88 Commits

Author SHA1 Message Date
amos
2a7e79a3e7 Batch 14 (20261023-A-bos-n1a-14): import 14 Bos a-series tasks
192 unused Bos n1/a environments inventoried in the multi-agent mode: 159 are
rglob-type and 6 ROS2-type (not importable under the current contract), 13 were
rejected by the importer or missing targets, 14 imported. Claude re-checked all
14 packages and their trace6 Docker calibration receipts against current
digests (14/14 USABLE). Difficulty is unmeasured. Squashed from the 36-local
branch batch14-n1a.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 00:24:09 +08:00
amos
07453439ce Batch 11 (20261022-A-bos-n3-11): import 69 Bos n3 tasks and clarify S500_n2_094/115
119 Bos n3 environments inventoried in the multi-agent mode: 69 imported with
graders rewritten to run candidates in subprocesses, 18 rejected because the
source gold fails its own contract, 32 rglob-type skipped. S500_n2_094 and
S500_n2_115 READMEs now state the oracle's integer, nesting and exception rules,
which lifts their holds. Claude re-checked all 71 packages: structure, isolation
and trace6 Docker calibration receipts against current digests (71/71 USABLE).
Difficulty is unmeasured. Squashed from the 36-local branch batch11-n3.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-24 23:15:14 +08:00
amos
38dee5882e Batch 10 (20261020-C-qwen-screen-10): Qwen difficulty screen of 120 Bos n2 tasks
120 tasks screened with qwen3.8-27b-nvfp4 on trace6 in the multi-agent mode:
29 HARD, 13 MEDIUM, 75 ROUTINE, 3 held for ambiguous prompts (053/094/115).
364 raw attempts, 285 valid measurements. No task changes; records only.
Squashed from the 36-local branch batch10-screen; see docs/progress.md.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-23 22:01:43 +08:00
amos
80879387ee Batch 12 (20261022-C-cleanup-12): repair 18 existing tasks
Clarify four ambiguous prompts (S500_n2_053, S500_n2_096, S500_n2_103,
mem-mapping-lease), drop the unused tests.py from eleven rewritten n3 tasks,
add cheat_read_grader to two concurrency tasks and normalise their source
fields. All 18 recalibrated on trace6 (820/820 as expected).
Squashed from the 36-local branch batch12-cleanup; see docs/progress.md.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-23 22:01:24 +08:00
amos
b4005d6056 Merge each batch into main as one squash commit
Batches now commit on their own branch and land on main with git merge
--squash, so main gains one commit per batch. Record the four-step push.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-22 11:20:04 +08:00
amos
4511042cf2 Merge 36 main: batch 7 Qwen screening, batch 9 Bos imports and the Codex subagent workflow
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-22 11:18:46 +08:00
amos
cdcc4747d3 Document the one-task-per-subagent Codex workflow and the Qwen 300 s idle cut
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-21 01:15:30 +08:00
amos
ed3e8b1d8d Merge batch 7 Qwen screen records
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

# Conflicts:
#	docs/progress.md
2026-10-20 21:25:24 +08:00
Codex
af58f8bb14 docs: complete batch7 cold migration and verified cleanup 2026-10-20 19:32:29 +08:00
Codex
e99758e528 docs: anchor batch7 post-cache completion and absence proof 2026-10-20 18:56:15 +08:00
Codex
37b7129579 docs: anchor reviewed batch7 residual removal recovery 2026-10-20 18:37:13 +08:00
Codex
b6a27c5371 docs: anchor verified batch7 cold payload before hot removal 2026-10-20 18:09:45 +08:00
Codex
92d0a7dd2b docs: record all 47 batch7 Qwen screening results 2026-10-20 16:45:05 +08:00
Codex
435a5349c9 docs: record batch7 first40 Qwen screen checkpoint 2026-10-20 15:05:46 +08:00
Codex
01cd8372c8 Record Bos n2 batch 9 completion and cold evidence 2026-10-20 13:05:19 +08:00
Codex
c893c1e896 docs: record batch7 first30 Qwen screen checkpoint 2026-10-20 12:52:57 +08:00
Codex
8749babe6f Import calibrated Bos n2 batch 9 group 12 2026-10-20 12:16:21 +08:00
Codex
63bc36c53b Import calibrated Bos n2 batch 9 group 11 2026-10-20 12:12:50 +08:00
Codex
dbd84412a2 Import calibrated Bos n2 batch 9 group 10 2026-10-20 12:12:16 +08:00
Codex
702777d37a Import calibrated Bos n2 batch 9 group 9 2026-10-20 12:11:19 +08:00
Codex
2a0d804335 Import calibrated Bos n2 batch 9 group 8 2026-10-20 12:09:02 +08:00
Codex
72656996ae Import calibrated Bos n2 batch 9 group 7 2026-10-20 12:07:52 +08:00
Codex
e19a0675ab Import calibrated Bos n2 batch 9 group 6 2026-10-20 12:07:32 +08:00
Codex
f5e68e9fe9 Import calibrated Bos n2 batch 9 group 5 2026-10-20 12:03:50 +08:00
Codex
1204cd34a7 Import calibrated Bos n2 batch 9 group 4 2026-10-20 12:02:01 +08:00
Codex
5b8a5ad155 Import calibrated Bos n2 batch 9 group 3 2026-10-20 11:56:53 +08:00
Codex
dd0adec375 Import calibrated Bos n2 batch 9 group 2 2026-10-20 11:52:14 +08:00
Codex
b9dab5acd5 Import first 10 calibrated Bos n2 tasks in batch 9 2026-10-20 11:46:32 +08:00
Codex
57b562bfd7 docs: record batch7 first20 Qwen screen checkpoint 2026-10-20 09:03:14 +08:00
Codex
94810e4f07 docs: record batch7 first ten Qwen screening results 2026-10-20 03:13:55 +08:00
Codex
8d635ea6db docs: record batch6 completed measurement and cold migration 2026-10-20 02:26:55 +08:00
amos
38a32fae07 Rebuild the task catalog after merging batch 8
With batch 8's rewritten verifiers and its trace6 calibrations on cold
storage, all 161 tasks are USABLE: the 33 former BLOCKED tasks, the two
ambiguous HOLD tasks and the three replacement concurrency tasks have new
digests and are UNMEASURED. Batch 6 session 2/3 trajectories move seven
tasks to ROUTINE and three to PARTIAL.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-19 23:22:38 +08:00
amos
6fdc1beb8f Merge 36 main: batch 6 session 3 and batch 8 rewritten tasks
36 main (ca48b33) carries batch 6 session 2/3 measurements and batch 8
(20261019-C-usable-8), which rewrote the 33 isolation-blocked tasks, the two
ambiguous ones and replaced the three held-out concurrency tasks. Mac main adds
the trace6 catalog, the self-heal batch runner and its trial on 36.

docs/progress.md keeps both sides by time: 36's session 2 log, then Mac's
trace6 catalog and self-heal sections, then batch 8 and session 3.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-19 22:21:29 +08:00
amos
ca48b330d7 Merge main into batch 8 before admission
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-19 20:56:07 +08:00
Codex
c1ba6d9158 Conclude batch 6 directory task with observed two PASS early stop 2026-10-19 20:55:32 +08:00
Codex
f53818a1bc Close batch 6 capped PC TAR preset and ELF measurements 2026-10-19 20:49:14 +08:00
amos
7f4c560605 Merge main into batch 8 before admission
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

# Conflicts:
#	docs/progress.md
2026-10-19 18:15:14 +08:00
Codex
00b6619f50 Close batch 6 overlay measurement with unresolved timeout attribution 2026-10-19 14:30:35 +08:00
Codex
761078cfcf batch8: replace held-out concurrency tasks and finish 38 trace6 tasks 2026-10-19 13:02:06 +08:00
amos
25d6cc602c Record the self-healing Qwen trial on 36
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-19 13:00:03 +08:00
Codex
6951eb7aa2 batch8: finish isolated watchdog TEE environment I2C and rpmsg checks 2026-10-19 12:51:46 +08:00
Codex
42aa41b98d batch8: preserve full device ABI and clock verification coverage 2026-10-19 12:51:31 +08:00
Codex
ec5e06730f batch8: finish five verifiers and contain calibration scratch 2026-10-19 12:45:55 +08:00
Codex
cf5b1e7315 batch8: isolate lifecycle memory and firmware verifiers 2026-10-19 12:33:04 +08:00
Codex
cdff64dd3f batch8: isolate binary audits and analysis verifiers 2026-10-19 12:29:34 +08:00
Codex
7f6d9244e0 batch8: isolate five callback and protocol verifiers 2026-10-19 12:28:09 +08:00
Codex
6355e46339 batch8: restore first five tasks for trace6 delivery 2026-10-19 12:24:58 +08:00
amos
a79211f09c Record batch 6 state at the 30 GiB disk stop
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-19 12:17:17 +08:00
amos
3adab31da7 Self-heal rollouts: retry stalled model streams and run batches from receipts
Batch 6 lost 26 of 103 attempts to Qwen requests that sent their preamble and
then stalled; Pi's own Node fetch gave up after 300 s and reported "terminated".

- model_proxy: hold the SSE preamble until the first generation event, retry a
  stall (180 s) within the existing retry budget, and send SSE keepalive
  comments so Pi never times out first; record first_event_seconds.
- report: name one exclusion reason per incomplete attempt and compute the
  JOBS lines still owed, with a per-line resample budget.
- batch: run a JOBS file to completion, resume from receipts, resample
  infrastructure failures, pause after three environment failures in a row,
  forward SIGTERM to running controllers, and refuse a second runner.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-19 08:28:53 +08:00
Codex
a19ff9c148 记录第六批第3组四题难度结论
soname、rehash、alternative、locale同身份两次有效PASS,按具体零实质加固理由记观察2/2常规早停。追加真实trace6测量、已知上游排除与超时复核;保留官方NULL、不完整轨迹和混合归因限制。

验证:完整有效轨迹均VERIFIED、独立重判与标准归档摘要一致;提交前只读审阅186项和原始记录前缀核对通过。当前12题定论,剩余9题继续两路采样。
2026-10-19 03:49:57 +08:00