From 017923aace92d1063df8eaff4297cfe81d7abd3e Mon Sep 17 00:00:00 2001 From: Agent Workbench Dev Date: Sun, 1 Nov 2026 21:25:15 +0800 Subject: [PATCH] chore: preserve sealed model wait evidence bytes --- .gitattributes | 3 + .../logs/model-wait-bind-package.txt | 2 +- .../logs/model-wait-build.txt | 40 ++--- .../logs/model-wait-contained-ui.txt | 12 +- .../logs/model-wait-formal-b-stage.txt | 2 +- .../logs/model-wait-formal-c-stage.txt | 2 +- .../logs/model-wait-formal-c-upgrade.txt | 2 +- .../logs/model-wait-formal-stage.txt | 2 +- .../logs/model-wait-formal-ui-b.txt | 2 +- .../logs/model-wait-formal-ui-c.txt | 2 +- .../logs/model-wait-initial.tap | 74 ++++----- .../logs/model-wait-long.txt | 2 +- .../logs/model-wait-owned-upgrade.txt | 2 +- .../logs/model-wait-package.txt | 140 +++++++++--------- .../logs/model-wait-protocol-ui.txt | 12 +- .../logs/model-wait-related.tap | 140 +++++++++--------- .../logs/model-wait-ui-scroll.txt | 12 +- .../logs/model-wait-ui.txt | 12 +- .../logs/model-wait-upgrade.tap | 62 ++++---- progress.md | 2 + 20 files changed, 266 insertions(+), 261 deletions(-) diff --git a/.gitattributes b/.gitattributes index 257c9a82..69a3ce1f 100644 --- a/.gitattributes +++ b/.gitattributes @@ -60,3 +60,6 @@ docs/engineering-evals-*-evidence/*.log binary docs/engineering-evals-*-evidence/**/*.blob binary docs/engineering-evals-*-evidence/*.blob binary docs/engineering-evals-*.json -text whitespace=blank-at-eol,blank-at-eof,space-before-tab,cr-at-eol + +docs/model-wait-release-evidence/** -text whitespace=blank-at-eol,blank-at-eof,space-before-tab,cr-at-eol +docs/model-wait-release-identity.json -text whitespace=blank-at-eol,blank-at-eof,space-before-tab,cr-at-eol diff --git a/docs/model-wait-release-evidence/logs/model-wait-bind-package.txt b/docs/model-wait-release-evidence/logs/model-wait-bind-package.txt index b13f7d9f..f7404b5e 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-bind-package.txt +++ b/docs/model-wait-release-evidence/logs/model-wait-bind-package.txt @@ -1 +1 @@ -{"success":true,"inputs":354,"compiled":22,"portableRoot":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.2-win-x64-20261101124548744"} +{"success":true,"inputs":354,"compiled":22,"portableRoot":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.2-win-x64-20261101124548744"} diff --git a/docs/model-wait-release-evidence/logs/model-wait-build.txt b/docs/model-wait-release-evidence/logs/model-wait-build.txt index 84c4ac55..fae8433a 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-build.txt +++ b/docs/model-wait-release-evidence/logs/model-wait-build.txt @@ -1,20 +1,20 @@ - -> local-agent-workbench@1.20.2 build -> tsc --noEmit && vite build && node scripts/build-mobile.mjs && node scripts/build-server.mjs - -vite v7.3.7 building client environment for production... -transforming... -✓ 1732 modules transformed. -rendering chunks... -computing gzip size... -dist-client/.vite/manifest.json 0.55 kB │ gzip: 0.22 kB -dist-client/index.html 0.58 kB │ gzip: 0.39 kB -dist-client/mobile.html 0.82 kB │ gzip: 0.46 kB -dist-client/assets/mobile-CNDnI_ru.css 11.92 kB │ gzip: 3.12 kB -dist-client/assets/desktop-B65VXbkr.css 147.58 kB │ gzip: 27.99 kB -dist-client/assets/mobile-DVWh54VU.js 24.31 kB │ gzip: 8.65 kB -dist-client/assets/x-Cc3T3VuL.js 225.51 kB │ gzip: 70.77 kB -dist-client/assets/desktop-DakkeVg6.js 322.94 kB │ gzip: 91.46 kB -✓ built in 1.17s -Mobile shell built: 3 allowed assets; API and project data are never cached. -Server bundle built. + +> local-agent-workbench@1.20.2 build +> tsc --noEmit && vite build && node scripts/build-mobile.mjs && node scripts/build-server.mjs + +vite v7.3.7 building client environment for production... +transforming... +✓ 1732 modules transformed. +rendering chunks... +computing gzip size... +dist-client/.vite/manifest.json 0.55 kB │ gzip: 0.22 kB +dist-client/index.html 0.58 kB │ gzip: 0.39 kB +dist-client/mobile.html 0.82 kB │ gzip: 0.46 kB +dist-client/assets/mobile-CNDnI_ru.css 11.92 kB │ gzip: 3.12 kB +dist-client/assets/desktop-B65VXbkr.css 147.58 kB │ gzip: 27.99 kB +dist-client/assets/mobile-DVWh54VU.js 24.31 kB │ gzip: 8.65 kB +dist-client/assets/x-Cc3T3VuL.js 225.51 kB │ gzip: 70.77 kB +dist-client/assets/desktop-DakkeVg6.js 322.94 kB │ gzip: 91.46 kB +✓ built in 1.17s +Mobile shell built: 3 allowed assets; API and project data are never cached. +Server bundle built. diff --git a/docs/model-wait-release-evidence/logs/model-wait-contained-ui.txt b/docs/model-wait-release-evidence/logs/model-wait-contained-ui.txt index 8c288d38..c1daebe2 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-contained-ui.txt +++ b/docs/model-wait-release-evidence/logs/model-wait-contained-ui.txt @@ -1,6 +1,6 @@ -PASS desktop saves seconds, preserves original pool/member and sends no model request -PASS invalid timeout rejected without saving -PASS saved values survive reload; narrow screen remains usable -PASS active request locks wait changes in both API and UI -PASS actual stalled stream shows exact idle reason, saves unknown use, never writes or retries -{"success":true,"directory":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-wait-ui-a700392c-c9d3-44a5-868a-976d0e5d8d7a","checks":5,"screenshots":4} +PASS desktop saves seconds, preserves original pool/member and sends no model request +PASS invalid timeout rejected without saving +PASS saved values survive reload; narrow screen remains usable +PASS active request locks wait changes in both API and UI +PASS actual stalled stream shows exact idle reason, saves unknown use, never writes or retries +{"success":true,"directory":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-wait-ui-a700392c-c9d3-44a5-868a-976d0e5d8d7a","checks":5,"screenshots":4} diff --git a/docs/model-wait-release-evidence/logs/model-wait-formal-b-stage.txt b/docs/model-wait-release-evidence/logs/model-wait-formal-b-stage.txt index 55ce006e..1bf5232e 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-formal-b-stage.txt +++ b/docs/model-wait-release-evidence/logs/model-wait-formal-b-stage.txt @@ -1 +1 @@ -{"success":false,"phase":"stage","output":".qa/model-wait-formal-b-stage.json","error":"AssertionError [ERR_ASSERTION]: sessionsSha256\n+ actual - expected\n\n+ '0ceeaa1dfd2efd10dc7e3536db689d3b17c88c4293dca4cecef118aca684bf1d'\n- '206f79d44152116ff4be90a12cb7f84ec6f8543fa854964e2763ee3f55c654f3'\n\n at compareOriginalState (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/desktop-f-state.mjs:47:116)\n at compareWaitState (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/model-wait-state.mjs:10:15)\n at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/model-wait-formal.mjs:44:115\n at process.processTicksAndRejections (node:internal/process/task_queues:104:5)"} +{"success":false,"phase":"stage","output":".qa/model-wait-formal-b-stage.json","error":"AssertionError [ERR_ASSERTION]: sessionsSha256\n+ actual - expected\n\n+ '0ceeaa1dfd2efd10dc7e3536db689d3b17c88c4293dca4cecef118aca684bf1d'\n- '206f79d44152116ff4be90a12cb7f84ec6f8543fa854964e2763ee3f55c654f3'\n\n at compareOriginalState (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/desktop-f-state.mjs:47:116)\n at compareWaitState (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/model-wait-state.mjs:10:15)\n at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/model-wait-formal.mjs:44:115\n at process.processTicksAndRejections (node:internal/process/task_queues:104:5)"} diff --git a/docs/model-wait-release-evidence/logs/model-wait-formal-c-stage.txt b/docs/model-wait-release-evidence/logs/model-wait-formal-c-stage.txt index d2eb7eb5..4c52259d 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-formal-c-stage.txt +++ b/docs/model-wait-release-evidence/logs/model-wait-formal-c-stage.txt @@ -1 +1 @@ -{"success":true,"phase":"staged-resume","eventCursor":6138,"records":3207} +{"success":true,"phase":"staged-resume","eventCursor":6138,"records":3207} diff --git a/docs/model-wait-release-evidence/logs/model-wait-formal-c-upgrade.txt b/docs/model-wait-release-evidence/logs/model-wait-formal-c-upgrade.txt index 2f6da91d..b3345391 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-formal-c-upgrade.txt +++ b/docs/model-wait-release-evidence/logs/model-wait-formal-c-upgrade.txt @@ -1 +1 @@ -{"success":true,"phase":"upgraded","output":".qa/model-wait-formal-c-upgrade.json"} +{"success":true,"phase":"upgraded","output":".qa/model-wait-formal-c-upgrade.json"} diff --git a/docs/model-wait-release-evidence/logs/model-wait-formal-stage.txt b/docs/model-wait-release-evidence/logs/model-wait-formal-stage.txt index 49368ee1..443e4276 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-formal-stage.txt +++ b/docs/model-wait-release-evidence/logs/model-wait-formal-stage.txt @@ -1 +1 @@ -{"success":false,"phase":"stage","output":".qa/model-wait-formal-stage.json","error":"AssertionError [ERR_ASSERTION]: Expected values to be strictly deep-equal:\n+ actual - expected\n\n+ undefined\n- {\n- modelResponseTimeoutMs: 300000,\n- modelStreamIdleTimeoutMs: 120000\n- }\n\n at compareWaitState (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/model-wait-state.mjs:7:12)\n at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/model-wait-formal.mjs:41:5\n at process.processTicksAndRejections (node:internal/process/task_queues:104:5)"} +{"success":false,"phase":"stage","output":".qa/model-wait-formal-stage.json","error":"AssertionError [ERR_ASSERTION]: Expected values to be strictly deep-equal:\n+ actual - expected\n\n+ undefined\n- {\n- modelResponseTimeoutMs: 300000,\n- modelStreamIdleTimeoutMs: 120000\n- }\n\n at compareWaitState (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/model-wait-state.mjs:7:12)\n at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/model-wait-formal.mjs:41:5\n at process.processTicksAndRejections (node:internal/process/task_queues:104:5)"} diff --git a/docs/model-wait-release-evidence/logs/model-wait-formal-ui-b.txt b/docs/model-wait-release-evidence/logs/model-wait-formal-ui-b.txt index 04359378..6ed94017 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-formal-ui-b.txt +++ b/docs/model-wait-release-evidence/logs/model-wait-formal-ui-b.txt @@ -1 +1 @@ -{"success":false,"results":2,"screenshots":4,"error":"page.screenshot: Timeout 30000ms exceeded.\nCall log:\n\u001b[2m - taking page screenshot\u001b[22m\n\u001b[2m - waiting for fonts to load...\u001b[22m\n\u001b[2m - fonts loaded\u001b[22m\n\n at capture (D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-wait-formal-ui.mjs:28:64)\n at inspect (D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-wait-formal-ui.mjs:33:9)\n at async file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/model-wait-formal-ui.mjs:61:109"} +{"success":false,"results":2,"screenshots":4,"error":"page.screenshot: Timeout 30000ms exceeded.\nCall log:\n\u001b[2m - taking page screenshot\u001b[22m\n\u001b[2m - waiting for fonts to load...\u001b[22m\n\u001b[2m - fonts loaded\u001b[22m\n\n at capture (D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-wait-formal-ui.mjs:28:64)\n at inspect (D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-wait-formal-ui.mjs:33:9)\n at async file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/model-wait-formal-ui.mjs:61:109"} diff --git a/docs/model-wait-release-evidence/logs/model-wait-formal-ui-c.txt b/docs/model-wait-release-evidence/logs/model-wait-formal-ui-c.txt index 16917df6..28bf9d89 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-formal-ui-c.txt +++ b/docs/model-wait-release-evidence/logs/model-wait-formal-ui-c.txt @@ -1 +1 @@ -{"success":true,"results":4,"screenshots":8} +{"success":true,"results":4,"screenshots":8} diff --git a/docs/model-wait-release-evidence/logs/model-wait-initial.tap b/docs/model-wait-release-evidence/logs/model-wait-initial.tap index f13849b9..85f2f8a6 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-initial.tap +++ b/docs/model-wait-release-evidence/logs/model-wait-initial.tap @@ -1,37 +1,37 @@ -✔ HTTP download preserves original malformed SSE bytes and artifact SHA instead of decoding invalid UTF8 (2426.5386ms) -✔ terminated SSE adapts empty optional tool arguments, retains the exact wire bytes and executes the validated batch once (2791.2168ms) -✔ reported SSE usage survives rejected required arguments "" without dispatching any tool (1584.8417ms) -✔ reported SSE usage survives rejected required arguments "{\"path\":" without dispatching any tool (1354.9623ms) -✔ reported SSE usage survives rejected required arguments "null" without dispatching any tool (1377.0252ms) -✔ a stream without DONE retains reported usage but cannot adapt or execute even an optional tool (1520.6525ms) -✔ a timeout after reasoning-only fragments creates one unknown receipt and never invents reported tokens (1597.1202ms) -✔ real Chat SSE carries UTF8 and split tool JSON; Runtime executes only after DONE, stores partial progress and original usage (2330.514ms) -✔ Responses typed SSE validates original item identity, terminal data, raw usage and tool result pair (2277.3525ms) -✔ incomplete network stream retains unknown attempt and never automatically switches pool or dispatches fragment tools (1590.889ms) -✔ stopping an active HTTP stream closes only original request and keeps partial text without executing tools (1390.7969ms) -✔ explicit streaming probe uses actual SSE despite unknown declaration and binds its own original attempt (700.3784ms) -✔ coalesced initial SSE events publish the latest partial state even when the upstream stays idle (1398.8886ms) -✔ stream timeout closes the original HTTP response, preserves redacted capture and never retries (988.5203ms) -✔ stream idle timeout preserves incomplete tool arguments, records unknown use and never fails over (1096.3096ms) -✔ SSE accepts CR-only final event boundaries and retains exact invalid UTF8 bytes without dispatch (0.7592ms) -▶ stream parser rejects truncation, finish length, malformed JSON, duplicate sequence, changed final item and oversized data - ✔ reject 0 (0.1688ms) - ✔ reject 1 (0.1502ms) - ✔ reject 2 (0.1392ms) - ✔ reject 3 (4.911ms) - ✔ reject 4 (0.136ms) - ✔ reject 5 (0.1465ms) -✔ stream parser rejects truncation, finish length, malformed JSON, duplicate sequence, changed final item and oversized data (6.0882ms) -✔ older configurations receive bounded wait defaults without changing the original object (1.0865ms) -✔ active stream survives sixty seconds; byte activity resets idle but cannot extend total deadline (1.0491ms) -✔ silent stream has its own accurate deadline; caller cancellation and cleanup preserve their cause (1.3579ms) -✔ waiting for headers is bounded independently of stream-idle time (0.2424ms) -✔ wait settings persist, pin new runs and leave model pool, credentials and old run snapshots intact (1271.6174ms) -ℹ tests 28 -ℹ suites 0 -ℹ pass 28 -ℹ fail 0 -ℹ cancelled 0 -ℹ skipped 0 -ℹ todo 0 -ℹ duration_ms 24652.2961 +✔ HTTP download preserves original malformed SSE bytes and artifact SHA instead of decoding invalid UTF8 (2426.5386ms) +✔ terminated SSE adapts empty optional tool arguments, retains the exact wire bytes and executes the validated batch once (2791.2168ms) +✔ reported SSE usage survives rejected required arguments "" without dispatching any tool (1584.8417ms) +✔ reported SSE usage survives rejected required arguments "{\"path\":" without dispatching any tool (1354.9623ms) +✔ reported SSE usage survives rejected required arguments "null" without dispatching any tool (1377.0252ms) +✔ a stream without DONE retains reported usage but cannot adapt or execute even an optional tool (1520.6525ms) +✔ a timeout after reasoning-only fragments creates one unknown receipt and never invents reported tokens (1597.1202ms) +✔ real Chat SSE carries UTF8 and split tool JSON; Runtime executes only after DONE, stores partial progress and original usage (2330.514ms) +✔ Responses typed SSE validates original item identity, terminal data, raw usage and tool result pair (2277.3525ms) +✔ incomplete network stream retains unknown attempt and never automatically switches pool or dispatches fragment tools (1590.889ms) +✔ stopping an active HTTP stream closes only original request and keeps partial text without executing tools (1390.7969ms) +✔ explicit streaming probe uses actual SSE despite unknown declaration and binds its own original attempt (700.3784ms) +✔ coalesced initial SSE events publish the latest partial state even when the upstream stays idle (1398.8886ms) +✔ stream timeout closes the original HTTP response, preserves redacted capture and never retries (988.5203ms) +✔ stream idle timeout preserves incomplete tool arguments, records unknown use and never fails over (1096.3096ms) +✔ SSE accepts CR-only final event boundaries and retains exact invalid UTF8 bytes without dispatch (0.7592ms) +▶ stream parser rejects truncation, finish length, malformed JSON, duplicate sequence, changed final item and oversized data + ✔ reject 0 (0.1688ms) + ✔ reject 1 (0.1502ms) + ✔ reject 2 (0.1392ms) + ✔ reject 3 (4.911ms) + ✔ reject 4 (0.136ms) + ✔ reject 5 (0.1465ms) +✔ stream parser rejects truncation, finish length, malformed JSON, duplicate sequence, changed final item and oversized data (6.0882ms) +✔ older configurations receive bounded wait defaults without changing the original object (1.0865ms) +✔ active stream survives sixty seconds; byte activity resets idle but cannot extend total deadline (1.0491ms) +✔ silent stream has its own accurate deadline; caller cancellation and cleanup preserve their cause (1.3579ms) +✔ waiting for headers is bounded independently of stream-idle time (0.2424ms) +✔ wait settings persist, pin new runs and leave model pool, credentials and old run snapshots intact (1271.6174ms) +ℹ tests 28 +ℹ suites 0 +ℹ pass 28 +ℹ fail 0 +ℹ cancelled 0 +ℹ skipped 0 +ℹ todo 0 +ℹ duration_ms 24652.2961 diff --git a/docs/model-wait-release-evidence/logs/model-wait-long.txt b/docs/model-wait-release-evidence/logs/model-wait-long.txt index 11ed81fd..2905aa5f 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-long.txt +++ b/docs/model-wait-release-evidence/logs/model-wait-long.txt @@ -1 +1 @@ -{"success":true,"results":[{"streaming":false,"durationMs":65034,"finishReason":"stop","content":"non-stream completed"},{"streaming":true,"durationMs":65037,"finishReason":"stop","content":"开始完成"}],"requests":2,"realModelRequests":0} +{"success":true,"results":[{"streaming":false,"durationMs":65034,"finishReason":"stop","content":"non-stream completed"},{"streaming":true,"durationMs":65037,"finishReason":"stop","content":"开始完成"}],"requests":2,"realModelRequests":0} diff --git a/docs/model-wait-release-evidence/logs/model-wait-owned-upgrade.txt b/docs/model-wait-release-evidence/logs/model-wait-owned-upgrade.txt index e3dc42d4..0d068cd2 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-owned-upgrade.txt +++ b/docs/model-wait-release-evidence/logs/model-wait-owned-upgrade.txt @@ -1 +1 @@ -{"success":true,"retained":{"originalRows":"exact","originalExports":"exact","originalArtifactBytes":"exact","originalModelCenter":"exact","publicSchemaAddition":"/waitSettings:300000/120000; original disk config unchanged"}} +{"success":true,"retained":{"originalRows":"exact","originalExports":"exact","originalArtifactBytes":"exact","originalModelCenter":"exact","publicSchemaAddition":"/waitSettings:300000/120000; original disk config unchanged"}} diff --git a/docs/model-wait-release-evidence/logs/model-wait-package.txt b/docs/model-wait-release-evidence/logs/model-wait-package.txt index 255c7f4e..e7165eb8 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-package.txt +++ b/docs/model-wait-release-evidence/logs/model-wait-package.txt @@ -1,70 +1,70 @@ -{ - "portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.2-win-x64-20261101124548744", - "sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.2-source-20261101124548744", - "portable": { - "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.2-win-x64-20261101124548744.zip", - "bytes": 627026168, - "sha256": "a5b47f3c4a02ca5794c24321b89e773a7fdd161063cee4c680a82ece657210f8" - }, - "source": { - "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.2-source-20261101124548744.zip", - "bytes": 627194835, - "sha256": "ec2eea17c90b38fc65a095c5b5eb25ff46a27bdf111e9808961fbf6a20165656" - }, - "installer": { - "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.2-win-x64-20261101124548744-Setup.exe", - "bytes": 586191896, - "sha256": "ca278ea713f61832fce93dbbb56e07e30b285850b0593a6741e78a53cfe07240", - "compiler": { - "version": "6.3.1", - "sha256": "3b22d36fc7e7c421d8caf780008ecdb42b14b3f0371b9bafe3cad64e6648d9cf" - }, - "source": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\installer-build-3f1750c0-e122-4b94-9de0-56d8c961c654\\installer.iss", - "version": "1.20.2", - "candidateDirectory": "Agent-Workbench-1.20.2-win-x64-20261101124548744", - "qaFixture": null - }, - "desktopRuntime": { - "version": "45.2.0", - "sha256": "010ea51bfb528c8143513439aa93fb40754403daa2023f9decd4517da71706ab", - "bytes": 249810432, - "executable": "desktop/AgentWorkbench.exe", - "scope": "Fixed original Windows Electron runtime, full license texts, isolated application loader and native bootstrap; original executable hash unchanged." - }, - "nativeLauncher": { - "bytes": 12288, - "sha256": "e3d31cb7ce5009d3ca5a96d04dc16b1add0bd1f5cde7e1304461de6713d37463", - "inputs": { - "compiler": "46809206887326d2d24db1eff1f3064de972c3451abe766b49111450a5e08e00", - "source": "1c8e7d7ee5c383897bec48e9aadb8051b47c09686f74bbf34e0b6b695cd01ae5", - "icon": "f1879074e45f01c480ad9bf50b818637cc60ad56526056c886f808a4812d7b0c" - }, - "compiler": "Windows .NET Framework C# compiler; source-bound cached original output, no deterministic-build claim." - }, - "nodeVersion": "v24.22.1", - "reaRuntime": { - "version": "6.8.0", - "protocolVersion": "2025-03-26", - "packages": 149, - "files": 8413, - "bytes": 142395402, - "lockSha256": "687fb3fa3089a12f239dd5e87d9fa07df55a87df4935931d495a92600a1b0f6e" - }, - "portableFiles": 19560, - "licenseTexts": 135, - "browserRuntime": { - "playwrightVersion": "1.64.1", - "packages": [ - { - "name": "playwright", - "version": "1.64.1", - "files": 60 - }, - { - "name": "playwright-core", - "version": "1.64.1", - "files": 115 - } - ] - } -} +{ + "portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.2-win-x64-20261101124548744", + "sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.2-source-20261101124548744", + "portable": { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.2-win-x64-20261101124548744.zip", + "bytes": 627026168, + "sha256": "a5b47f3c4a02ca5794c24321b89e773a7fdd161063cee4c680a82ece657210f8" + }, + "source": { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.2-source-20261101124548744.zip", + "bytes": 627194835, + "sha256": "ec2eea17c90b38fc65a095c5b5eb25ff46a27bdf111e9808961fbf6a20165656" + }, + "installer": { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.2-win-x64-20261101124548744-Setup.exe", + "bytes": 586191896, + "sha256": "ca278ea713f61832fce93dbbb56e07e30b285850b0593a6741e78a53cfe07240", + "compiler": { + "version": "6.3.1", + "sha256": "3b22d36fc7e7c421d8caf780008ecdb42b14b3f0371b9bafe3cad64e6648d9cf" + }, + "source": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\installer-build-3f1750c0-e122-4b94-9de0-56d8c961c654\\installer.iss", + "version": "1.20.2", + "candidateDirectory": "Agent-Workbench-1.20.2-win-x64-20261101124548744", + "qaFixture": null + }, + "desktopRuntime": { + "version": "45.2.0", + "sha256": "010ea51bfb528c8143513439aa93fb40754403daa2023f9decd4517da71706ab", + "bytes": 249810432, + "executable": "desktop/AgentWorkbench.exe", + "scope": "Fixed original Windows Electron runtime, full license texts, isolated application loader and native bootstrap; original executable hash unchanged." + }, + "nativeLauncher": { + "bytes": 12288, + "sha256": "e3d31cb7ce5009d3ca5a96d04dc16b1add0bd1f5cde7e1304461de6713d37463", + "inputs": { + "compiler": "46809206887326d2d24db1eff1f3064de972c3451abe766b49111450a5e08e00", + "source": "1c8e7d7ee5c383897bec48e9aadb8051b47c09686f74bbf34e0b6b695cd01ae5", + "icon": "f1879074e45f01c480ad9bf50b818637cc60ad56526056c886f808a4812d7b0c" + }, + "compiler": "Windows .NET Framework C# compiler; source-bound cached original output, no deterministic-build claim." + }, + "nodeVersion": "v24.22.1", + "reaRuntime": { + "version": "6.8.0", + "protocolVersion": "2025-03-26", + "packages": 149, + "files": 8413, + "bytes": 142395402, + "lockSha256": "687fb3fa3089a12f239dd5e87d9fa07df55a87df4935931d495a92600a1b0f6e" + }, + "portableFiles": 19560, + "licenseTexts": 135, + "browserRuntime": { + "playwrightVersion": "1.64.1", + "packages": [ + { + "name": "playwright", + "version": "1.64.1", + "files": 60 + }, + { + "name": "playwright-core", + "version": "1.64.1", + "files": 115 + } + ] + } +} diff --git a/docs/model-wait-release-evidence/logs/model-wait-protocol-ui.txt b/docs/model-wait-release-evidence/logs/model-wait-protocol-ui.txt index f4277167..450e331f 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-protocol-ui.txt +++ b/docs/model-wait-release-evidence/logs/model-wait-protocol-ui.txt @@ -1,6 +1,6 @@ -PASS actual form saves Responses and declared stream, refresh preserves both and narrow editor remains operable -PASS separate text, nonce tool and actual SSE probes bind only their requested capability and own attempts -PASS actual pooled task excludes text-only before dispatch, executes original tool once and downloads SHA-matched original SSE -PASS desktop and actual paired gateway show same bounded stream; mobile stops original HTTP with zero fragment tool dispatch or replay -PASS truncated output keeps explicit unknown ledger, partial evidence and no automatic failover or incomplete tool execution -EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\model-protocols-ui-12baf4c3-6ef1-4afe-b4fc-dd990e44223a +PASS actual form saves Responses and declared stream, refresh preserves both and narrow editor remains operable +PASS separate text, nonce tool and actual SSE probes bind only their requested capability and own attempts +PASS actual pooled task excludes text-only before dispatch, executes original tool once and downloads SHA-matched original SSE +PASS desktop and actual paired gateway show same bounded stream; mobile stops original HTTP with zero fragment tool dispatch or replay +PASS truncated output keeps explicit unknown ledger, partial evidence and no automatic failover or incomplete tool execution +EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\model-protocols-ui-12baf4c3-6ef1-4afe-b4fc-dd990e44223a diff --git a/docs/model-wait-release-evidence/logs/model-wait-related.tap b/docs/model-wait-release-evidence/logs/model-wait-related.tap index 31fcc85f..4cda8f6d 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-related.tap +++ b/docs/model-wait-release-evidence/logs/model-wait-related.tap @@ -1,70 +1,70 @@ -✔ a question about the previous workbench error receives local error context and current change states (2572.0986ms) -✔ a transient model failure after an approved command retries only the model request (3613.6709ms) -✔ exhausted model retries preserve tool results, and explicit resume adds no new user turn or replay (3626.3978ms) -✔ stopping during model backoff cancels further requests and clears the running request state (1781.9182ms) -✔ HTTP authentication errors are classified, redacted and never automatically retried (21.0006ms) -✔ temporary HTTP service errors retry and recover with recorded attempt counts (20.4214ms) -✔ invalid and oversized protocol responses fail once with a useful response-format diagnosis (3.9159ms) -✔ HTTP rate limits expose their source and obey the service retry interval before recovery (1016.1704ms) -✔ Windows commands preserve Chinese through a PowerShell pipeline into Node (1072.6146ms) -✔ Windows shell syntax errors stay readable and native command exit codes are retained (1457.3246ms) -✔ review and completed states do not turn a generic continue click into a new model request (888.6061ms) -✔ old session data receives a truthful historical connection diagnosis without rewriting history (564.2336ms) -✔ model registry keeps original credentials/endpoint intact, rejects stale edits, and forgets only volatile keys on restart (1470.5084ms) -✔ config import previews exact revisions, keeps secrets volatile, syncs only when enabled and preserves manual edits on conflicts (1171.4104ms) -✔ real HTTP pool fails over 429 to another model and never repeats completed tools; attempts seal actual request bytes and Run identity (4000.4454ms) -✔ pool rotation and weights select members on new Runs; disabled and missing credentials are excluded without requests (5179.6987ms) -✔ 401 blocks the credential revision; updating the key restores availability without leaking error echoes (1754.9103ms) -✔ queued request cancellation and in-flight disable release only owned leases and do not dispatch another HTTP request (1277.136ms) -✔ compiled model-center HTTP API persists public profiles, blocks forged origins, and local operations never invoke a model (2529.498ms) -✔ model registry disk failures restore routing, pool profiles and credential references without partial updates (1011.5669ms) -✔ model selection and saved configuration commit together and failures preserve the original mode and endpoint (1006.0569ms) -✔ configuration imports roll back the entire batch and retain one usable preview after validation or commit failure (674.2603ms) -✔ saved engine budgets verify all Chat/Responses route variants and reject a mismatched output allowance (1090.6984ms) -✔ owned CC Switch SQLite imports the selected TOML Responses wire_api and leaves unknown clients untouched (1548.632ms) -✔ Responses executes one original tool through Runtime, carries encrypted Items, reports raw usage and seals exact wire bytes (2755.3635ms) -✔ mixed-protocol pool keeps both actual variants and changes route on 429 without re-executing completed tools (3770.6098ms) -▶ Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool - ✔ Reject {"body":{"id":"resp_owned","status":"incomplete","output":[{"type":"function_call","id":"fc_partial" (1949.4119ms) - ✔ Reject {"body":{"id":"resp_owned","status":"failed","output":[{"type":"function_call","id":"fc_failed","cal (2082.742ms) - ✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"function_call","id":"fc_bad","cal (2016.589ms) - ✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"computer_call","id":"not-supporte (1919.9253ms) -✔ Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool (7969.4088ms) -▶ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay - ✔ chat-completions (1824.526ms) - ✔ responses (2252.4703ms) -✔ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay (4077.3534ms) -✔ wire adapter preserves tool IDs but never passes Responses-private Items to Chat or another endpoint (0.1564ms) -✔ connection JSON import accepts explicit Responses protocol and continues to reject unknown protocols without reading client sessions (862.7606ms) -✔ capability routing skips text-only members before acquiring a lease and records exact refusal in the original Run (2017.5982ms) -✔ all incompatible members reject with no network request, no lease, preserved Task and explicit non-dispatched ledger (1570.3869ms) -✔ explicit synthetic tool probe verifies only actual matching call, never executes it and loses verification on revision changes (1059.7389ms) -✔ plain text probe cannot verify tools; wrong tool nonce and client supplied evidence cannot claim verified support (1192.9938ms) -✔ a disabled connection invalidates an in-flight probe even when toggle mutates its original registry object (1022.9602ms) -✔ a stop from the event loop interrupts immediate model replies before later tools (1620.311ms) -✔ a stop after the first tool preserves a complete interrupted multi-call protocol group (2388.9177ms) -✔ the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands (6014.3933ms) -✔ denial prevents command execution and produces a paired denied result (2269.3286ms) -✔ stopping during approval interrupts pending calls without executing or replaying them (2111.8268ms) -✔ stopping a running fixture command terminates its own process tree and retains uncertain state (2361.3446ms) -✔ command output decodes split UTF-8 and excludes the workbench key from child environment (1288.7983ms) -✔ model-list testing uses a tentative key without changing the saved connection and redacts service errors (12.439ms) -✔ truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities (4150.4139ms) -✔ request projection keeps exact tool pairs and complete recent user instructions while preserving disk history (1713.3195ms) -✔ operational questions are diagnostic while explicit repair requests remain execution instructions (1.0512ms) -✔ file delivery requires a positive instruction, not saved evidence or a prohibited write (1.2058ms) -✔ an unsubstantiated text claim cannot complete a requested file delivery (1601.8128ms) -✔ HTML without tests ends at reviewed file delivery and never offers automatic rechecking (2770.1918ms) -✔ diagnostic answers retain the unfinished task, limits and check result, and enforce read-only tools (4569.8906ms) -✔ review continuation is a system action and adds no testing demand or fake user instruction (3182.5911ms) -✔ a provider cannot execute tests against an explicit no-test task even if it ignores advertised tools (1482.0105ms) -✔ a budget pause becomes visible only after its input snapshot can be sealed with the original Run (1270.4707ms) -✔ alternating duplicate file reads and listing files still pauses without treating new pages as duplicates (11266.4412ms) -ℹ tests 60 -ℹ suites 0 -ℹ pass 60 -ℹ fail 0 -ℹ cancelled 0 -ℹ skipped 0 -ℹ todo 0 -ℹ duration_ms 65317.1144 +✔ a question about the previous workbench error receives local error context and current change states (2572.0986ms) +✔ a transient model failure after an approved command retries only the model request (3613.6709ms) +✔ exhausted model retries preserve tool results, and explicit resume adds no new user turn or replay (3626.3978ms) +✔ stopping during model backoff cancels further requests and clears the running request state (1781.9182ms) +✔ HTTP authentication errors are classified, redacted and never automatically retried (21.0006ms) +✔ temporary HTTP service errors retry and recover with recorded attempt counts (20.4214ms) +✔ invalid and oversized protocol responses fail once with a useful response-format diagnosis (3.9159ms) +✔ HTTP rate limits expose their source and obey the service retry interval before recovery (1016.1704ms) +✔ Windows commands preserve Chinese through a PowerShell pipeline into Node (1072.6146ms) +✔ Windows shell syntax errors stay readable and native command exit codes are retained (1457.3246ms) +✔ review and completed states do not turn a generic continue click into a new model request (888.6061ms) +✔ old session data receives a truthful historical connection diagnosis without rewriting history (564.2336ms) +✔ model registry keeps original credentials/endpoint intact, rejects stale edits, and forgets only volatile keys on restart (1470.5084ms) +✔ config import previews exact revisions, keeps secrets volatile, syncs only when enabled and preserves manual edits on conflicts (1171.4104ms) +✔ real HTTP pool fails over 429 to another model and never repeats completed tools; attempts seal actual request bytes and Run identity (4000.4454ms) +✔ pool rotation and weights select members on new Runs; disabled and missing credentials are excluded without requests (5179.6987ms) +✔ 401 blocks the credential revision; updating the key restores availability without leaking error echoes (1754.9103ms) +✔ queued request cancellation and in-flight disable release only owned leases and do not dispatch another HTTP request (1277.136ms) +✔ compiled model-center HTTP API persists public profiles, blocks forged origins, and local operations never invoke a model (2529.498ms) +✔ model registry disk failures restore routing, pool profiles and credential references without partial updates (1011.5669ms) +✔ model selection and saved configuration commit together and failures preserve the original mode and endpoint (1006.0569ms) +✔ configuration imports roll back the entire batch and retain one usable preview after validation or commit failure (674.2603ms) +✔ saved engine budgets verify all Chat/Responses route variants and reject a mismatched output allowance (1090.6984ms) +✔ owned CC Switch SQLite imports the selected TOML Responses wire_api and leaves unknown clients untouched (1548.632ms) +✔ Responses executes one original tool through Runtime, carries encrypted Items, reports raw usage and seals exact wire bytes (2755.3635ms) +✔ mixed-protocol pool keeps both actual variants and changes route on 429 without re-executing completed tools (3770.6098ms) +▶ Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool + ✔ Reject {"body":{"id":"resp_owned","status":"incomplete","output":[{"type":"function_call","id":"fc_partial" (1949.4119ms) + ✔ Reject {"body":{"id":"resp_owned","status":"failed","output":[{"type":"function_call","id":"fc_failed","cal (2082.742ms) + ✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"function_call","id":"fc_bad","cal (2016.589ms) + ✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"computer_call","id":"not-supporte (1919.9253ms) +✔ Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool (7969.4088ms) +▶ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay + ✔ chat-completions (1824.526ms) + ✔ responses (2252.4703ms) +✔ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay (4077.3534ms) +✔ wire adapter preserves tool IDs but never passes Responses-private Items to Chat or another endpoint (0.1564ms) +✔ connection JSON import accepts explicit Responses protocol and continues to reject unknown protocols without reading client sessions (862.7606ms) +✔ capability routing skips text-only members before acquiring a lease and records exact refusal in the original Run (2017.5982ms) +✔ all incompatible members reject with no network request, no lease, preserved Task and explicit non-dispatched ledger (1570.3869ms) +✔ explicit synthetic tool probe verifies only actual matching call, never executes it and loses verification on revision changes (1059.7389ms) +✔ plain text probe cannot verify tools; wrong tool nonce and client supplied evidence cannot claim verified support (1192.9938ms) +✔ a disabled connection invalidates an in-flight probe even when toggle mutates its original registry object (1022.9602ms) +✔ a stop from the event loop interrupts immediate model replies before later tools (1620.311ms) +✔ a stop after the first tool preserves a complete interrupted multi-call protocol group (2388.9177ms) +✔ the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands (6014.3933ms) +✔ denial prevents command execution and produces a paired denied result (2269.3286ms) +✔ stopping during approval interrupts pending calls without executing or replaying them (2111.8268ms) +✔ stopping a running fixture command terminates its own process tree and retains uncertain state (2361.3446ms) +✔ command output decodes split UTF-8 and excludes the workbench key from child environment (1288.7983ms) +✔ model-list testing uses a tentative key without changing the saved connection and redacts service errors (12.439ms) +✔ truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities (4150.4139ms) +✔ request projection keeps exact tool pairs and complete recent user instructions while preserving disk history (1713.3195ms) +✔ operational questions are diagnostic while explicit repair requests remain execution instructions (1.0512ms) +✔ file delivery requires a positive instruction, not saved evidence or a prohibited write (1.2058ms) +✔ an unsubstantiated text claim cannot complete a requested file delivery (1601.8128ms) +✔ HTML without tests ends at reviewed file delivery and never offers automatic rechecking (2770.1918ms) +✔ diagnostic answers retain the unfinished task, limits and check result, and enforce read-only tools (4569.8906ms) +✔ review continuation is a system action and adds no testing demand or fake user instruction (3182.5911ms) +✔ a provider cannot execute tests against an explicit no-test task even if it ignores advertised tools (1482.0105ms) +✔ a budget pause becomes visible only after its input snapshot can be sealed with the original Run (1270.4707ms) +✔ alternating duplicate file reads and listing files still pauses without treating new pages as duplicates (11266.4412ms) +ℹ tests 60 +ℹ suites 0 +ℹ pass 60 +ℹ fail 0 +ℹ cancelled 0 +ℹ skipped 0 +ℹ todo 0 +ℹ duration_ms 65317.1144 diff --git a/docs/model-wait-release-evidence/logs/model-wait-ui-scroll.txt b/docs/model-wait-release-evidence/logs/model-wait-ui-scroll.txt index 9b44b39d..eea2112c 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-ui-scroll.txt +++ b/docs/model-wait-release-evidence/logs/model-wait-ui-scroll.txt @@ -1,6 +1,6 @@ -PASS desktop saves seconds, preserves original pool/member and sends no model request -PASS invalid timeout rejected without saving -PASS saved values survive reload; narrow screen remains usable -PASS active request locks wait changes in both API and UI -PASS actual stalled stream shows exact idle reason, saves unknown use, never writes or retries -{"success":true,"directory":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-wait-ui-79af8e3a-14f6-4114-a28f-580430d7d8e8","checks":5,"screenshots":4} +PASS desktop saves seconds, preserves original pool/member and sends no model request +PASS invalid timeout rejected without saving +PASS saved values survive reload; narrow screen remains usable +PASS active request locks wait changes in both API and UI +PASS actual stalled stream shows exact idle reason, saves unknown use, never writes or retries +{"success":true,"directory":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-wait-ui-79af8e3a-14f6-4114-a28f-580430d7d8e8","checks":5,"screenshots":4} diff --git a/docs/model-wait-release-evidence/logs/model-wait-ui.txt b/docs/model-wait-release-evidence/logs/model-wait-ui.txt index b3ee92af..a3f03f18 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-ui.txt +++ b/docs/model-wait-release-evidence/logs/model-wait-ui.txt @@ -1,6 +1,6 @@ -PASS desktop saves seconds, preserves original pool/member and sends no model request -PASS invalid timeout rejected without saving -PASS saved values survive reload; narrow screen remains usable -PASS active request locks wait changes in both API and UI -PASS actual stalled stream shows exact idle reason, saves unknown use, never writes or retries -{"success":true,"directory":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-wait-ui-6050b00d-fd6d-4e3f-a6e8-e703f6a8bb8c","checks":5,"screenshots":4} +PASS desktop saves seconds, preserves original pool/member and sends no model request +PASS invalid timeout rejected without saving +PASS saved values survive reload; narrow screen remains usable +PASS active request locks wait changes in both API and UI +PASS actual stalled stream shows exact idle reason, saves unknown use, never writes or retries +{"success":true,"directory":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-wait-ui-6050b00d-fd6d-4e3f-a6e8-e703f6a8bb8c","checks":5,"screenshots":4} diff --git a/docs/model-wait-release-evidence/logs/model-wait-upgrade.tap b/docs/model-wait-release-evidence/logs/model-wait-upgrade.tap index 9c812005..29703512 100644 --- a/docs/model-wait-release-evidence/logs/model-wait-upgrade.tap +++ b/docs/model-wait-release-evidence/logs/model-wait-upgrade.tap @@ -1,31 +1,31 @@ -✔ JSON migration survives process exit before commit and retains exact legacy backups (4222.5377ms) -✔ process exit after_state rolls back state, event and outbox together (2616.4939ms) -✔ process exit after_event rolls back state, event and outbox together (2814.9776ms) -✔ crash recovery at accepted retains execution identity and never replays side effects (2317.0945ms) -✔ crash recovery at queued retains execution identity and never replays side effects (2731.1714ms) -✔ crash recovery at approval_wait retains execution identity and never replays side effects (3499.4361ms) -✔ crash recovery at approved retains execution identity and never replays side effects (2630.7769ms) -✔ crash recovery at effect_unrecorded retains execution identity and never replays side effects (2793.8295ms) -✔ crash recovery at result_committed retains execution identity and never replays side effects (2711.2371ms) -✔ crash recovery at before_next_model retains execution identity and never replays side effects (2910.4549ms) -✔ state and event failures publish no success and preserve the last committed memory snapshot (585.7129ms) -✔ tool result artifacts and event cursors retain project ownership across restart (1303.6506ms) -✔ token budgets pause before tools execute and continuation keeps original task and accumulated usage (1493.6537ms) -✔ a time budget interrupts an unresponsive model and persists a resumable run (989.5623ms) -✔ a corrupted large result artifact cannot become a recovered success (911.5817ms) -✔ schema1 connections remain readable without inventing observed capabilities or migrating original state (1304.3561ms) -✔ protocol, unsupported capabilities and stream choice persist; client claims cannot forge verified evidence (1244.037ms) -✔ ability evidence belongs to exact connection and credential revision; unknown and unsupported reject required routing (0.2737ms) -✔ invalid declarations and inconsistent stream settings reject before registry, revision and credentials mutate (1325.4096ms) -✔ hot upgrade adopts a retained virtual data root without reopening SQLite or changing rows, Provider or routing (1903.3432ms) -✔ failed adoption restores the original virtual data-root name and original open database (955.6613ms) -✔ hot upgrade refreshes retained model and importer methods while preserving credential and routing objects (1340.7943ms) -✔ hot upgrade refuses active probes and restores retained model methods if installation fails (854.4396ms) -ℹ tests 23 -ℹ suites 0 -ℹ pass 23 -ℹ fail 0 -ℹ cancelled 0 -ℹ skipped 0 -ℹ todo 0 -ℹ duration_ms 34661.5798 +✔ JSON migration survives process exit before commit and retains exact legacy backups (4222.5377ms) +✔ process exit after_state rolls back state, event and outbox together (2616.4939ms) +✔ process exit after_event rolls back state, event and outbox together (2814.9776ms) +✔ crash recovery at accepted retains execution identity and never replays side effects (2317.0945ms) +✔ crash recovery at queued retains execution identity and never replays side effects (2731.1714ms) +✔ crash recovery at approval_wait retains execution identity and never replays side effects (3499.4361ms) +✔ crash recovery at approved retains execution identity and never replays side effects (2630.7769ms) +✔ crash recovery at effect_unrecorded retains execution identity and never replays side effects (2793.8295ms) +✔ crash recovery at result_committed retains execution identity and never replays side effects (2711.2371ms) +✔ crash recovery at before_next_model retains execution identity and never replays side effects (2910.4549ms) +✔ state and event failures publish no success and preserve the last committed memory snapshot (585.7129ms) +✔ tool result artifacts and event cursors retain project ownership across restart (1303.6506ms) +✔ token budgets pause before tools execute and continuation keeps original task and accumulated usage (1493.6537ms) +✔ a time budget interrupts an unresponsive model and persists a resumable run (989.5623ms) +✔ a corrupted large result artifact cannot become a recovered success (911.5817ms) +✔ schema1 connections remain readable without inventing observed capabilities or migrating original state (1304.3561ms) +✔ protocol, unsupported capabilities and stream choice persist; client claims cannot forge verified evidence (1244.037ms) +✔ ability evidence belongs to exact connection and credential revision; unknown and unsupported reject required routing (0.2737ms) +✔ invalid declarations and inconsistent stream settings reject before registry, revision and credentials mutate (1325.4096ms) +✔ hot upgrade adopts a retained virtual data root without reopening SQLite or changing rows, Provider or routing (1903.3432ms) +✔ failed adoption restores the original virtual data-root name and original open database (955.6613ms) +✔ hot upgrade refreshes retained model and importer methods while preserving credential and routing objects (1340.7943ms) +✔ hot upgrade refuses active probes and restores retained model methods if installation fails (854.4396ms) +ℹ tests 23 +ℹ suites 0 +ℹ pass 23 +ℹ fail 0 +ℹ cancelled 0 +ℹ skipped 0 +ℹ todo 0 +ℹ duration_ms 34661.5798 diff --git a/progress.md b/progress.md index c0ed3412..7c183a9d 100644 --- a/progress.md +++ b/progress.md @@ -2,6 +2,8 @@ ## 1.20.2 本地交付完成 +最终Git字节核对补齐新证据目录的-text属性:保留验收日志原CRLF字节,避免后续检出时SHA与封存清单不符。按范围重新暂存原字节并增加逐个Git blob核对,产品源码和已安装发行均不变。首份ACCEPTANCE仅校验工作区证据;最终FINAL收据额外绑定提交内原证据字节,前份保留。 + 1.20.2已完成模型响应等待修复与保留状态部署:单次响应默认300秒、流式无数据120秒,模型中心可调整。111项专项/关联回归、真实本机JSON/SSE各65秒、五组等待UI/五组协议UI及五组随包等待UI通过;实际旧版到新版升级及正式Edge/Electron两视口回看通过。正式PID36552/Provider、17项目/31全部会话/3207记录/6138事件和1761个工件文件原字节保持,仅公开模型中心增加计算出的等待默认值;磁盘配置不回写。本轮验收发起真实模型请求0。 正式预检首轮辅助比较器错误要求旧版也已含新waitSettings字段,在安装前停止;修正为仅新增字段出现时做严格归一化,原失败保留,新b轮完成完整Setup暂存与独立候选核对,但因安装期间又新增原模型重试,原会话摘要变化被拒绝;新c轮沿用同一已校验候选,使用新鲜完整基线/备份后升级通过。用户自行新增的原超时记录一并保持。本次未主动续跑用户任务。代码提交3b650275ffe6984a1147a39ba1c22dd3a6859a61;正式UI首轮Edge两视口通过,Electron首窗口尚在导航时立即reload引发ERR_ABORTED;原失败和四张截图保留。b轮补等就绪后遇隐藏窗口截图超时;c轮沿用上一版已验证的可见窗口方式通过,复用已完成Edge截图,不修改产品或重复安装。源码/归档/安装SHA与最终去敏证据见docs/model-wait-release-identity.json。封存后另做本地文档Git收尾,不改不可变发行。