-win-static-pitfalls
• cjpm-build-repair
• computer-use
• delegate-task
• graphify
• gsap-core
• gsap-frameworks
• gsap-performance
• gsap-plugins
• gsap-react
• gsap-scrolltrigger
• gsap-skills
• gsap-timeline
• gsap-utils
• hdc-device-ops
• skill-discovery
• video-shotcraft
• vpn-manager
• browser-automation-preflight
• file-op-error-recovery
• harmony-device-screenshot-verification
• harmony-ops-flow
• harmony-runtime-log-verification
• harmony-toolchain-report
• harmony-uitest-layout-ground-truth
• harmony-vision-provider-routing-fix
• harmony-vision-ui-regression-fallback
• harmony-worktree-runtime-reverify
• network-preflight-for-harmony-tools
• safe-file-ops
• safe-path-existence-check
• turn-budget-aware-verification
• turn-budget-checkpointing
• windows-browser-publish-preflight
• windows-command-compatibility
• windows-file-path-verification

canary:

• deveco-studio-windows-major-upgrade-migration
• harmony-build-doctor-windows-invocation
• harmony-codelinter-preflight
• harmony-device-test-explicit-bundle
• harmony-emulator-state-ground-truth
• harmony-feature-module-shell-completion
• harmony-local-ui-baseline-check
• harmony-project-create-page-baseline
• harmony-schema-check-restore-verification
• harmony-vision-false-negative-triage
• harmony-worktree-resume-reverify
• hmharness-session-log-search
• kaihongos-vmware-vmx-pci-fix
• serialize-same-file-edits
• truncated-verify-path-resolution
• windows-codelinter-direct-invocation
• windows-git-gh-shim-proxy-fix
• windows-large-vision-request-payload-file
• windows-self-media-publishing-toolbox

draft:

• api-endpoint-connectivity-check
• arkui-scroll-verify-pattern
• codexhost-bridge-stuck-thinking
• codexhost-offline-upgrade
• codexhost-source-merge-upgrade
• codexhost-streaming-bridge
• codexhost-upstream-merge-workflow
• continue-hmharness-conversation-workflow
• continue-hmharness-workflow
• harmony-api-lookup-blindspot-workaround
• harmony-api-lookup-disk-crosscheck
• harmony-api-sdk-declaration-crosscheck
• harmony-api-symbol-verification
• harmony-arkts-symbol-guard
• harmony-emulator-ui-regression-evidence-loop
• harmony-emulator-ui-regression-loop
• harmony-failure-environment-triage
• harmony-hap-path-resolution
• harmony-launch-install-preflight
• harmony-md-task-executor
• harmony-mock-backend-smoke-test
• harmony-schema-lint-build-loop
• harmony-sdk-symbol-verification
• harmony-staged-task-executor
• harmony-staged-verify-executor
• harmony-tool-failure-env-probe
• harmony-toolchain-preflight
• harmony-verification-task-runner
• harmony-vision-provider-capability-marking
• harmony-windows-tool-path-resolution
• harmony-windows-toolchain-preflight
• harmony-windows-verify-file-read
• harmony-windows-worktree-tool-path-preflight
• harmony-worktree-path-discovery
• hmh-noninteractive-execution
• hmh-noninteractive-execution-in-codexhost
• hmharness-memory-json-init
• mcp-http-endpoint-config
• read-verify-file-workflow
• scoped-verification-stage-guard
• self-introduction-workflow
• verify-before-execution-workflow
• verify-before-read-workflow
• verify-staged-task-runner
• verify-task-turn-budget-gating
• windows-command-compat-workflow
• windows-curl-download-retry
• windows-harmony-toolchain-path-resolution
• windows-installer-hash-signature-verification-fallback
• windows-process-port-recovery
• windows-tool-failure-alternative-strategy
• windows-worktree-path-preflight