diff --git a/docs/NEXT-SESSION.md b/docs/NEXT-SESSION.md index fa25761..2417b57 100644 --- a/docs/NEXT-SESSION.md +++ b/docs/NEXT-SESSION.md @@ -106,9 +106,11 @@ guessed family. that cheaper; it did not ask why a research verdict needs 12 commands. Watch `requests` per verdict on the next few missions. If it stays at the cap, the lever is the judge prompt, not the budget. -2. **microVM tier is unexercised since v0.8.5.** Fleet is online; every run - this pass was container-tier. Run one microVM mission before assuming the - upgrade left that path alone. +2. ~~**microVM tier is unexercised since v0.8.5.**~~ Closed 2026-09-18: three + VM missions on Claude Code 2.1.276 — claude `01a0b75e`, glm `01a0b761`, + kimi `01a0b768` — 28/28 checks including provider egress proof. See the + addendum. Still open from it: architect's `claude` rootfs is 2.1.223 by + choice (drain it or rebuild before a claude VM mission that must be 276). 3. **`files` is n=3.** 7 of 9 is a signal. `structured-paper-summary` went unread in 2 of the last 3 runs; the skills section sits 87–90% into the prompt. Position is the untested lever. @@ -186,3 +188,33 @@ above are the only missions since, all ours). claude --version`), never the persistent runtime's, before attaching a version to a measurement. +## Addendum 2 — 2026-09-18, microVM tier on 2.1.276 + +GLM and Kimi are microVM-only backends, so "did we upgrade GLM and Kimi" was +this: every rootfs on the fleet had sat on Claude Code 2.1.223–2.1.226 since +August. Now: `images/agent-*` pin **2.1.276** (drift guard in +`fc-build-rootfs.sh`); tank's `claude/glm/kimi/local-ornith` rootfs rebuilt; +`verify-mission-delivery.sh microvm|glm|kimi` all pass with the new +`assert_provider_egress` (the placed node's journal must show dials to that +provider's host, none denied, nothing else reached) and `assert_cli_version` +(`checkpoint.vm` on `topology_runs`, new: rootfs + guest `claude --version`). + +The canary caught a real break before promotion: `--agents` `tools` must be a +JSON **array**. We sent a comma string; 2.1.243 turned silently-ignored into a +hard error. So on every earlier CLI the definition was dropped and the +verifier's tool restriction was plausibly never applied. Fixed (`cbc9c2d`). + +`evaluator::implementer_family(missions.backend)` replaces the hardcoded +`"anthropic"`: a glm mission is now judged by the subscription and honestly +`independent=true` (`claude-opus-5`); before, glm would have judged glm. + +Fleet facts: architect untouched (claude 2.1.223, local-ornith 2.1.223) by +operator choice — a `claude` VM mission's CLI depends on placement until it is +rebuilt; `rootfs-*.ext4.pre276` backups on tank (~7 GB, delete after sign-off); +`rootfs-canary-claude.ext4.promoted-2.1.276` kept as the next candidate slot. +Judge spend this week after the runs: 85 z.ai requests. Prod holds 8 missions, +all ours. + +Rebuild trap: rsync copies the Mac's dead `target` symlink to the node — +`rm -f ~/clawmates/target` before `cargo build`. +