docs: microVM tier on 2.1.276 — three backends proven, the canary's catch, and what stays open
deploy / test (push) Successful in 5m4s
deploy / build (push) Successful in 59s

Co-Authored-By: Claude Opus 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01WZb5A2kfVfjpdwSochkuHz
This commit is contained in:
Omar Sobh
2026-09-18 21:08:35 -05:00
co-authored by Claude Opus 5
parent cbc9c2d353
commit 9bc1e7fc52
+35 -3
View File
@@ -106,9 +106,11 @@ guessed family.
that cheaper; it did not ask why a research verdict needs 12 commands. 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 Watch `requests` per verdict on the next few missions. If it stays at the
cap, the lever is the judge prompt, not the budget. cap, the lever is the judge prompt, not the budget.
2. **microVM tier is unexercised since v0.8.5.** Fleet is online; every run 2. ~~**microVM tier is unexercised since v0.8.5.**~~ Closed 2026-09-18: three
this pass was container-tier. Run one microVM mission before assuming the VM missions on Claude Code 2.1.276 — claude `01a0b75e`, glm `01a0b761`,
upgrade left that path alone. 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 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 8790% into the unread in 2 of the last 3 runs; the skills section sits 8790% into the
prompt. Position is the untested lever. 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 claude --version`), never the persistent runtime's, before attaching a version
to a measurement. 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 2.1.2232.1.226 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`.