Commit Graph
100 Commits
Author SHA1 Message Date
Tianyi Cui 3fc9027a01 docs(session): refresh replay config source location 2026-09-08 16:56:53 +08:00
Tianyi Cui 53f42a781b test(session): close canonical envelope CI gaps 2026-09-08 16:56:53 +08:00
Tianyi Cui c4d8ee5ff2 test(session): canonicalize headless expected system replacements 2026-09-08 16:56:52 +08:00
Tianyi Cui 920e917988 fix(session): retain unknown required events for vocabulary validation 2026-09-08 16:56:52 +08:00
Tianyi Cui b7622e9f13 chore(session): refresh canonical API catalog after integration 2026-09-08 16:56:52 +08:00
Tianyi Cui 756b10fcfe test(session): cover composed canonical and PTC restoration 2026-09-08 16:56:52 +08:00
Tianyi Cui c28639587a test(session): keep historical fixtures outside current V3 encoding 2026-09-08 16:56:52 +08:00
Tianyi Cui 657e68186a fix(session): canonicalize V3 envelopes through adjacent migration 2026-09-08 16:56:52 +08:00
Tianyi Cui 7cbb052661 Merge pull request #3711 from deepseek-harness/integrate/v3-latest-master-for-canonical
ci(session): merge latest master into V3 for canonical review
2026-09-08 16:50:33 +08:00
Tianyi Cui be9d401c33 test(web): await action acknowledgements before following controls 2026-09-08 15:00:53 +08:00
Tianyi Cui 6c0e258b27 test(web): await observed browser settlement in replay scenarios 2026-09-08 14:35:11 +08:00
Tianyi Cui d058899194 test(snapshot): isolate child-turn diagnostic timeout from harvesting 2026-09-08 13:59:47 +08:00
Tianyi Cui 1c06f1d3ac test(snapshot): declare spill command fixture plugin types 2026-09-08 13:40:49 +08:00
Tianyi Cui 154b2a3cd6 test(snapshot): reconcile V3 fixtures with isolated master replay 2026-09-08 13:36:12 +08:00
Tianyi Cui 2b64ea5f1a test(web): align V3 seeded stats with absent decode timing 2026-09-08 13:20:43 +08:00
Tianyi Cui 96fa1dfac8 Merge pinned master 84bde6c7 into V3 readiness repair 2026-09-08 13:16:35 +08:00
Tianyi Cui 0bb083d898 Merge pull request #3646 from deepseek-harness/fix/pr-ci-reliability-20260906
fix(ci): 隔离临时存储并稳定测试夹具
2026-09-08 13:06:58 +08:00
Tianyi Cui c389f96bf3 Merge pull request #3713 from deepseek-harness/fix/workspace-browser-race
test(web): 等待种子 Session 归属投影后再选择
2026-09-08 00:46:19 +08:00
Tianyi Cui eec9c3b694 test(snapshot): avoid duplicate projection registry setup 2026-09-08 00:37:58 +08:00
Tianyi Cui 47434e8554 fix(session-format): align v3 migration with merged release version 2026-09-08 00:32:02 +08:00
Tianyi Cui e73906d06f test(web): await seeded workspace membership before selection 2026-09-08 00:28:25 +08:00
Tianyi Cui ccb861d0e2 Merge branch 'master' into fix/pr-ci-reliability-20260906 2026-09-08 00:23:08 +08:00
Tianyi Cui 5b039c1796 Merge master 822041865d into Session V3 release 2026-09-08 00:17:14 +08:00
Tianyi Cui 3ef3bc17c5 Merge pull request #3483 from deepseek-harness/feat/system-prompt-in-history
feat(agent-loop): append a changed system prompt in history on capable routes
2026-09-08 00:06:45 +08:00
Tianyi Cui 4eebc70df2 test(agent-loop): account for route switch notice during prompt admission
The plain-to-capable transition emits the model-selection notice inherited from master. Preserve the exact in-history system ordering and assert both the admitted user input and the single durable notice instead of expecting the obsolete five-message request. Reproduces the identical Linux and Windows CI failure; all 57 adjacent admission, projection, reconstruction and selection tests pass.
2026-09-07 23:29:49 +08:00
Tianyi Cui 053bf8aaad Merge branch 'feat/system-prompt-surface-node' into feat/system-prompt-in-history 2026-09-07 19:45:32 +08:00
Tianyi Cui 34832ddb2e Merge published V3 repair root into system-message branch
Include the root merge from #3678 without altering the previously validated implementation tree. Preserve structural V3 system messages and the current native-runtime recordings.
2026-09-07 19:45:32 +08:00
Tianyi Cui 98c043ab0f Merge branch 'master' into fix/pr-ci-reliability-20260906 2026-09-07 19:44:51 +08:00
Tianyi Cui 4bcabe6da4 test: pair spill cleanup roots with concurrent run results 2026-09-07 19:20:39 +08:00
Tianyi Cui 23b48b7577 Merge pull request #3678 from deepseek-harness/fix/v3-benchmark-reliability
fix(ci): integrate latest master and repair V3 performance/readiness checks
2026-09-07 19:14:22 +08:00
Tianyi Cui f3c98e4539 test(web): settle queue tooltip and select exact seeded session 2026-09-07 19:03:25 +08:00
Tianyi Cui 89bafdb945 Merge native subprocess containment into in-history updates
Preserve both sdk-minimal-in-history and native runner smoke scenarios. Record the current Cordis inspection through the actual upper headless owner while retaining upstream V2 bytes and strict prompt admission semantics.
2026-09-07 18:49:19 +08:00
Tianyi Cui 90307dd7d6 Merge native containment master into V3 system-message layer
Preserve strict live-smoke challenges and structural system messages while adopting the native subprocess runtime. Regenerate only the current Cordis inspection recording from the upstream V2 source to retain its no-ordinary-PID coverage; predecessor bytes match master.
2026-09-07 18:46:59 +08:00
Tianyi Cui 1dc95884a1 Merge frozen native containment master f6132bd into V3 repair
Preserve the root V3 current-writer, PTC dispatch identity, and reliability fixes while incorporating provider-owned native ranges and the private packaged runner bootstrap.

Refresh only the current cordis-inspect-jsdoc V3 owner through the built headless profile so upstream subprocess API coverage is exercised. Preserve incoming master V2 bytes and all other fixtures and benchmark thresholds.
2026-09-07 18:42:02 +08:00
Tianyi Cui b000ca44f6 Merge branch 'feat/system-prompt-surface-node' into feat/system-prompt-in-history 2026-09-07 18:20:03 +08:00
Tianyi Cui 3ae70558e7 test: make publint assertion callbacks explicitly void 2026-09-07 18:19:45 +08:00
Tianyi Cui f4e10a61b1 test: make publint assertion callbacks explicitly void 2026-09-07 18:19:44 +08:00
Tianyi Cui 0deeec02c4 Merge current master and CI readiness repairs into in-history updates
Preserve prepared-route admission and V3 prompt semantics while adopting latest master. Regenerate the new model-switch recording at its actual upper-layer title ordering, retain the V2 predecessor, and keep queued-image and publint lifetime assertions strict.
2026-09-07 18:18:08 +08:00
Tianyi Cui 153d54a2f2 ci: retain shared persistent npm cache 2026-09-07 18:14:33 +08:00
Tianyi Cui d792a694ef test: bind publint subprocess lifetime to lane cancellation 2026-09-07 18:14:17 +08:00
Tianyi Cui 710823fd24 Merge current master and benchmark repairs into V3 system messages
Adopt current model-switch notices, lazy observation, and open-in-app integration while preserving structural V3 admission. Regenerate only the new model-switch owner’s native V3 recording, prompt-count manifest and expected delimiter; keep the master V2 predecessor byte-exact.
2026-09-07 18:14:14 +08:00
Tianyi Cui f91f33094a test: bind publint subprocess lifetime to lane cancellation 2026-09-07 18:13:07 +08:00
Tianyi Cui c4ad45378d test(web): await admitted queue image before snapshot 2026-09-07 18:07:13 +08:00
Tianyi Cui 07b9d2e780 test(web): await admitted queue image before snapshot 2026-09-07 18:06:55 +08:00
Tianyi Cui 89f4acbd74 Merge frozen master 777d73f into V3 benchmark repair
Bring model-switch notices, lazy observations, and open-in-app into the root V3 integration without importing the child structural header changes. Preserve V3 migration, PTC, and all predecessor fixtures.

Refresh only the model-switch-notice owner through dsh --profile headless to harvest native current-writer session.v3.jsonl. Keep the master session.v2.jsonl byte-exact; existing header pin and versioned writer helpers require no changes.
2026-09-07 18:04:19 +08:00
Tianyi Cui 4ee338532a ci: retain shared pnpm store across runner instances 2026-09-07 17:28:12 +08:00
Tianyi Cui 2c2092e2c6 Merge branch 'feat/system-prompt-surface-node' into feat/system-prompt-in-history 2026-09-07 17:21:56 +08:00
Tianyi Cui dbd28a8071 fix(benchmarks): keep composer focus during streamed input 2026-09-07 17:21:56 +08:00
Tianyi Cui 9baebd8f3f fix(benchmarks): keep composer focus during streamed input 2026-09-07 17:21:55 +08:00
Tianyi Cui 09e56a4b4a Merge branch 'feat/system-prompt-surface-node' into feat/system-prompt-in-history 2026-09-07 17:18:19 +08:00
Tianyi Cui 201987b374 perf(llm): scan file content without per-array callbacks 2026-09-07 17:18:18 +08:00
Tianyi Cui a7661e2672 perf(llm): scan file content without per-array callbacks 2026-09-07 17:18:18 +08:00
Tianyi Cui d718965f00 Merge branch 'feat/system-prompt-surface-node' into feat/system-prompt-in-history 2026-09-07 16:58:53 +08:00
Tianyi Cui f277ec0e06 Merge published V3 root after master integration approval
Include the root merge ancestry from #3669. Preserve the already validated system-message child recording rather than restoring the root’s header-system representation. The resulting tree is unchanged from the preceding representation head.
2026-09-07 16:58:52 +08:00
Tianyi Cui 7ef325619f Merge branch 'master' into fix/pr-ci-reliability-20260906 2026-09-07 16:46:31 +08:00
Tianyi Cui 930e4d67ea Merge pull request #3669 from deepseek-harness/fix/spkv-root-latest-master
ci(session): bring protected V3 integration onto latest master
2026-09-07 16:45:19 +08:00
Tianyi Cui b0ba955be2 Merge branch 'feat/system-prompt-surface-node' into feat/system-prompt-in-history 2026-09-07 16:17:19 +08:00
Tianyi Cui 476918da0a Merge latest master teardown and migration waiter fixes
Observe actual shared-preparation waiter admission and settle both callers before cleanup, preserving current V3 migration expectations. Adopt master’s cross-platform teardown regressions without changing budgets or Session data.
2026-09-07 16:15:57 +08:00
Tianyi Cui a062772d7d Merge latest master teardown and migration waiter fixes
Observe actual shared-preparation waiter admission and settle both callers before cleanup, preserving current V3 migration expectations. Adopt master’s cross-platform teardown regressions without changing budgets or Session data.
2026-09-07 16:15:57 +08:00
Tianyi Cui 4ac4e3d014 Merge pull request #3668 from deepseek-harness/fix/windows-subagent-teardown-ci
test(ci): synchronize Windows waiters and complete teardown
2026-09-07 15:52:01 +08:00
Tianyi Cui 7ebde31dde Merge current master human inbox controls into in-history updates
Preserve in-history request ordering and native V3 system heads while incorporating master’s human inbox controls. Regenerate only the current SDK child recording through its actual owner; retained V2 predecessor bytes match master.
2026-09-07 15:50:05 +08:00
Tianyi Cui d9042f61e1 test(snapshot): refresh V3 human-steering child recording
Record current V3 output from master’s human inbox control scenario while retaining the V2 predecessor unchanged. No additional product behavior or validation change.
2026-09-07 15:48:25 +08:00
Tianyi Cui b7f66f4440 test(sdk): record native V3 human-steering inbox transitions
Refresh the current V3 child recording through the actual SDK scenario after master’s inbox-control change. Preserve the V2 predecessor inherited from master and retain system-message admission and current references.
2026-09-07 15:47:27 +08:00
Tianyi Cui 50cce9c28d Merge latest master human inbox controls into system-prompt layer
Preserve the V3 PTC SDK assertion and enable the new human-steering runtime fixture while carrying master’s inbox lifecycle changes. Retain prior deterministic CI repairs and immutable predecessor ownership.
2026-09-07 15:45:09 +08:00
Tianyi Cui fffd39b101 Merge latest master human inbox controls into V3 integration
Preserve the V3 PTC scenario while enabling the current subagent human-steering fixture environment. All product changes are inherited from master; no V3 migration semantics are altered.
2026-09-07 15:44:17 +08:00
Tianyi Cui ce9f124e0e Merge branch 'feat/system-prompt-surface-node' into feat/system-prompt-in-history 2026-09-07 15:40:52 +08:00
Tianyi Cui e2b3800a7e fix(python): challenge fresh file state in live SDK smoke 2026-09-07 15:40:51 +08:00
Tianyi Cui 275ff714cf Merge branch 'feat/system-prompt-surface-node' into feat/system-prompt-in-history 2026-09-07 15:03:33 +08:00
Tianyi Cui f7b1658ff2 fix(benchmarks): reserve system heads in generated V3 histories 2026-09-07 15:03:32 +08:00
Tianyi Cui 0d0914b814 fix(agent-loop): import message type for freeze provenance
Restore the explicit Message type import needed by master’s per-agent WeakSet after composing it with the in-history request builder.
2026-09-07 14:56:45 +08:00
Tianyi Cui 70ae2354d0 Merge latest master performance work and V3 preset migration
Freeze exactly the post-admission derived message array using the inherited per-agent provenance cache, preserving the prepared-route ordering and retry semantics. Adopt the root’s legacy preset migration without changing native V3 custom preset behavior. Request freeze, admission, projection and reconstruction regressions pass58 tests.
2026-09-07 14:55:12 +08:00
Tianyi Cui 19d167cec2 Merge latest master request-freeze and frontend performance work
Preserve the V3 system-prompt projection while adopting master’s per-agent frozen-message provenance and frontend performance gates. Keep benchmark workload admission and diagnostics fixes intact, and retain both migration and first-open/reopen lifecycle guarantees.
2026-09-07 14:53:00 +08:00
Tianyi Cui 95400aa52c Merge V3 preset-reference migration into system-prompt representation
Compose the root’s exact legacy code-to-ptc preset conversion with the existing structural system-head migration. Keep dense source events, audited payload admission, local reference mapping, and native V3 extension behavior unchanged. Preserve the historical preset migration fixture byte-for-byte and test unsupported sparse/opaque sources explicitly.
2026-09-07 14:51:05 +08:00
Tianyi Cui 85dcebcda4 Merge remote-tracking branch 'origin/master' into fix/spkv-root-latest-master 2026-09-07 14:48:39 +08:00
Tianyi Cui 8d0f45febc Merge remote-tracking branch 'origin/release/session-log-v3' into fix/spkv-root-latest-master 2026-09-07 14:47:55 +08:00
Tianyi Cui 5608528e14 Merge pull request #3637 from deepseek-harness/perf/frontend-scenarios
test(perf): gate long-session browser and reconnect workflows
2026-09-07 14:42:15 +08:00
Tianyi Cui b53c95e458 Merge pull request #3664 from deepseek-harness/fix/scroll-follow-pending-sample
fix(chat): preserve pinned scroll-follow across layout changes
2026-09-07 14:38:43 +08:00
Tianyi Cui 4023879df7 test(codex): finish captured cleanup after sibling failures 2026-09-07 14:30:31 +08:00
Tianyi Cui a1d11f213f test(session): observe shared waiter admission before cancellation 2026-09-07 14:30:29 +08:00
Tianyi Cui 5b2c9ba2d2 Merge pull request #3666 from deepseek-harness/worktree/session-v3-preset-rename
fix(session): migrate legacy code preset references to ptc
2026-09-07 14:30:24 +08:00
Tianyi Cui 1ca0df2e24 test(python): synchronize advanced snapshot workflow membership 2026-09-07 14:26:30 +08:00
Tianyi Cui 0ff0850678 Merge branch 'feat/system-prompt-surface-node' into feat/system-prompt-in-history 2026-09-07 14:21:50 +08:00
Tianyi Cui d1e9254454 fix(web-tests): author preset and stats seeds in current format
Generated V0 logs put user surfaces before the first step and cannot migrate to a protected V3 system head without changing chronology. Author native current headers, open the first step before the empty system head and user, keep title sequence references aligned, and supply embedded assistant streams.

Give the preset child a current identified user message. Preserve all paging, geometry, preset assertions and committed historical fixtures. Validated both generators red/green through the source seed reader, one full build, all preset/stats/trajectory browser tests (11), and scoped type-aware lint.
2026-09-07 14:21:50 +08:00
Tianyi Cui dda0f05999 fix(web-tests): generate native system head before chat users
The long-chat builder emitted current V3 with user/message before system/message, so seed restoration rejected its protected head before browser assertions ran. Open the first step and append the system head before the user surface; keep Session-assigned title and tool-result references.

Add an independent seed-reader regression for current version, protected head order, title/tool references and closed turns. Observed protected-head failure before the fix; focused regression and full configured type-aware lint pass. Existing browser scroll assertions are unchanged; full built owner runs follow.
2026-09-07 14:17:08 +08:00
Tianyi Cui 12dd429331 Merge remote-tracking branch 'origin/master' into fix/spkv-root-latest-master 2026-09-07 14:02:51 +08:00
Tianyi Cui 2eccae5631 Merge branch 'release/session-log-v3' into worktree/session-v3-preset-rename 2026-09-07 14:00:22 +08:00
Tianyi Cui 73865675a4 docs(system-prompt): combine cache guarantees in model-experience field
Keep the merged in-history and stable suffix guarantees within the required single KV Cache effect paragraph. No behavior or guarantee changes.
2026-09-07 13:58:41 +08:00
Tianyi Cui c1be95a0cd Merge branch 'feat/system-prompt-surface-node' into feat/system-prompt-in-history 2026-09-07 13:56:15 +08:00
Tianyi Cui a4f6250be9 Merge remote-tracking branch 'origin/release/session-log-v3' into feat/system-prompt-surface-node 2026-09-07 13:56:08 +08:00
Tianyi Cui 086b94d4f6 Merge pull request #3655 from deepseek-harness/fix/v3-pwsh-current-fixtures
test(session): 同步最新 master 并修复 V3 PowerShell fixtures
2026-09-07 13:53:21 +08:00
Tianyi Cui d43d93d89f test(agent-loop): use current persona slots in admission harness
Adopt master’s explicit personaPrefix/personaSuffix configuration in the in-history test harness. The assembly override and all admission assertions remain unchanged; this fixes the typed build integration rather than weakening the tests.
2026-09-07 13:46:33 +08:00
Tianyi Cui 9ef426d729 fix(chat): keep genuine near-floor scroll gestures pending 2026-09-07 13:46:30 +08:00
Tianyi Cui 421e3b075c test(subagent): preserve lane budgets and await teardown completion 2026-09-07 13:39:56 +08:00
Tianyi Cui a4e445236f Merge latest master prompt placement into in-history updates
Keep prepared-route in-history append, clear-all, and normalization semantics while adopting named persona prefix/suffix and late environment facts from master. Resolve documentation against the derived system-message history and retain the existing strict migration behavior.
2026-09-07 13:39:12 +08:00
Tianyi Cui d3ed6d6f88 Merge remote-tracking branch 'origin/master' into feat/system-prompt-surface-node 2026-09-07 13:35:06 +08:00
Tianyi Cui 57885bd73d Merge latest master prompt placement through V3 integration
Preserve system/message persistence while adopting named persona prefix/suffix and environment facts after reusable instructions. Resolve the Web assertion against the logged system message, not retired header.system. Keep the existing protected V3 integration PR as the root publication path; no rules are bypassed.
2026-09-07 13:34:43 +08:00
Tianyi Cui cbdf32447e fix(benchmarks): calibrate repeated hosted browser open median 2026-09-07 13:29:38 +08:00
Tianyi Cui 1a3af89a8d fix(benchmarks): calibrate hosted paging and trajectory endpoints 2026-09-07 13:29:38 +08:00
Tianyi Cui 620c2b0b27 fix(benchmarks): calibrate hosted frontend endpoints and preserve input overlap 2026-09-07 13:29:38 +08:00
Tianyi Cui 0ac1d4d865 test(perf): align browser provisioning with hosted benchmark runner 2026-09-07 13:29:38 +08:00