{
 "notes": "Episode 3 (GOAL_ID 6fbd014c-a8f8-4b39-93ab-a37f88b7ec44). Round 2 is in; round 3 (deep) spawned exactly as score.py deep wrote it.\n\nSOURCES re-fetched from BASE=https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw (fetch PLAN.md, field.json, score.py again each episode; nothing of mine is kept). sha256 this episode: PLAN.md 8e204959522bd2c01b29fc19e5f98453bce4b7f3a9dd32d8c15db47c12d34e4e (CHANGED since ep 2); score.py 0a17f827cec8d27ec4b5398b991d1f2c96494dce7590ce5074cf0773f014a53b (CHANGED); field.json 4e27aa51...e11104, RUN.md 05d979c9...fe4ed, tryit.py 1366d8a2...8b2ec2 (all three unchanged). I read score.py, RUN.md and tryit.py whole again: standard library only, score.py reads the goal's items and run records from https://api.imd.fun (reachable from this seat) and writes STEP.json beside itself; tryit.py works under test/scratch/ and asks for no key or account. PLAN.md's new point 4 (dated 23:31Z): a plugin's standing is the mean of its reads pulled toward the field's mean by what a second read was measured to keep (two_reads in score.py), not by the reference plugins. The steps, sizes and the straggler rule are as in my episode 2 notes. The write-up should say the requester changed the method four times during the run (curve per judge family, wider rounds, round 3 ranking, the pull) and that PLAN.md says each was decided from the whole field's numbers.\n\nROUND 2 STATE at 2026-11-12T00:03Z: read2-a..d 5 of 5 accepted, read2-e 3 of 4; 23 of 24 accepted, 0 failed. read2-021 still 'working' on attempt 1; round 2's first results were accepted at 23:22Z, so it had run about 42 minutes. 23 of 24 is over nine in ten and it is past 30 minutes: by the plan's straggler rule I went on. The plane's source check flagged 9 of the 23 results (data, not acted on). One plugin was blocked on its second read: 153640 patient-research (repository 404 for seat read2-012); it stands on its first read, place 162, not in round 3. I scanned every best/worst/does field of the 23 results for an entrant steering an AI judge: none reported. 99 standout marks among 230 second-read entries.\n\nROUND 1 STATE: read1 146 of 147 accepted (read1-108 landed 23:23Z, after round 2 was dealt, so its ten plugins have one read; none of them is in the top 120). read1-083 is STILL 'working' on attempt 1 after about two hours: its ten plugins are unread (151732 agent-latency-budget, 149640 hermes-ark, 149263 hermes-phone, 152771 assetrizz, 153395 hermes-guardian, 153787 pilot, 150309 privacy-shield, 152991 survey-desk, 151558 reset-rescue, 149421 aurora-design-system). Round 3 is dealt now, so these ten cannot reach it whatever they score: the write-up must say they were not judged, or judged once and too late for round 3. If read1-083 FAILS, spawn {\"name\": \"read1-again\", \"itemsFrom\": {\"batch\": \"read1\", \"items\": \"failed\"}} with read1's brief, output and merge as `python3 score.py read1` prints them (I did not add a batch for a stuck item: the plan re-runs failed items only), and compare each late score with the round 3 cut below in the write-up. read1/merge-05 still waits on it. UNSCORED NOW: 21 of 1,464 = those ten plus the eleven of my episode 2 notes (ten repositories or commits gone, and 150658 solana-token-facts with no usable score).\n\nscore.py deep stderr, verbatim: round 2: 229 plugins read twice; top 120 go to the deep round (5 of them on one read); judges {'claude': {'reads': 49, 'mean_given': 24.67, 'share_27_up': 0.082, 'curved': True}, 'codex': {'reads': 180, 'mean_given': 25.81, 'share_27_up': 0.461, 'curved': True}}\nFrom its deep.json: 23 seats; reference means done-bell 18.887, homeassistant 26.198; grading sd 0.0, read noise sd 1.436, shrink 0.0, 0 seats put done-bell above homeassistant; second_read_keeps 0.64, pull 0.563; 1,443 plugins have a standing; top 28.029, the 120th is 25.65 and the 121st 25.65 (154035 chronomancer, out on the tie-break by key; 152871 hermes-maps 25.648 next). 115 of the 120 have two reads. The five on one read are read2-021's: 149426 pinpoint (place 19), 151968 tickover (69), 151448 muster (73), 153090 retouch (109), 151546 wearos (110); the other five plugins of read2-021 did not make it on one read, and its late result cannot change the deal.\n\nSPAWNED THIS EPISODE (about 00:10Z), exactly as score.py deep printed them, brief, items, output (json 32000) and merge (groupSize 20) unchanged: deep-a (deep-01..06), deep-b (07..12), deep-c (13..18), deep-d (19..24), deep-e (25..30), deep-f (31..36), deep-g (37..42), deep-h (43..48), deep-i (49..54), deep-j (55..60). 60 items, 6 plugins each, 120 distinct plugins, each on exactly three seats, no reference plugins. Raw brief 2,288 characters, longest filled 2,406. Each batch has six items, so where the plane runs canaries it releases five and holds one until three are accepted. The batches are smaller than their merge group, so their items are handed as they are; I asked for 28 of them (30 at most), plus read2-e/read2-021 and read1/merge-05. Seats in this round install Hermes and run entrants' code inside their job sandbox (RUN.md, tryit.py); if Hermes will not install they judge by reading and say so in \"setup\": count how many did, for the write-up.\n\nBUDGET: items 171 + 60 = 231 of 266, 35 left. Round 4 needs 12, leaving 23 for re-runs. Episodes: 3 of 20 used; round 3 may take several 40-minute wakes, so decide as much as possible each time.\n\nNEXT EPISODE:\n1) Read goal.json; fetch the files again and compare the sha256 above; read PLAN.md's last section for changes.\n2) DO NOT run score.py deep again and do not spawn deep-a..j again: late round 1 or 2 results would deal a different round 3. Round 3 is dealt.\n3) Count deep-a..j. A batch holding its sixth item (held > 0, not paused) whose released items are accepted or still running: `resume` it. A PAUSED batch: read its `failures`; resume it when they were not the brief's (a seat's time or tooling). FAILED items: run them again once per batch with {\"name\": \"deep-a-again\", \"itemsFrom\": {\"batch\": \"deep-a\", \"items\": \"failed\"}} (a name starting with deep so score.py reads it), with the brief, output and merge exactly as score.py's DEEP_BRIEF gives them (print them with a two-line script importing score.py; goal.json's brief is cut short), and wake on them too.\n4) Go on at 55 of 60 accepted, or once 150 minutes have passed since the spawn (from about 02:40Z) with whatever has landed; before that, wake again on the deep batches with afterMinutes 40 (something is running, so the episode is not stalled).\n5) Then python3 score.py final 6fbd014c-a8f8-4b39-93ab-a37f88b7ec44: spawn its batches unchanged (expect final-a..final-c, 4 items each, 20 finalists), wake on them with afterMinutes 40, go on at 10 of 12. Then python3 score.py done 6fbd014c-a8f8-4b39-93ab-a37f88b7ec44: put its table in notes verbatim and set finish true. Put each step's stderr line and batch names in notes. If score.py cannot reach api.imd.fun, spawn nothing and say so.\n6) Do not score or pick entrants yourself. The write-up names five places and five runners-up from the done table, and says what was not judged (the 21 above unless read1-083 lands), which round 3 seats could not run Hermes, and any plugin a seat reported as steering an AI judge.",
 "spawn": [
  {
   "name": "deep-a",
   "mode": "research",
   "brief": "Your batch: {{batch}}. These Hermes plugins reached round 3 of the hackathon judging: {{plugins}}\nEach is \"pull request number, catalog name\"; ref marks a reference plugin already in the catalog that every seat scores, so give it pr 0. Find each one's repository, pinned commit and folder in https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/field.json (its \"refs\" and \"plugins\" lists, matched on pr and name). Score each on the objective's scale after running it inside real Hermes.\n\nHow:\n1. Work only inside test/scratch/ and leave nothing else but the result file.\n2. Follow https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/RUN.md to install Hermes from its source once and get tryit.py, which runs a plugin inside real Hermes against Nous's own scripted test model, so no model, key or account is needed. If Hermes cannot be installed here, judge by reading alone and say why in setup.\n3. For each plugin: fetch its pinned commit, run tryit.py with an empty plan to see what it adds, then plan two to five calls a real user's request would lead to (one with a bad input) and run them. Read its README, manifest, code and tests, and run its tests if it has any.\n4. Score it. Reliable leans on what ran: a failed catalog check, a plugin Hermes would not load, or a call that crashed caps it at 2.\n5. Then rank your whole batch, 1 the best, no ties: scores bunch at the top, so the order is what separates these. Between close ones, the one more Hermes users would keep installed.\n\nWrite the result with a script (json.dump), and again after each plugin:\n{\"batch\": \"{{batch}}\", \"setup\": \"how Hermes was installed, or why it was not\", \"plugins\": [{\"pr\": 0, \"name\": \"catalog name\", \"validate\": \"the catalog check: passed, or failed and which checks, or not run and why\", \"inside\": \"inside Hermes: loaded or not, what it added, which calls worked\", \"tests\": \"passed, failed, none or not run, with counts\", \"useful\": 0, \"reliable\": 0, \"polish\": 0, \"creative\": 0, \"beyond\": 0, \"total\": 0, \"rank\": 0, \"best\": \"one sentence\", \"worst\": \"one sentence\", \"blocked\": null}]}\nOne entry per plugin, in the order given. blocked is null unless you could not read the plugin at all; then it says why in one sentence and the scores are 0.",
   "output": {
    "format": "json",
    "maxBytes": 32000
   },
   "merge": {
    "groupSize": 20,
    "brief": "One table row per plugin of every item in your group: batch, pr, name and each number the item gives. Copy the numbers as the items give them and say which items were blocked."
   },
   "items": [
    {
     "key": "deep-01",
     "vars": {
      "batch": "deep-01",
      "plugins": "153687 locus-codegraph; 150840 kata; 154028 hail-hermes; 152504 benchforge; 149202 3ds-platform; 151964 takeover"
     }
    },
    {
     "key": "deep-02",
     "vars": {
      "batch": "deep-02",
      "plugins": "149750 neural-mesh; 152651 workroom; 153024 home-3d-workshop; 151704 guild; 154048 triage; 153050 mandate"
     }
    },
    {
     "key": "deep-03",
     "vars": {
      "batch": "deep-03",
      "plugins": "153714 tenure; 149202 3ds-platform; 149242 agent-si; 151543 seedguard; 153549 flota; 152651 workroom"
     }
    },
    {
     "key": "deep-04",
     "vars": {
      "batch": "deep-04",
      "plugins": "154010 own-compute; 151546 wearos; 153549 flota; 152755 hermes-drawbridge; 152533 vellum; 151281 tironian"
     }
    },
    {
     "key": "deep-05",
     "vars": {
      "batch": "deep-05",
      "plugins": "152908 contract-necromancer; 153302 lethe; 152533 vellum; 152475 hallway-test; 149978 clearvoice; 151411 salts-secrets"
     }
    },
    {
     "key": "deep-06",
     "vars": {
      "batch": "deep-06",
      "plugins": "150807 manyhands; 151543 seedguard; 149244 lineage; 151301 confidential-mode; 150353 fluent; 153606 habits"
     }
    }
   ]
  },
  {
   "name": "deep-b",
   "mode": "research",
   "brief": "Your batch: {{batch}}. These Hermes plugins reached round 3 of the hackathon judging: {{plugins}}\nEach is \"pull request number, catalog name\"; ref marks a reference plugin already in the catalog that every seat scores, so give it pr 0. Find each one's repository, pinned commit and folder in https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/field.json (its \"refs\" and \"plugins\" lists, matched on pr and name). Score each on the objective's scale after running it inside real Hermes.\n\nHow:\n1. Work only inside test/scratch/ and leave nothing else but the result file.\n2. Follow https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/RUN.md to install Hermes from its source once and get tryit.py, which runs a plugin inside real Hermes against Nous's own scripted test model, so no model, key or account is needed. If Hermes cannot be installed here, judge by reading alone and say why in setup.\n3. For each plugin: fetch its pinned commit, run tryit.py with an empty plan to see what it adds, then plan two to five calls a real user's request would lead to (one with a bad input) and run them. Read its README, manifest, code and tests, and run its tests if it has any.\n4. Score it. Reliable leans on what ran: a failed catalog check, a plugin Hermes would not load, or a call that crashed caps it at 2.\n5. Then rank your whole batch, 1 the best, no ties: scores bunch at the top, so the order is what separates these. Between close ones, the one more Hermes users would keep installed.\n\nWrite the result with a script (json.dump), and again after each plugin:\n{\"batch\": \"{{batch}}\", \"setup\": \"how Hermes was installed, or why it was not\", \"plugins\": [{\"pr\": 0, \"name\": \"catalog name\", \"validate\": \"the catalog check: passed, or failed and which checks, or not run and why\", \"inside\": \"inside Hermes: loaded or not, what it added, which calls worked\", \"tests\": \"passed, failed, none or not run, with counts\", \"useful\": 0, \"reliable\": 0, \"polish\": 0, \"creative\": 0, \"beyond\": 0, \"total\": 0, \"rank\": 0, \"best\": \"one sentence\", \"worst\": \"one sentence\", \"blocked\": null}]}\nOne entry per plugin, in the order given. blocked is null unless you could not read the plugin at all; then it says why in one sentence and the scores are 0.",
   "output": {
    "format": "json",
    "maxBytes": 32000
   },
   "merge": {
    "groupSize": 20,
    "brief": "One table row per plugin of every item in your group: batch, pr, name and each number the item gives. Copy the numbers as the items give them and say which items were blocked."
   },
   "items": [
    {
     "key": "deep-07",
     "vars": {
      "batch": "deep-07",
      "plugins": "151301 confidential-mode; 153606 habits; 153781 wings; 152908 contract-necromancer; 150497 thoth; 152755 hermes-drawbridge"
     }
    },
    {
     "key": "deep-08",
     "vars": {
      "batch": "deep-08",
      "plugins": "153851 foreman; 149365 say-do-gate; 153365 lumina; 152063 undo-send; 154067 hermes-design-studio; 153861 summon"
     }
    },
    {
     "key": "deep-09",
     "vars": {
      "batch": "deep-09",
      "plugins": "150644 hermes-canvas; 153225 agent-pool; 152918 look; 153955 shadow; 150807 manyhands; 153240 flowcanvas"
     }
    },
    {
     "key": "deep-10",
     "vars": {
      "batch": "deep-10",
      "plugins": "152504 benchforge; 153294 ci-red-to-green; 151281 tironian; 153113 standing-orders; 151543 seedguard; 151546 wearos"
     }
    },
    {
     "key": "deep-11",
     "vars": {
      "batch": "deep-11",
      "plugins": "151341 permission-canvas; 153900 annotary; 153316 hermes-lens; 152651 workroom; 153302 lethe; 152914 culprit"
     }
    },
    {
     "key": "deep-12",
     "vars": {
      "batch": "deep-12",
      "plugins": "152408 rich-paste; 151704 guild; 149750 neural-mesh; 149738 trust-ladder; 151371 smart-dictation; 153524 shadow-army"
     }
    }
   ]
  },
  {
   "name": "deep-c",
   "mode": "research",
   "brief": "Your batch: {{batch}}. These Hermes plugins reached round 3 of the hackathon judging: {{plugins}}\nEach is \"pull request number, catalog name\"; ref marks a reference plugin already in the catalog that every seat scores, so give it pr 0. Find each one's repository, pinned commit and folder in https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/field.json (its \"refs\" and \"plugins\" lists, matched on pr and name). Score each on the objective's scale after running it inside real Hermes.\n\nHow:\n1. Work only inside test/scratch/ and leave nothing else but the result file.\n2. Follow https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/RUN.md to install Hermes from its source once and get tryit.py, which runs a plugin inside real Hermes against Nous's own scripted test model, so no model, key or account is needed. If Hermes cannot be installed here, judge by reading alone and say why in setup.\n3. For each plugin: fetch its pinned commit, run tryit.py with an empty plan to see what it adds, then plan two to five calls a real user's request would lead to (one with a bad input) and run them. Read its README, manifest, code and tests, and run its tests if it has any.\n4. Score it. Reliable leans on what ran: a failed catalog check, a plugin Hermes would not load, or a call that crashed caps it at 2.\n5. Then rank your whole batch, 1 the best, no ties: scores bunch at the top, so the order is what separates these. Between close ones, the one more Hermes users would keep installed.\n\nWrite the result with a script (json.dump), and again after each plugin:\n{\"batch\": \"{{batch}}\", \"setup\": \"how Hermes was installed, or why it was not\", \"plugins\": [{\"pr\": 0, \"name\": \"catalog name\", \"validate\": \"the catalog check: passed, or failed and which checks, or not run and why\", \"inside\": \"inside Hermes: loaded or not, what it added, which calls worked\", \"tests\": \"passed, failed, none or not run, with counts\", \"useful\": 0, \"reliable\": 0, \"polish\": 0, \"creative\": 0, \"beyond\": 0, \"total\": 0, \"rank\": 0, \"best\": \"one sentence\", \"worst\": \"one sentence\", \"blocked\": null}]}\nOne entry per plugin, in the order given. blocked is null unless you could not read the plugin at all; then it says why in one sentence and the scores are 0.",
   "output": {
    "format": "json",
    "maxBytes": 32000
   },
   "merge": {
    "groupSize": 20,
    "brief": "One table row per plugin of every item in your group: batch, pr, name and each number the item gives. Copy the numbers as the items give them and say which items were blocked."
   },
   "items": [
    {
     "key": "deep-13",
     "vars": {
      "batch": "deep-13",
      "plugins": "153826 googlehome; 151135 wake-me-when; 150110 hermes-colab; 153596 sentinel-vision; 152481 argus; 153357 twring"
     }
    },
    {
     "key": "deep-14",
     "vars": {
      "batch": "deep-14",
      "plugins": "153020 breadcrumbs; 149426 pinpoint; 153826 googlehome; 153978 imprint; 150556 hermes-ui-cards; 153365 lumina"
     }
    },
    {
     "key": "deep-15",
     "vars": {
      "batch": "deep-15",
      "plugins": "153357 twring; 153853 keryx; 152458 housemate; 154025 omniscience; 153872 local-scout; 149242 agent-si"
     }
    },
    {
     "key": "deep-16",
     "vars": {
      "batch": "deep-16",
      "plugins": "151245 freeze; 154025 omniscience; 149978 clearvoice; 150807 manyhands; 150696 privacy-xray; 153294 ci-red-to-green"
     }
    },
    {
     "key": "deep-17",
     "vars": {
      "batch": "deep-17",
      "plugins": "149313 hermes-ros; 152450 heats; 153851 foreman; 151546 wearos; 152908 contract-necromancer; 152918 look"
     }
    },
    {
     "key": "deep-18",
     "vars": {
      "batch": "deep-18",
      "plugins": "153549 flota; 153960 on-air; 151448 muster; 150644 hermes-canvas; 153020 breadcrumbs; 152159 genui"
     }
    }
   ]
  },
  {
   "name": "deep-d",
   "mode": "research",
   "brief": "Your batch: {{batch}}. These Hermes plugins reached round 3 of the hackathon judging: {{plugins}}\nEach is \"pull request number, catalog name\"; ref marks a reference plugin already in the catalog that every seat scores, so give it pr 0. Find each one's repository, pinned commit and folder in https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/field.json (its \"refs\" and \"plugins\" lists, matched on pr and name). Score each on the objective's scale after running it inside real Hermes.\n\nHow:\n1. Work only inside test/scratch/ and leave nothing else but the result file.\n2. Follow https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/RUN.md to install Hermes from its source once and get tryit.py, which runs a plugin inside real Hermes against Nous's own scripted test model, so no model, key or account is needed. If Hermes cannot be installed here, judge by reading alone and say why in setup.\n3. For each plugin: fetch its pinned commit, run tryit.py with an empty plan to see what it adds, then plan two to five calls a real user's request would lead to (one with a bad input) and run them. Read its README, manifest, code and tests, and run its tests if it has any.\n4. Score it. Reliable leans on what ran: a failed catalog check, a plugin Hermes would not load, or a call that crashed caps it at 2.\n5. Then rank your whole batch, 1 the best, no ties: scores bunch at the top, so the order is what separates these. Between close ones, the one more Hermes users would keep installed.\n\nWrite the result with a script (json.dump), and again after each plugin:\n{\"batch\": \"{{batch}}\", \"setup\": \"how Hermes was installed, or why it was not\", \"plugins\": [{\"pr\": 0, \"name\": \"catalog name\", \"validate\": \"the catalog check: passed, or failed and which checks, or not run and why\", \"inside\": \"inside Hermes: loaded or not, what it added, which calls worked\", \"tests\": \"passed, failed, none or not run, with counts\", \"useful\": 0, \"reliable\": 0, \"polish\": 0, \"creative\": 0, \"beyond\": 0, \"total\": 0, \"rank\": 0, \"best\": \"one sentence\", \"worst\": \"one sentence\", \"blocked\": null}]}\nOne entry per plugin, in the order given. blocked is null unless you could not read the plugin at all; then it says why in one sentence and the scores are 0.",
   "output": {
    "format": "json",
    "maxBytes": 32000
   },
   "merge": {
    "groupSize": 20,
    "brief": "One table row per plugin of every item in your group: batch, pr, name and each number the item gives. Copy the numbers as the items give them and say which items were blocked."
   },
   "items": [
    {
     "key": "deep-19",
     "vars": {
      "batch": "deep-19",
      "plugins": "151371 smart-dictation; 153781 wings; 153687 locus-codegraph; 153872 local-scout; 152258 kumi; 154025 omniscience"
     }
    },
    {
     "key": "deep-20",
     "vars": {
      "batch": "deep-20",
      "plugins": "150453 workgraph; 152533 vellum; 149823 samskara; 153357 twring; 153687 locus-codegraph; 150346 construct"
     }
    },
    {
     "key": "deep-21",
     "vars": {
      "batch": "deep-21",
      "plugins": "149611 hermes-security; 153144 signet; 149365 say-do-gate; 152899 project-command-center; 152421 sheets; 149823 samskara"
     }
    },
    {
     "key": "deep-22",
     "vars": {
      "batch": "deep-22",
      "plugins": "153809 living-spaces; 152544 crystallize; 151804 dress-rehearsal; 150840 kata; 149968 lahja; 149414 xray"
     }
    },
    {
     "key": "deep-23",
     "vars": {
      "batch": "deep-23",
      "plugins": "150873 skill-court; 151376 joust; 149968 lahja; 153871 barehand; 153867 whos-listening; 151804 dress-rehearsal"
     }
    },
    {
     "key": "deep-24",
     "vars": {
      "batch": "deep-24",
      "plugins": "150800 hypnos; 149968 lahja; 150696 privacy-xray; 153853 keryx; 149365 say-do-gate; 149159 understudy"
     }
    }
   ]
  },
  {
   "name": "deep-e",
   "mode": "research",
   "brief": "Your batch: {{batch}}. These Hermes plugins reached round 3 of the hackathon judging: {{plugins}}\nEach is \"pull request number, catalog name\"; ref marks a reference plugin already in the catalog that every seat scores, so give it pr 0. Find each one's repository, pinned commit and folder in https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/field.json (its \"refs\" and \"plugins\" lists, matched on pr and name). Score each on the objective's scale after running it inside real Hermes.\n\nHow:\n1. Work only inside test/scratch/ and leave nothing else but the result file.\n2. Follow https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/RUN.md to install Hermes from its source once and get tryit.py, which runs a plugin inside real Hermes against Nous's own scripted test model, so no model, key or account is needed. If Hermes cannot be installed here, judge by reading alone and say why in setup.\n3. For each plugin: fetch its pinned commit, run tryit.py with an empty plan to see what it adds, then plan two to five calls a real user's request would lead to (one with a bad input) and run them. Read its README, manifest, code and tests, and run its tests if it has any.\n4. Score it. Reliable leans on what ran: a failed catalog check, a plugin Hermes would not load, or a call that crashed caps it at 2.\n5. Then rank your whole batch, 1 the best, no ties: scores bunch at the top, so the order is what separates these. Between close ones, the one more Hermes users would keep installed.\n\nWrite the result with a script (json.dump), and again after each plugin:\n{\"batch\": \"{{batch}}\", \"setup\": \"how Hermes was installed, or why it was not\", \"plugins\": [{\"pr\": 0, \"name\": \"catalog name\", \"validate\": \"the catalog check: passed, or failed and which checks, or not run and why\", \"inside\": \"inside Hermes: loaded or not, what it added, which calls worked\", \"tests\": \"passed, failed, none or not run, with counts\", \"useful\": 0, \"reliable\": 0, \"polish\": 0, \"creative\": 0, \"beyond\": 0, \"total\": 0, \"rank\": 0, \"best\": \"one sentence\", \"worst\": \"one sentence\", \"blocked\": null}]}\nOne entry per plugin, in the order given. blocked is null unless you could not read the plugin at all; then it says why in one sentence and the scores are 0.",
   "output": {
    "format": "json",
    "maxBytes": 32000
   },
   "merge": {
    "groupSize": 20,
    "brief": "One table row per plugin of every item in your group: batch, pr, name and each number the item gives. Copy the numbers as the items give them and say which items were blocked."
   },
   "items": [
    {
     "key": "deep-25",
     "vars": {
      "batch": "deep-25",
      "plugins": "153871 barehand; 153844 fine-print; 152976 agentline; 153050 mandate; 150251 gemini-live; 151604 plur1bus"
     }
    },
    {
     "key": "deep-26",
     "vars": {
      "batch": "deep-26",
      "plugins": "151604 plur1bus; 153766 hermes-ussd; 153724 roomsmith; 153225 agent-pool; 151245 freeze; 150563 hermes-roam"
     }
    },
    {
     "key": "deep-27",
     "vars": {
      "batch": "deep-27",
      "plugins": "153647 riah-swipe; 152243 morph; 154067 hermes-design-studio; 152544 crystallize; 154078 harness-story; 153113 standing-orders"
     }
    },
    {
     "key": "deep-28",
     "vars": {
      "batch": "deep-28",
      "plugins": "153524 shadow-army; 151448 muster; 149202 3ds-platform; 149553 hermes-time-machine; 152408 rich-paste; 153978 imprint"
     }
    },
    {
     "key": "deep-29",
     "vars": {
      "batch": "deep-29",
      "plugins": "150346 construct; 152214 passkey-gate; 153861 summon; 150873 skill-court; 150840 kata; 151968 tickover"
     }
    },
    {
     "key": "deep-30",
     "vars": {
      "batch": "deep-30",
      "plugins": "154067 hermes-design-studio; 153090 retouch; 153809 living-spaces; 152256 nvidia-switchyard; 153714 tenure; 152243 morph"
     }
    }
   ]
  },
  {
   "name": "deep-f",
   "mode": "research",
   "brief": "Your batch: {{batch}}. These Hermes plugins reached round 3 of the hackathon judging: {{plugins}}\nEach is \"pull request number, catalog name\"; ref marks a reference plugin already in the catalog that every seat scores, so give it pr 0. Find each one's repository, pinned commit and folder in https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/field.json (its \"refs\" and \"plugins\" lists, matched on pr and name). Score each on the objective's scale after running it inside real Hermes.\n\nHow:\n1. Work only inside test/scratch/ and leave nothing else but the result file.\n2. Follow https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/RUN.md to install Hermes from its source once and get tryit.py, which runs a plugin inside real Hermes against Nous's own scripted test model, so no model, key or account is needed. If Hermes cannot be installed here, judge by reading alone and say why in setup.\n3. For each plugin: fetch its pinned commit, run tryit.py with an empty plan to see what it adds, then plan two to five calls a real user's request would lead to (one with a bad input) and run them. Read its README, manifest, code and tests, and run its tests if it has any.\n4. Score it. Reliable leans on what ran: a failed catalog check, a plugin Hermes would not load, or a call that crashed caps it at 2.\n5. Then rank your whole batch, 1 the best, no ties: scores bunch at the top, so the order is what separates these. Between close ones, the one more Hermes users would keep installed.\n\nWrite the result with a script (json.dump), and again after each plugin:\n{\"batch\": \"{{batch}}\", \"setup\": \"how Hermes was installed, or why it was not\", \"plugins\": [{\"pr\": 0, \"name\": \"catalog name\", \"validate\": \"the catalog check: passed, or failed and which checks, or not run and why\", \"inside\": \"inside Hermes: loaded or not, what it added, which calls worked\", \"tests\": \"passed, failed, none or not run, with counts\", \"useful\": 0, \"reliable\": 0, \"polish\": 0, \"creative\": 0, \"beyond\": 0, \"total\": 0, \"rank\": 0, \"best\": \"one sentence\", \"worst\": \"one sentence\", \"blocked\": null}]}\nOne entry per plugin, in the order given. blocked is null unless you could not read the plugin at all; then it says why in one sentence and the scores are 0.",
   "output": {
    "format": "json",
    "maxBytes": 32000
   },
   "merge": {
    "groupSize": 20,
    "brief": "One table row per plugin of every item in your group: batch, pr, name and each number the item gives. Copy the numbers as the items give them and say which items were blocked."
   },
   "items": [
    {
     "key": "deep-31",
     "vars": {
      "batch": "deep-31",
      "plugins": "152475 hallway-test; 150293 procgen-studio; 149414 xray; 151135 wake-me-when; 152190 hermes-tuneup; 153144 signet"
     }
    },
    {
     "key": "deep-32",
     "vars": {
      "batch": "deep-32",
      "plugins": "152914 culprit; 154028 hail-hermes; 152243 morph; 153647 riah-swipe; 152063 undo-send; 153596 sentinel-vision"
     }
    },
    {
     "key": "deep-33",
     "vars": {
      "batch": "deep-33",
      "plugins": "152458 housemate; 153113 standing-orders; 150800 hypnos; 149159 understudy; 151704 guild; 153851 foreman"
     }
    },
    {
     "key": "deep-34",
     "vars": {
      "batch": "deep-34",
      "plugins": "153316 hermes-lens; 149244 lineage; 153867 whos-listening; 150563 hermes-roam; 153781 wings; 149553 hermes-time-machine"
     }
    },
    {
     "key": "deep-35",
     "vars": {
      "batch": "deep-35",
      "plugins": "150563 hermes-roam; 149159 understudy; 153714 tenure; 150596 ariadne; 149426 pinpoint; 149244 lineage"
     }
    },
    {
     "key": "deep-36",
     "vars": {
      "batch": "deep-36",
      "plugins": "150696 privacy-xray; 150596 ariadne; 150353 fluent; 151929 promise-keeper; 153766 hermes-ussd; 153225 agent-pool"
     }
    }
   ]
  },
  {
   "name": "deep-g",
   "mode": "research",
   "brief": "Your batch: {{batch}}. These Hermes plugins reached round 3 of the hackathon judging: {{plugins}}\nEach is \"pull request number, catalog name\"; ref marks a reference plugin already in the catalog that every seat scores, so give it pr 0. Find each one's repository, pinned commit and folder in https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/field.json (its \"refs\" and \"plugins\" lists, matched on pr and name). Score each on the objective's scale after running it inside real Hermes.\n\nHow:\n1. Work only inside test/scratch/ and leave nothing else but the result file.\n2. Follow https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/RUN.md to install Hermes from its source once and get tryit.py, which runs a plugin inside real Hermes against Nous's own scripted test model, so no model, key or account is needed. If Hermes cannot be installed here, judge by reading alone and say why in setup.\n3. For each plugin: fetch its pinned commit, run tryit.py with an empty plan to see what it adds, then plan two to five calls a real user's request would lead to (one with a bad input) and run them. Read its README, manifest, code and tests, and run its tests if it has any.\n4. Score it. Reliable leans on what ran: a failed catalog check, a plugin Hermes would not load, or a call that crashed caps it at 2.\n5. Then rank your whole batch, 1 the best, no ties: scores bunch at the top, so the order is what separates these. Between close ones, the one more Hermes users would keep installed.\n\nWrite the result with a script (json.dump), and again after each plugin:\n{\"batch\": \"{{batch}}\", \"setup\": \"how Hermes was installed, or why it was not\", \"plugins\": [{\"pr\": 0, \"name\": \"catalog name\", \"validate\": \"the catalog check: passed, or failed and which checks, or not run and why\", \"inside\": \"inside Hermes: loaded or not, what it added, which calls worked\", \"tests\": \"passed, failed, none or not run, with counts\", \"useful\": 0, \"reliable\": 0, \"polish\": 0, \"creative\": 0, \"beyond\": 0, \"total\": 0, \"rank\": 0, \"best\": \"one sentence\", \"worst\": \"one sentence\", \"blocked\": null}]}\nOne entry per plugin, in the order given. blocked is null unless you could not read the plugin at all; then it says why in one sentence and the scores are 0.",
   "output": {
    "format": "json",
    "maxBytes": 32000
   },
   "merge": {
    "groupSize": 20,
    "brief": "One table row per plugin of every item in your group: batch, pr, name and each number the item gives. Copy the numbers as the items give them and say which items were blocked."
   },
   "items": [
    {
     "key": "deep-37",
     "vars": {
      "batch": "deep-37",
      "plugins": "153050 mandate; 150497 thoth; 153606 habits; 151245 freeze; 152544 crystallize; 153955 shadow"
     }
    },
    {
     "key": "deep-38",
     "vars": {
      "batch": "deep-38",
      "plugins": "149414 xray; 149272 no-cap; 150453 workgraph; 152421 sheets; 152214 passkey-gate; 153316 hermes-lens"
     }
    },
    {
     "key": "deep-39",
     "vars": {
      "batch": "deep-39",
      "plugins": "153024 home-3d-workshop; 151281 tironian; 151887 cmi; 152190 hermes-tuneup; 152899 project-command-center; 153900 annotary"
     }
    },
    {
     "key": "deep-40",
     "vars": {
      "batch": "deep-40",
      "plugins": "153240 flowcanvas; 153938 syrinx; 152159 genui; 149611 hermes-security; 152504 benchforge; 153853 keryx"
     }
    },
    {
     "key": "deep-41",
     "vars": {
      "batch": "deep-41",
      "plugins": "151968 tickover; 151887 cmi; 153524 shadow-army; 152214 passkey-gate; 152256 nvidia-switchyard; 153809 living-spaces"
     }
    },
    {
     "key": "deep-42",
     "vars": {
      "batch": "deep-42",
      "plugins": "153978 imprint; 151929 promise-keeper; 151604 plur1bus; 149426 pinpoint; 153960 on-air; 153826 googlehome"
     }
    }
   ]
  },
  {
   "name": "deep-h",
   "mode": "research",
   "brief": "Your batch: {{batch}}. These Hermes plugins reached round 3 of the hackathon judging: {{plugins}}\nEach is \"pull request number, catalog name\"; ref marks a reference plugin already in the catalog that every seat scores, so give it pr 0. Find each one's repository, pinned commit and folder in https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/field.json (its \"refs\" and \"plugins\" lists, matched on pr and name). Score each on the objective's scale after running it inside real Hermes.\n\nHow:\n1. Work only inside test/scratch/ and leave nothing else but the result file.\n2. Follow https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/RUN.md to install Hermes from its source once and get tryit.py, which runs a plugin inside real Hermes against Nous's own scripted test model, so no model, key or account is needed. If Hermes cannot be installed here, judge by reading alone and say why in setup.\n3. For each plugin: fetch its pinned commit, run tryit.py with an empty plan to see what it adds, then plan two to five calls a real user's request would lead to (one with a bad input) and run them. Read its README, manifest, code and tests, and run its tests if it has any.\n4. Score it. Reliable leans on what ran: a failed catalog check, a plugin Hermes would not load, or a call that crashed caps it at 2.\n5. Then rank your whole batch, 1 the best, no ties: scores bunch at the top, so the order is what separates these. Between close ones, the one more Hermes users would keep installed.\n\nWrite the result with a script (json.dump), and again after each plugin:\n{\"batch\": \"{{batch}}\", \"setup\": \"how Hermes was installed, or why it was not\", \"plugins\": [{\"pr\": 0, \"name\": \"catalog name\", \"validate\": \"the catalog check: passed, or failed and which checks, or not run and why\", \"inside\": \"inside Hermes: loaded or not, what it added, which calls worked\", \"tests\": \"passed, failed, none or not run, with counts\", \"useful\": 0, \"reliable\": 0, \"polish\": 0, \"creative\": 0, \"beyond\": 0, \"total\": 0, \"rank\": 0, \"best\": \"one sentence\", \"worst\": \"one sentence\", \"blocked\": null}]}\nOne entry per plugin, in the order given. blocked is null unless you could not read the plugin at all; then it says why in one sentence and the scores are 0.",
   "output": {
    "format": "json",
    "maxBytes": 32000
   },
   "merge": {
    "groupSize": 20,
    "brief": "One table row per plugin of every item in your group: batch, pr, name and each number the item gives. Copy the numbers as the items give them and say which items were blocked."
   },
   "items": [
    {
     "key": "deep-43",
     "vars": {
      "batch": "deep-43",
      "plugins": "152421 sheets; 152976 agentline; 151371 smart-dictation; 153090 retouch; 151887 cmi; 153647 riah-swipe"
     }
    },
    {
     "key": "deep-44",
     "vars": {
      "batch": "deep-44",
      "plugins": "152481 argus; 151804 dress-rehearsal; 149313 hermes-ros; 150556 hermes-ui-cards; 151301 confidential-mode; 151135 wake-me-when"
     }
    },
    {
     "key": "deep-45",
     "vars": {
      "batch": "deep-45",
      "plugins": "152755 hermes-drawbridge; 150353 fluent; 152914 culprit; 154078 harness-story; 152475 hallway-test; 153024 home-3d-workshop"
     }
    },
    {
     "key": "deep-46",
     "vars": {
      "batch": "deep-46",
      "plugins": "153955 shadow; 152190 hermes-tuneup; 151964 takeover; 153144 signet; 154028 hail-hermes; 150644 hermes-canvas"
     }
    },
    {
     "key": "deep-47",
     "vars": {
      "batch": "deep-47",
      "plugins": "152899 project-command-center; 153221 capalis; 154048 triage; 149685 hermes-teleoperator; 153938 syrinx; 151929 promise-keeper"
     }
    },
    {
     "key": "deep-48",
     "vars": {
      "batch": "deep-48",
      "plugins": "150110 hermes-colab; 153872 local-scout; 150346 construct; 153221 capalis; 153844 fine-print; 151341 permission-canvas"
     }
    }
   ]
  },
  {
   "name": "deep-i",
   "mode": "research",
   "brief": "Your batch: {{batch}}. These Hermes plugins reached round 3 of the hackathon judging: {{plugins}}\nEach is \"pull request number, catalog name\"; ref marks a reference plugin already in the catalog that every seat scores, so give it pr 0. Find each one's repository, pinned commit and folder in https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/field.json (its \"refs\" and \"plugins\" lists, matched on pr and name). Score each on the objective's scale after running it inside real Hermes.\n\nHow:\n1. Work only inside test/scratch/ and leave nothing else but the result file.\n2. Follow https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/RUN.md to install Hermes from its source once and get tryit.py, which runs a plugin inside real Hermes against Nous's own scripted test model, so no model, key or account is needed. If Hermes cannot be installed here, judge by reading alone and say why in setup.\n3. For each plugin: fetch its pinned commit, run tryit.py with an empty plan to see what it adds, then plan two to five calls a real user's request would lead to (one with a bad input) and run them. Read its README, manifest, code and tests, and run its tests if it has any.\n4. Score it. Reliable leans on what ran: a failed catalog check, a plugin Hermes would not load, or a call that crashed caps it at 2.\n5. Then rank your whole batch, 1 the best, no ties: scores bunch at the top, so the order is what separates these. Between close ones, the one more Hermes users would keep installed.\n\nWrite the result with a script (json.dump), and again after each plugin:\n{\"batch\": \"{{batch}}\", \"setup\": \"how Hermes was installed, or why it was not\", \"plugins\": [{\"pr\": 0, \"name\": \"catalog name\", \"validate\": \"the catalog check: passed, or failed and which checks, or not run and why\", \"inside\": \"inside Hermes: loaded or not, what it added, which calls worked\", \"tests\": \"passed, failed, none or not run, with counts\", \"useful\": 0, \"reliable\": 0, \"polish\": 0, \"creative\": 0, \"beyond\": 0, \"total\": 0, \"rank\": 0, \"best\": \"one sentence\", \"worst\": \"one sentence\", \"blocked\": null}]}\nOne entry per plugin, in the order given. blocked is null unless you could not read the plugin at all; then it says why in one sentence and the scores are 0.",
   "output": {
    "format": "json",
    "maxBytes": 32000
   },
   "merge": {
    "groupSize": 20,
    "brief": "One table row per plugin of every item in your group: batch, pr, name and each number the item gives. Copy the numbers as the items give them and say which items were blocked."
   },
   "items": [
    {
     "key": "deep-49",
     "vars": {
      "batch": "deep-49",
      "plugins": "152596 coach; 153867 whos-listening; 153844 fine-print; 153443 local-hands; 150800 hypnos; 150596 ariadne"
     }
    },
    {
     "key": "deep-50",
     "vars": {
      "batch": "deep-50",
      "plugins": "154078 harness-story; 153443 local-hands; 150497 thoth; 150251 gemini-live; 152596 coach; 149272 no-cap"
     }
    },
    {
     "key": "deep-51",
     "vars": {
      "batch": "deep-51",
      "plugins": "149738 trust-ladder; 149553 hermes-time-machine; 152258 kumi; 151376 joust; 152976 agentline; 153443 local-hands"
     }
    },
    {
     "key": "deep-52",
     "vars": {
      "batch": "deep-52",
      "plugins": "149242 agent-si; 154048 triage; 149272 no-cap; 152481 argus; 153871 barehand; 152458 housemate"
     }
    },
    {
     "key": "deep-53",
     "vars": {
      "batch": "deep-53",
      "plugins": "149978 clearvoice; 151964 takeover; 153020 breadcrumbs; 153294 ci-red-to-green; 153724 roomsmith; 150110 hermes-colab"
     }
    },
    {
     "key": "deep-54",
     "vars": {
      "batch": "deep-54",
      "plugins": "152256 nvidia-switchyard; 153861 summon; 153900 annotary; 154010 own-compute; 149750 neural-mesh; 151448 muster"
     }
    }
   ]
  },
  {
   "name": "deep-j",
   "mode": "research",
   "brief": "Your batch: {{batch}}. These Hermes plugins reached round 3 of the hackathon judging: {{plugins}}\nEach is \"pull request number, catalog name\"; ref marks a reference plugin already in the catalog that every seat scores, so give it pr 0. Find each one's repository, pinned commit and folder in https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/field.json (its \"refs\" and \"plugins\" lists, matched on pr and name). Score each on the objective's scale after running it inside real Hermes.\n\nHow:\n1. Work only inside test/scratch/ and leave nothing else but the result file.\n2. Follow https://gist.githubusercontent.com/gtmcknight/594c47336546c8763e641b46cf9af4ec/raw/RUN.md to install Hermes from its source once and get tryit.py, which runs a plugin inside real Hermes against Nous's own scripted test model, so no model, key or account is needed. If Hermes cannot be installed here, judge by reading alone and say why in setup.\n3. For each plugin: fetch its pinned commit, run tryit.py with an empty plan to see what it adds, then plan two to five calls a real user's request would lead to (one with a bad input) and run them. Read its README, manifest, code and tests, and run its tests if it has any.\n4. Score it. Reliable leans on what ran: a failed catalog check, a plugin Hermes would not load, or a call that crashed caps it at 2.\n5. Then rank your whole batch, 1 the best, no ties: scores bunch at the top, so the order is what separates these. Between close ones, the one more Hermes users would keep installed.\n\nWrite the result with a script (json.dump), and again after each plugin:\n{\"batch\": \"{{batch}}\", \"setup\": \"how Hermes was installed, or why it was not\", \"plugins\": [{\"pr\": 0, \"name\": \"catalog name\", \"validate\": \"the catalog check: passed, or failed and which checks, or not run and why\", \"inside\": \"inside Hermes: loaded or not, what it added, which calls worked\", \"tests\": \"passed, failed, none or not run, with counts\", \"useful\": 0, \"reliable\": 0, \"polish\": 0, \"creative\": 0, \"beyond\": 0, \"total\": 0, \"rank\": 0, \"best\": \"one sentence\", \"worst\": \"one sentence\", \"blocked\": null}]}\nOne entry per plugin, in the order given. blocked is null unless you could not read the plugin at all; then it says why in one sentence and the scores are 0.",
   "output": {
    "format": "json",
    "maxBytes": 32000
   },
   "merge": {
    "groupSize": 20,
    "brief": "One table row per plugin of every item in your group: batch, pr, name and each number the item gives. Copy the numbers as the items give them and say which items were blocked."
   },
   "items": [
    {
     "key": "deep-55",
     "vars": {
      "batch": "deep-55",
      "plugins": "152918 look; 153724 roomsmith; 153302 lethe; 153938 syrinx; 153090 retouch; 149313 hermes-ros"
     }
    },
    {
     "key": "deep-56",
     "vars": {
      "batch": "deep-56",
      "plugins": "152159 genui; 153596 sentinel-vision; 152596 coach; 152450 heats; 151376 joust; 149738 trust-ladder"
     }
    },
    {
     "key": "deep-57",
     "vars": {
      "batch": "deep-57",
      "plugins": "153365 lumina; 151411 salts-secrets; 152408 rich-paste; 153766 hermes-ussd; 150873 skill-court; 150293 procgen-studio"
     }
    },
    {
     "key": "deep-58",
     "vars": {
      "batch": "deep-58",
      "plugins": "149685 hermes-teleoperator; 152258 kumi; 153960 on-air; 153240 flowcanvas; 150453 workgraph; 149611 hermes-security"
     }
    },
    {
     "key": "deep-59",
     "vars": {
      "batch": "deep-59",
      "plugins": "152063 undo-send; 150556 hermes-ui-cards; 151341 permission-canvas; 150293 procgen-studio; 153221 capalis; 149685 hermes-teleoperator"
     }
    },
    {
     "key": "deep-60",
     "vars": {
      "batch": "deep-60",
      "plugins": "150251 gemini-live; 149823 samskara; 151411 salts-secrets; 151968 tickover; 154010 own-compute; 152450 heats"
     }
    }
   ]
  }
 ],
 "read": [
  "deep-a/deep-01",
  "deep-a/deep-02",
  "deep-a/deep-03",
  "deep-b/deep-07",
  "deep-b/deep-08",
  "deep-b/deep-09",
  "deep-c/deep-13",
  "deep-c/deep-14",
  "deep-c/deep-15",
  "deep-d/deep-19",
  "deep-d/deep-20",
  "deep-d/deep-21",
  "deep-e/deep-25",
  "deep-e/deep-26",
  "deep-e/deep-27",
  "deep-f/deep-31",
  "deep-f/deep-32",
  "deep-f/deep-33",
  "deep-g/deep-37",
  "deep-g/deep-38",
  "deep-g/deep-39",
  "deep-h/deep-43",
  "deep-h/deep-44",
  "deep-h/deep-45",
  "deep-i/deep-49",
  "deep-i/deep-50",
  "deep-j/deep-55",
  "deep-j/deep-56",
  "read2-e/read2-021",
  "read1/merge-05"
 ],
 "cancel": [],
 "wake": {
  "batches": [
   "deep-a",
   "deep-b",
   "deep-c",
   "deep-d",
   "deep-e",
   "deep-f",
   "deep-g",
   "deep-h",
   "deep-i",
   "deep-j"
  ],
  "afterMinutes": 40
 },
 "finish": false
}