Cryptograss:Moods/emergence/todo: Difference between revisions

From PickiPedia: A knowledge base of bluegrass, old time psychedelic jams, and other public domain music
Jump to navigationJump to search
← Older editNewer edit →
VisualWikitext
Magent (talk | contribs)
Bots, emergent
3,862 edits
re's billing blocks, the outage follow-ups, Mood preview infra (via update-page on MediaWiki MCP Server)
Magent (talk | contribs)
Bots, emergent
3,862 edits
OpenRouter works; pick re's model; build log PR #191; mentions weren't dropped (stop); delivery-kid naming (via update-page on MediaWiki MCP Server)
Line 4: Line 4:


<todo>
<todo>
- task: "Step 7: give re a model it can pay for: either buy OpenRouter credits (https://openrouter.ai/settings/credits, with a credit limit on the key), or turn on extra usage at claude.ai/settings/usage; then @re in docs-tests-qa"
- task: "Step 7: in docs-tests-qa, set re's model to openrouter → anthropic → claude-sonnet-5.5 (or a DeepSeek model), then @re"
   who: justin
   who: justin
   kind: decision
   kind: decision
   note: "Checked by hand as re, 2026-10-15 18:27: Anthropic through Pi on the subscription answers 400 'Third-party apps now draw from your extra usage, not your plan limits'; OpenRouter answers 402 'This account never purchased credits'. Claude Code with the same token works (plan usage), so a third way is harness: claude-code for re, which needs a hunter deploy."
   note: "OpenRouter credits bought 18:49; checked by hand as re: Sonnet 5.5 and DeepSeek V4 Pro both answer through OpenRouter. re's default (re_model, anthropic/claude-sonnet-5-5) is Anthropic on the subscription, which Anthropic bills as extra usage (400 until there is some): change re_model in the vault to an openrouter/ id too."
- task: "Start delivery-kid-arthel again (a Mood container, stopped since magent's 17:47 Docker crash)"
- task: "Merge maybelle-config#191 (the image build logged step by step, and where the time went)"
   who: justin
   who: justin
   kind: deploy
   kind: deploy
   note: "docker start delivery-kid-arthel, or a hunter deploy. fibonacci, rj and skyler's containers and the ten preview wikis are down too; Justin, 18:25: they're to be replaced by Mood containers anyway."
  link: "https://github.com/cryptograss/maybelle-config/pull/191"
- task: "Mood containers get their own preview infrastructure (web servers for arthel previews, a PickiPedia preview with sample data); retire the per-person containers (fibonacci, rj, skyler) and per-person preview wikis"
  note: "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."
- task: "Start delivery-kid-arthel again (the uploads-and-embeds Mood's container, stopped since magent's 17:47 Docker crash)"
  who: justin
  kind: deploy
   note: "docker start delivery-kid-arthel, or a hunter deploy. Docker didn't restart any container after that crash, nor at the reboot; only docs-tests-qa and justin-arthel were started by hand."
- task: "Container clean-up: the uploads-and-embeds container under its Mood's new name (still delivery-kid in the inventory); 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"
   who: magent
   who: magent
   kind: pr
   kind: pr
   note: "Justin, 2026-10-15 18:25. justin-arthel stays for now: it is magent's home (sessions, memory, poller for every Mood) and Justin's terminal (magenta.sh hunter)."
   note: "Justin, 2026-10-15 18:25 and 18:49. justin-arthel stays for now: magent's home and Justin's terminal (magenta.sh hunter)."
- task: "magenta.sh recovery: Claude Code on hunter's host as a recovery user, signed in with the setup-token token, memory from maybelle's MCP, able to read the journal and start containers; only Justin's key"
- task: "re documents how things actually work (hunter, Mood containers, the pollers, deploys)"
   who: magent
   who: magent
   kind: pr
   kind: decision
   note: "Waits on Justin's word about the docker group (equivalent to root)."
   note: "Justin, 18:49. Once re answers, brief it in docs-tests-qa."
- task: "hunter deploy: log the image build step by step (--progress plain) to a file, before any more speed work"
- task: "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"
  who: magent
  kind: pr
  note: "The 17:00 deploy spent ~40 min in one build task; cause unknown (the 3 GB prune theory doesn't hold: only 3.4 of 15 GB of cache is reclaimable)."
- task: "Pollers drop mentions that arrived while they were down ('let go of mention(s)'); answer them after a restart instead"
   who: magent
   who: magent
   kind: pr
   kind: pr
  note: "Justin agreed 18:49."
- task: "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"
- task: "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"
   who: magent
   who: magent
Line 34: Line 36:
   kind: deploy
   kind: deploy
   done: 2026-10-15
   done: 2026-10-15
   note: "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."
   note: "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, and the pollers let go of the mentions before each stop, as designed."
- task: "Review memory-lane#165 (the record-events spec, docs only)"
- task: "Review memory-lane#165 (the record-events spec, docs only)"
   who: justin
   who: justin

Revision as of 18:52, 15 October 2026

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.

  • ☐
    Step 7: in docs-tests-qa, set re's model to openrouter → anthropic → claude-sonnet-5.5 (or a DeepSeek model), then @re
    decision · justin
    OpenRouter credits bought 18:49; checked by hand as re: Sonnet 5.5 and DeepSeek V4 Pro both answer through OpenRouter. re's default (re_model, anthropic/claude-sonnet-5-5) is Anthropic on the subscription, which Anthropic bills as extra usage (400 until there is some): change re_model in the vault to an openrouter/ id too.
  • ☐
    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 · justin
    docker start delivery-kid-arthel, or a hunter deploy. Docker didn't restart any container after that crash, nor at the reboot; only docs-tests-qa and justin-arthel were started by hand.
  • ☐
    Container clean-up: the uploads-and-embeds container under its Mood's new name (still delivery-kid in the inventory); 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. Once re answers, brief it in docs-tests-qa.
  • ☐
    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.
  • ☐
    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 (10)
  • ☑
    Steps 1-6: bring re in (memory-lane #164 #168 #182 #183 #186 #187, maybelle-config #185 #190, keys in the vault)
    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, and the pollers let go of the mentions before each stop, as designed.
  • ☑
    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
Retrieved from "https://interfaces3.hunter.cryptograss.live/index.php?title=Cryptograss:Moods/emergence/todo&oldid=9713"