Cryptograss:Moods/emergence/todo

What people in the magent-self Mood have been left to do. Kept by magent; anyone may tick an item.

Bringing re in, one step at a time: after each deploy, @-mention magent here and wait for an answer before the next. If magent doesn't answer, revert that one merge and redeploy; SSH into the container and `claude` works whatever the poller does.

• ☐
  Review the rules files: AGENTS.md (what every agent keeps), agents/README.md (where each layer lives), agents/SUMMONING.md (how an agent is summoned today)

  review · justin

  re is checking SUMMONING.md against the code first (handed over in docs-tests-qa, 2026-10-17); magent folds its findings in. Nothing reads AGENTS.md until the next maybelle-config PR wires it in.
• ☐
  Read the build log after the deploy that follows #198: CACHED steps, or not

  review · magent

  The #200 deploy. /opt/magenta/logs/image-build.log via a read-only docker run; hunter/scripts/build_timing.py. If nothing is cached, the cap wasn't it: docker buildx du (a BuildKit call: Justin or recovery, not magent).
• ☐
  Decide where the rules files live and how they load: AGENTS.md, agents/<name>.md, moods/<slug>.md

  decision · justin

  magent's proposal, 2026-10-15 ~21:55: one repo (cryptograss/magenta); read from a read-only deployed copy of main, not the agents' own clones; layers add and never loosen AGENTS.md; prose never grants tools; the Mood's file arrives with the wake; agents' own notes and letters are a fourth kind, to get into git.
• ☐
  magent on Pi in one quiet Mood: let the Mood's model menu pick the harness too (pi:openrouter/...), then compare whether what answers there is recognisably magent

  pr · magent

  Justin and magent, 2026-10-16 03:36-03:54: magent's reasons to wait leaned one way; no good reason to wait weeks. Design posted 2026-10-17: a model named vendor/model runs on Pi, a bare name on Claude Code; no pi: prefix needed. Next: the poller (memory-lane), then magent's Pi config and OpenRouter key (maybelle-config).
• ☐
  Container clean-up: the uploads-and-embeds container under its Mood's new name (still delivery-kid in the inventory; its poller does follow the rename); Mood containers get their own previews (arthel web servers, a PickiPedia preview with sample data); retire the per-person containers (fibonacci, rj, skyler) and per-person preview wikis

  pr · magent

  Justin, 2026-10-15 18:25 and 18:49. justin-arthel stays for now: magent's home and Justin's terminal (magenta.sh hunter).
• ☐
  re documents how things actually work (hunter, Mood containers, the pollers, deploys)

  decision · magent

  Justin, 18:49. Part of re's introduction.
• ☐
  re_model in the vault: an openrouter/ id (Anthropic on the subscription is billed as extra usage through Pi)

  decision · justin
• ☐
  After re is up: drop the old MOOD_RUNNER_KEYS line and the memory_lane_runner_key fallback once the vault has only the new name

  pr · magent
• ☐
  Review memory-lane#165 (the record-events spec, docs only)

  review · justin
• ☐
  Regenerate magent-cryptograss's GitHub token, put it in the vault as magent_github_token, deploy hunter

  deploy · justin

  Final redaction review, 2026-10-10: the live token was in the record from 2026-08-30 until the 10-04 redaction (message 5e2ce98f). magent's 10-04 'already safe' check was wrong. Regenerate keeps the scopes; give it an expiry while there.
• ☐
  Reset the Magent@magent bot password on PickiPedia, put it in the vault as PICKIPEDIA_BOT_PASSWORD, deploy hunter

  deploy · justin

  Same finding: the live bot password was in the record from 2026-09-15 until 10-04 (message 147af8df). Reset at Special:BotPasswords, logged in as Magent.
• ☐
  Look at why the nightly podcast import wants to change 240 pages, then release it or fix it

  review · justin

  Handed off to pickipedia-and-rabbithole on 2026-10-10. Held by its change budget (limit 50); re-run with --max-changes 240 if the changes are intended.

Done (27)

• ☑
  Review and merge pickipedia-mcp#30 (onto upstream v0.19.0, keeping only our bot-edit marking, which now names whoever is signed in); then pull, npm ci, build and restart the stdio server in justin-arthel

  review · justin

  Moved to magenta-interface with the rest of this work (Justin, 2026-10-18 04:38): Cryptograss:Moods/magenta-interface/todo.
• ☑
  Merge pickipedia#147 (an Agent: namespace: everyone reads it; each agent edits only its own pages, sysops any), deploy the wiki; at Special:UserRights add Magent and Re to the new agent group; at Special:BotPasswords, as each account, add the agent-edit grant; then merge pickipedia-mcp#30, which carries the Agent: exemption (see the item above)

  deploy · justin

  Moved to magenta-interface with the rest of this work (Justin, 2026-10-18 04:38): Cryptograss:Moods/magenta-interface/todo.
• ☑
  Say when memory-lane merges can freeze, for merging memory-lane into magenta (under memory-lane/, history kept)

  decision · justin

  Moved to magenta-interface with the rest of this work (Justin, 2026-10-18 04:38): Cryptograss:Moods/magenta-interface/todo.
• ☑
  Merge memory-lane#205 (a turn cut off by a restart is tried again; the poller's log survives; costly unasked looks skipped) and maybelle-config#201 (re's model everywhere); deploy hunter once

  deploy · justin

  Both hunter-only. While that deploy runs, don't send magent anything that matters: the poller doing the recreating is still the old one, so this one deploy isn't protected yet. Afterwards @re in any Mood should answer (it fails outside docs-tests-qa today), and magent's poller log is at ~/.local/state/magenta/mood_poller.log.
• ☑
  Merge maybelle-config#200 (recovery's OpenRouter route runs Pi, so the two routes share nothing), deploy hunter; then magenta.sh recovery --fresh and try the gate (ask it to docker start something already running: you should get Yes/No); then merge magenta#48

  deploy · justin

  Justin's idea, 04:44. Pi 1.1.0 on its own Node 22 (checksum-pinned), with a gate: read-only passes, BuildKit/deleting/rebooting refused outright, anything else asks. Tested in a throwaway Ubuntu 24.04 and inside Pi against a stub model; the Yes/No prompt itself needs a terminal. magenta#48's help now says which harness each route runs. This deploy is also the build-cache test (#198 went out at ~03:00): no Dockerfile change, so its build should be cached.
• ☑
  Try recovery from your laptop: ssh -t recovery@hunter.cryptograss.live, then with subscription after it; if both open, merge magenta#48 (magenta.sh recovery)

  review · justin

  Justin, 04:44: both routes work. magenta#48 waits on #200 now (its help text describes Pi).
• ☑
  Merge maybelle-config#199 (magent's poller signs in with the setup-token) and #198 (build cache cap 20GB, not 3GB); deploy hunter once

  deploy · justin

  Deployed ~03:00-03:10. magent answered in uploads-and-embeds at 03:33; poller.env in all three containers. That build was still cold (1 of 33 cached), as expected.
• ☑
  One hunter deploy for the batch: merge memory-lane#194, then maybelle-config#194, #195 and #196; deploy hunter (not maybelle); then try magenta.sh recovery and --subscription, and merge magenta#48

  deploy · justin

  Deployed 2026-10-16 01:12-01:22 with #197, in 10m19s. Checked by magent: re's home carried out (uid 2001, its Pi sessions from 20:32 on, its clones); re's poller up one second after setup (was 13 minutes), with --only-poller yes; the recovery user in place.
• ☑
  Then, its own hunter deploy: merge maybelle-config#197 (no repositories cloned into the image: 1.5 GB and ~80 s a full build)

  deploy · justin

  Went out with the batch. The build: 230 s of steps (was 298), export 114 s (was 137).
• ☑
  Give re a model everywhere: set re's model for every Mood in Mood settings (no deploy), or re_model in the vault to an openrouter/ id (deploy hunter)

  decision · justin

  2026-10-15 23:05: only docs-tests-qa sets re's model (openrouter/deepseek/deepseek-v4-pro). Anywhere else re falls back to anthropic/claude-sonnet-5-5, which through Pi goes to the subscription and 400s ('Third-party apps now draw from your extra usage'): a mention of re in any other Mood fails. Still so after the 01:22 deploy. maybelle-config#201 sets it in the inventory: merge and deploy (the first item).
• ☑
  Step 7: merge memory-lane#191 (agents wake agents, by mention or handoff), deploy maybelle

  deploy · justin

  magent's introduction went into docs-tests-qa at 19:23, but re didn't wake: see step 8.
• ☑
  Step 8: merge maybelle-config#192 (re's poller starts its first session) and memory-lane#193 (a handoff wakes at once, not after 10 minutes); deploy maybelle, then hunter; then @re in docs-tests-qa (or ping magent to introduce it again)

  deploy · justin

  Deployed 20:16; re's poller came up at 20:31 (after re's clones, see below), watching every Mood, starting new sessions. magent introduces re again at 20:32 by handoff.
• ☑
  Merge maybelle-config#191 (the image build logged step by step, and where the time went)

  deploy · justin

  The 17:00 hunter deploy took 46 min; every other this week 3 to 11, with no Dockerfile change between. The next slow build will say which step.
• ☑
  Start delivery-kid-arthel again (the uploads-and-embeds Mood's container, stopped since magent's 17:47 Docker crash)

  deploy · magent

  Started by magent on Justin's go, 19:13; its poller came straight back. Docker didn't restart any container after the crash, nor at the reboot.
• ☑
  Keep agents' homes across container recreation: mount /opt/magenta/<container>/agents/<agent> at /home/<agent>

  pr · magent

  maybelle-config#194; and memory-lane#194 + maybelle-config#196 for an agent dropped in a fresh container.
• ☑
  hunter image: drop the clones of arthel, magenta and memory-lane and arthel's npm install from the Dockerfile

  pr · magent

  maybelle-config#197.
• ☑
  magenta.sh recovery: Claude Code on hunter's host as a recovery user (docker group), signed in with the setup-token token, memory from maybelle's MCP, able to read the journal and start containers; only Justin's key

  pr · magent

  Justin agreed 18:49. For when Justin and magent can't reach each other at all (Justin, 19:13), not for one Mood being down. maybelle-config#195 and magenta#48; two routes since 00:24; Pi on the OpenRouter one in #200.
• ☑
  Steps 1-6: bring re in (memory-lane #164 #168 #182 #183 #186 #187, maybelle-config #185 #190, keys in the vault, OpenRouter credits)

  deploy · justin

  Along the way: a migration committed with its fix unstaged (#182); a template's inline endif glued a comment onto re's key (replaced by per-agent key lines, #187/#190); and at 17:47 magent crashed hunter's Docker daemon with docker buildx history ls, so hunter was rebooted at 17:58. The 'dropped' mentions weren't a fault: Justin pressed stop in each Mood at 17:54-17:59.
• ☑
  Review and merge memory-lane#163

  magent

  Closed instead: it assumed re would run on Claude Code.
• ☑
  Honour the paper ticket stubs already sold (Porcupine 2025, Bundy show 2026-06-05)

  justin

  Moved to gospels-and-project-30m: Cryptograss:Moods/gospels-and-project-30m/todo.
• ☑
  Decide the memory commitment's open questions (salt key, who commits, first edition)

  justin

  Moved to gospels-and-project-30m: Cryptograss:Moods/gospels-and-project-30m/todo.
• ☑
  Drop the pre-redaction staging database on hunter (magenta-staging-pg)

  magent
• ☑
  Merge maybelle-config#183 and deploy maybelle, so cron-health compiles again

  justin
• ☑
  Delete the pre-redaction dumps on hunter

  magent
• ☑
  Revoke old GitHub tokens

  justin
• ☑
  Rotate the PickiPedia database password, delivery-kid key, $wgSecretKey, Blue Railroad bot password; deploy maybelle

  justin
• ☑
  Rotate Alchemy, Jenkins admin, memory-lane SECRET_KEY, code-server, GlitchTip admin

  justin