openmerit 0.1.11 → 0.2.0

package/dist/terminal/public/styles.css

@@ -914,133 +914,8 @@ progress:indeterminate { opacity:.55; }
 .terminal-loading progress { max-width:260px;margin-bottom:16px; }
 .terminal-loading>span { color:var(--muted);font-size:12px; }
 @media(max-width:700px) { .index-progress { grid-template-columns:1fr auto;gap:14px; }.index-progress progress { grid-column:1 / -1;grid-row:2; }.index-progress small { line-height:1.5; } }
-/* Hosted comparison uses the terminal's existing typography and neutral surfaces. */
-.sample-disclosure a { color: inherit; white-space: nowrap; text-decoration: none; }
-.sample-disclosure a:hover { color: var(--text); }
-.sample-method { display: flex; justify-content: flex-end; margin: -10px 0 18px; font-size: 11px; }
-.comparison { margin: 0 0 32px; padding: 28px 30px 20px; border: 1px solid var(--line-strong); border-radius: 16px; background: var(--stack); box-shadow: inset 0 1px 0 var(--panel-glint); }
-.comparison-top { display: flex; align-items: center; gap: 28px; }
-.comparison-bottom { display: grid; grid-template-columns: minmax(0,1fr) 24px minmax(0,1fr) minmax(0,1fr); align-items: center; gap: 26px; padding: 26px 0; border-block: 1px solid var(--line); }
-.comparison-top { justify-content: space-between; margin-bottom: 26px; }
-.comparison h2 { margin: 0 0 8px; font-size: 28px; line-height: 1.2; font-weight: 500; letter-spacing: -.85px; }
-.comparison-top p { margin: 0; color: var(--muted); font-size: 12px; line-height: 1.6; }
-.comparison-switch { display: flex; padding: 4px; gap: 3px; border: 1px solid var(--track); border-radius: 9px; background: var(--bg); flex-shrink: 0; }
-.comparison-switch button { border: 0; border-radius: 5px; background: transparent; color: var(--quiet); padding: 11px 16px; font: inherit; font-size: 12px; cursor: pointer; transition: background-color 160ms ease-out, color 160ms ease-out, transform 160ms ease-out; }
-.comparison-switch button[aria-pressed="true"] { background: var(--accent); color: var(--on-accent); box-shadow: 0 1px 3px #0003; }
-.comparison-switch button:active { transform: scale(.98); }
-.comparison-switch button:focus-visible { outline: 2px solid var(--muted); outline-offset: 3px; }
-.comparison-cost { display: grid; gap: 10px; min-width: 0; color: var(--muted); transition: color 180ms ease-out; }
-.comparison-cost.selected { color: var(--strong); }
-.comparison-cost > span { font-size: 12px; color: var(--muted); }
-.comparison-cost strong { font-size: clamp(30px,3.15vw,44px); line-height: 1.15; letter-spacing: -1.5px; font-weight: 450; font-variant-numeric: tabular-nums; white-space: nowrap; }
-.comparison-arrow { color: var(--line-active); font-size: 24px; padding-top: 26px; text-align: center; }
-.comparison-saving { min-width: 0; padding-left: 26px; border-left: 1px solid var(--line-strong); display: grid; gap: 7px; }
-.comparison-saving strong { color: var(--amber); font-size: 28px; line-height: 1.2; letter-spacing: -.7px; font-weight: 450; }
-.comparison-saving span { color: var(--muted); font-size: 12px; line-height: 1.5; font-variant-numeric: tabular-nums; }
-.comparison-saving > button { justify-self: start; margin-top: 3px; padding: 0; font-size: 12px; color: var(--text); }
-.comparison-note { margin: 12px 0 0; color: var(--quiet); font-size: 11px; line-height: 1.7; }
-.pricing-method { font-size: 12px; line-height: 1.7; color: var(--muted); padding-bottom: 16px; }
-.price-assignment { padding: 22px 0; border-top: 1px solid var(--line); font-size: 12px; }
-.price-provider { display: flex; justify-content: space-between; margin-bottom: 16px; }
-.price-provider > span:last-child { color: var(--quiet); font-variant-numeric: tabular-nums; }
-.price-models { display: grid; grid-template-columns: minmax(0,1fr) 18px minmax(0,1fr); gap: 12px; }
-.price-models > div { display: flex; flex-direction: column; gap: 7px; }
-.price-models strong { font-size: 13px; font-weight: 450; }
-.price-models span, .price-result span { color: var(--quiet); font-size: 11px; }
-.price-assignment a { color: var(--muted); font-size: 11px; text-decoration-color: var(--scrollbar); text-underline-offset: 3px; }
-.price-assignment a:hover { color: var(--strong); }
-.price-result { margin-top: 18px; color: var(--text); font-variant-numeric: tabular-nums; }
-@media (max-width: 1000px) {
-  .comparison { padding-inline: 24px; }
-  .comparison-bottom { grid-template-columns: minmax(0,1fr) 20px minmax(0,1fr); gap: 20px; }
-  .comparison-saving { grid-column: 1 / -1; grid-template-columns: 1fr auto; border-left: 0; border-top: 1px solid var(--line); padding: 20px 0 0; margin-top: 4px; }
-  .comparison-saving > span { grid-row: 2; }
-  .comparison-saving > button { grid-column: 2; grid-row: 1 / 3; align-self: center; }
-}
 @media (max-width: 650px) {
-  .comparison { margin-bottom: 24px; padding: 22px 18px 18px; border-radius: 12px; }
-  .comparison h2 { font-size: 24px; letter-spacing: -.65px; }
-  .comparison-top { align-items: flex-start; flex-direction: column; gap: 20px; margin-bottom: 22px; }
-  .comparison-top p { line-height: 1.6; }
-  .comparison-switch { width: 100%; }
-  .comparison-switch button { flex: 1; padding: 10px 8px; }
-  .comparison-bottom { gap: 12px; grid-template-columns: minmax(0,1fr) 16px minmax(0,1fr); padding: 22px 0; }
-  .comparison-cost { gap: 8px; }
-  .comparison-cost strong { font-size: clamp(19px,5.5vw,32px); letter-spacing: -.6px; }
-  .comparison-cost > span { font-size: 11px; }
-  .comparison-arrow { font-size: 18px; padding-top: 22px; }
-  .comparison-saving { grid-template-columns: minmax(0,1fr); padding-top: 18px; margin-top: 8px; }
-  .comparison-saving strong { font-size: 25px; }
-  .comparison-saving > button { grid-column: 1; grid-row: 3; margin-top: 5px; }
-  .comparison-note { margin-top: 15px; }
   .sample-disclosure { align-items: flex-start; gap: 14px; }
-  .sample-disclosure a { white-space: normal; min-width: 70px; }
 }
-@media (prefers-reduced-motion: reduce) { .comparison-switch button, .comparison-cost { transition: none; } }
-
-.pricing-assumptions { margin-top: 14px; }
-.pricing-assumptions summary { cursor: pointer; color: var(--text); }
-.pricing-assumptions p { margin-top: 12px; }
-body.keyboard .comparison-switch button, body.keyboard .comparison-cost { transition: none; }
-
-.comparison-controls { display: grid; gap: 10px; min-width: 314px; }
-.comparison-preference { display: flex; align-items: center; gap: 12px; }
-.comparison-preference > span { font-size: 11px; color: var(--quiet); white-space: nowrap; }
-.comparison-preference .select-trigger { flex: 1; width: auto; min-width: 0; }
-.comparison-eligibility { margin-top: 16px; display: flex; flex-wrap: wrap; gap: 8px 24px; color: var(--secondary); font-size: 12px; line-height: 1.6; }
-.comparison-eligibility > span:last-child { color: var(--quiet); }
-.preference-unresolved { color: var(--amber); }
-.price-workload { display: flex; align-items: baseline; gap: 12px; justify-content: space-between; margin-bottom: 12px; }
-.price-workload h3 { font-size: 14px; font-weight: 450; margin: 0; }
-.price-workload > span { color: var(--muted); font-size: 11px; }
-.price-workload > .preference-unresolved { color: var(--amber); }
-.price-decision { line-height: 1.6; color: var(--secondary); margin: 16px 0 10px; }
-.benchmark-checks { margin: 12px 0; border-top: 1px solid var(--node-hover); }
-.benchmark-check { display: flex; justify-content: space-between; gap: 16px; align-items: center; border-bottom: 1px solid var(--node-hover); padding: 10px 0; }
-.benchmark-check > div { display: grid; gap: 4px; }
-.benchmark-check > div > span { color: var(--quiet); font-size: 11px; }
-.benchmark-check strong { font-weight: 400; font-size: 12px; color: var(--secondary); }
-.benchmark-values { text-align: right; color: var(--text); font-size: 12px; font-variant-numeric: tabular-nums; }
-.candidate-review { padding: 16px 0; border-bottom: 1px solid var(--node-hover); }
-.candidate-review > p { line-height: 1.6; color: var(--muted); }
-.candidate-review > a { display: block; margin: 10px 0; }
-.candidate-review .benchmark-method { font-size: 11px; color: var(--quiet); }
-@media (max-width: 650px) { .comparison-controls { width: 100%; min-width: 0; } .comparison-eligibility { gap: 6px; } .comparison-note { font-size: 12px; } }
-
-.comparison-switch button { flex: 1; }
-
-.comparison-decisions { margin-top: 18px; border-top: 1px solid var(--node-hover); padding-top: 14px; }
-.comparison-decisions > summary { cursor: pointer; width: fit-content; color: var(--secondary); font-size: 12px; }
-.comparison-decisions > summary > span { margin-left: 8px; color: var(--quiet); font-variant-numeric: tabular-nums; }
-.comparison-decisions .data-table { margin-top: 14px; }
-.comparison-decisions td { vertical-align: top; }
-.comparison-decisions td small { display: block; color: var(--quiet); font-size: 12px; margin-top: 6px; }
-.candidate-review > summary { display: flex; justify-content: space-between; gap: 16px; font-size: 12px; line-height: 1.5; }
-.candidate-review > summary > span:last-child { color: var(--quiet); white-space: nowrap; }
-.price-models > div > span { overflow-wrap: anywhere; }
-
-.comparison-decisions .data-table th, .comparison-decisions .data-table td { text-align: left; font-family: var(--sans); }
-.comparison-decisions .data-table td { font-size: 12px; color: var(--text); }
-.comparison-decisions > summary::marker { color: var(--line-active); }
-.comparison-decisions .table-wrap { max-width: 100%; }
-.comparison-decisions .data-table td:last-child { color: var(--quiet); }
-
-.comparison-unresolved { margin-top: 18px; padding: 16px 0; border-top: 1px solid var(--line-soft); border-bottom: 1px solid var(--line-soft); }
-.comparison-unresolved > div { display: flex; justify-content: space-between; gap: 12px; flex-wrap: wrap; }
-.comparison-unresolved strong { font-size: 13px; font-weight: 450; color: var(--text); }
-.comparison-unresolved ul { display: grid; grid-template-columns: repeat(3, minmax(0, 1fr)); gap: 16px; list-style: none; padding: 0; margin: 16px 0; }
-.comparison-unresolved li { font-size: 12px; }
-.comparison-unresolved small { display: block; margin-top: 6px; font-size: 12px; color: var(--quiet); }
-.comparison-unresolved > p { font-size: 12px; color: var(--muted); line-height: 1.6; margin-bottom: 0; }
-@media (max-width: 650px) { .comparison-unresolved ul { grid-template-columns: 1fr; gap: 14px; } }
-
-/* Preference exceptions use the terminal's existing warm evidence color. */
-.comparison-override{display:flex;align-items:baseline;gap:8px 14px;flex-wrap:wrap;margin:12px 0 0;padding:12px 0;border-top:1px solid var(--line);font-size:12px;line-height:1.6}
-.comparison-override strong,.preference-override,.price-workload .preference-override{color:var(--amber)}
-.comparison-override span{color:var(--muted)}
-.override-evidence{padding:14px 0;border-block:1px solid var(--line);font-size:12px;line-height:1.7}
-.override-evidence strong{color:var(--amber);font-weight:500}
-.override-evidence ul{margin:8px 0;padding-left:18px}
-.benchmark-check[data-check="regression"] .benchmark-values{color:var(--amber)}
 
 ::selection { background: var(--selected); color: var(--text); }

package/dist/terminal/scout-update.json

@@ -1 +1 @@
-{"format":1,"contract":"scout-recommend-v1","version":"0.1.11","skill":"---\nname: openmerit-scout\ndescription: Consults OpenMerit Scout before choosing, adding, downloading, replacing or configuring any application inference model, including implicit choices while building features, pretrained browser/local models, SDK defaults, embeddings, OCR, speech, classification, detection, segmentation, LLMs and agents. Not for unrelated edits, ordinary inference calls or this coding agent's own model.\n---\n\n# OpenMerit · Scout\n\nBefore introducing, recommending, replacing or configuring an application\ninference model, call the `scout_models` tool on the `openmerit` MCP server.\nThis applies even when the user never mentions models or Scout. Downloading local\nweights, using a pretrained browser model or accepting an SDK default is a model\ndecision: consult Scout before model-specific code, installs or downloads.\nPreserve the user's explicit model choice; assess it rather than silently replacing\nit. Leave unchanged, approved application selections in place.\n\n## Project policy\n\nRead `.openmerit/scout.json` before searching. If it is absent, ask once whether this\nproject uses **existing-only** (only endpoints it can already reach) or\n**existing-first** (prefer them, ask before searching the whole catalogue), and\nwhich public catalogue endpoint IDs it can access. Save the answer:\n\n```sh\nnpx -y openmerit@latest project --policy existing-only --endpoint-id <id> ...\n```\n\nNever infer access from a model name, SDK or environment-variable name. Never\nrecord credentials, private URLs, prompts or customer data. An empty inventory\nis not permission to search all models.\n\n## Searching\n\nCall `scout_models` with a non-confidential task description and\n`endpointIds` set to the saved inventory, including `[]` when empty.\nExisting-only never broadens. For existing-first, if no existing candidate fits,\nexplain the gap and ask before a separate search without `endpointIds`. Send\nonly task requirements, never source files, secrets or real customer records.\n\nCompare model AND endpoint, evidence, reference cost/time, unknowns and\nwarnings. For multiple tasks read `tasks[].slots[0].recommendations`; the\ntop-level list is empty. Prefer the cheapest usable option the quality evidence\nsupports, without claiming benchmarks prove application accuracy. Use the\nreturned provider model ID and the project's actual SDK and protocol.\n\n## Boundaries\n\nAsk before adding providers or credentials, spending, deploying or external\nwrites. Report recommendation, endpoint connectivity and application checks as\nseparate results, each only after it succeeds. Do not switch this coding agent's\nown model.\n\nIf Scout fails or has no suitable candidate/evidence for the required deployment,\nsay so and pause the model decision; do not substitute a remembered recommendation\nor SDK default. Continue only model-independent work. Local/browser models are not\nexempt when the catalogue lacks coverage. If it reports that the device key is missing,\nexpired or revoked, run `npx -y openmerit@latest login` and then\n`npx -y openmerit@latest install` again. Never ask the user to paste a key.\n","rule":"# Application model decisions · OpenMerit Scout\n\nBefore choosing, recommending, adding, downloading, replacing or configuring\nANY application inference model, load the `openmerit-scout` skill and consult\n`scout_models` on the `openmerit` MCP server before committing to a model.\nThis applies even when the user only asks you to build a feature, never mentions\nmodels or Scout, or names a model themselves (assess it; do not silently replace it).\n\nA pretrained model, local weights, browser inference, an SDK's default model,\nembeddings, OCR, speech, image classification, detection and segmentation all\ncount as model choices, not implementation details. Identify this decision before\nwriting model-specific code, installing a model package or downloading weights.\n\nFollow the skill's project access policy. If it is missing, ask and save it first.\nIf Scout is unavailable, fails or has no suitable evidence/candidate, disclose the\ngap and pause the model decision; do not fall back to a remembered or SDK-default\nmodel. You may continue work that does not commit to a model.\n\nDo not consult Scout for unrelated edits, normal inference calls using an unchanged\napproved model, or this coding agent's own model. Do not reselect approved models\nunless the task introduces or changes a model decision.\n\nWhen the user says \"update openmerit\", run\n`npx -y openmerit@latest update --scope user` (use `--scope project` if this\nrule is in the project's .claude/rules directory). Report the result, including\nany conflict or manual-upgrade requirement. Do not delete edited files, bypass\npermissions or rerun login automatically. A new session loads updated instructions.\n"}
+{"format":1,"contract":"scout-recommend-v1","version":"0.2.0","skill":"---\nname: openmerit-scout\ndescription: Consults OpenMerit Scout before choosing, adding, downloading, replacing or configuring any application inference model, including implicit choices while building features, pretrained browser/local models, SDK defaults, embeddings, OCR, speech, classification, detection, segmentation, LLMs and agents. Not for unrelated edits, ordinary inference calls or this coding agent's own model.\n---\n\n# OpenMerit · Scout\n\nBefore introducing, recommending, replacing or configuring an application\ninference model, call the `scout_models` tool on the `openmerit` MCP server.\nThis applies even when the user never mentions models or Scout. Downloading local\nweights, using a pretrained browser model or accepting an SDK default is a model\ndecision: consult Scout before model-specific code, installs or downloads.\nPreserve the user's explicit model choice; assess it rather than silently replacing\nit. Leave unchanged, approved application selections in place.\n\n## Project policy\n\nRead `.openmerit/scout.json` before searching. If it is absent, ask once whether this\nproject uses **existing-only** (only endpoints it can already reach) or\n**existing-first** (prefer them, ask before searching the whole catalogue), and\nwhich public catalogue endpoint IDs it can access. Save the answer:\n\n```sh\nnpx -y openmerit@latest project --policy existing-only --endpoint-id <id> ...\n```\n\nNever infer access from a model name, SDK or environment-variable name. Never\nrecord credentials, private URLs, prompts or customer data. An empty inventory\nis not permission to search all models.\n\n## Searching\n\nCall `scout_models` with a non-confidential task description as `prompt` and\n`endpointIds` set to the saved inventory, including `[]` when empty. Send\nonly task requirements, never source files, secrets or real customer records.\nIf the MCP tool is unavailable, run\n`npx -y openmerit@latest scout \"<task>\" --json`; it applies the saved inventory.\n\nScout is a conversation with the agent behind openmerit.ai/scout. When\n`status` is `needs_answers`, fill in what the user or project already states,\nshow the user Scout's brief and remaining questions, and wait for their answers.\nThen call again with the returned `conversationId` and `brief` set to the\nrewritten components, or `skip: true` if the user wants Scout to assume. Never\nanswer Scout's questions with guesses. Send later refinements to the same\n`conversationId`. A call with only a `conversationId` reads an interrupted turn.\n\nWhen `status` is `recommended`, Scout has split the work into `tasks`, one\nper model, each with up to five ranked `models`; cover every task. Each\nmodel's `cost` names the `endpointId` and `providerModelId` to call.\nExisting-only never broadens. For existing-first, if no existing candidate fits a\ntask, explain the gap and ask before a new conversation without `endpointIds`.\nCompare quality evidence, reference cost/time and watch-outs. Prefer the cheapest\nusable option the evidence supports, without claiming benchmarks prove\napplication accuracy. Use the project's actual SDK and protocol.\n\n## Boundaries\n\nAsk before adding providers or credentials, spending, deploying or external\nwrites. Report recommendation, endpoint connectivity and application checks as\nseparate results, each only after it succeeds. Do not switch this coding agent's\nown model.\n\nIf Scout fails or has no suitable candidate/evidence for the required deployment,\nsay so and pause the model decision; do not substitute a remembered recommendation\nor SDK default. Continue only model-independent work. Local/browser models are not\nexempt when the catalogue lacks coverage. If it reports that the device key is missing,\nexpired or revoked, run `npx -y openmerit@latest login` and then\n`npx -y openmerit@latest install` again. Never ask the user to paste a key.\n","rule":"# Application model decisions · OpenMerit Scout\n\nBefore choosing, recommending, adding, downloading, replacing or configuring\nANY application inference model, load the `openmerit-scout` skill and consult\n`scout_models` on the `openmerit` MCP server before committing to a model.\nThis applies even when the user only asks you to build a feature, never mentions\nmodels or Scout, or names a model themselves (assess it; do not silently replace it).\n\nA pretrained model, local weights, browser inference, an SDK's default model,\nembeddings, OCR, speech, image classification, detection and segmentation all\ncount as model choices, not implementation details. Identify this decision before\nwriting model-specific code, installing a model package or downloading weights.\n\nFollow the skill's project access policy. If it is missing, ask and save it first.\nScout may answer with clarifying questions: relay them to the user and continue\nthe same Scout conversation with their answers before choosing.\nIf Scout is unavailable, fails or has no suitable evidence/candidate, disclose the\ngap and pause the model decision; do not fall back to a remembered or SDK-default\nmodel. You may continue work that does not commit to a model.\n\nDo not consult Scout for unrelated edits, normal inference calls using an unchanged\napproved model, or this coding agent's own model. Do not reselect approved models\nunless the task introduces or changes a model decision.\n\nWhen the user says \"update openmerit\", run\n`npx -y openmerit@latest update --scope user` (use `--scope project` if this\nrule is in the project's .claude/rules directory). Report the result, including\nany conflict or manual-upgrade requirement. Do not delete edited files, bypass\npermissions or rerun login automatically. A new session loads updated instructions.\n"}

package/dist/terminal/src/cli.mjs

@@ -10,6 +10,7 @@ import { commandTelemetry } from './telemetry.mjs';
 const help = `OpenMerit · Inference Terminal
 
   openmerit dash [path] [options]
+  openmerit scout --help             Ask Scout which models fit your tasks
   openmerit install --help           Connect OpenMerit to your coding agent
   openmerit update --help            Update installed Scout instructions
   openmerit eval --help              Evaluate CLI changes across coding agents
@@ -31,6 +32,7 @@ Coding-harness usage is outside this terminal's scope.
 async function main() {
   const args = process.argv.slice(2);
   if (['install', 'status', 'remove', 'login', 'logout', 'project', 'doctor', 'update'].includes(args[0])) { const { main } = await import('./install.mjs'); process.exitCode = await main(args); return; }
+  if (args[0] === 'scout') { const { main } = await import('./scout.js'); process.exitCode = await main(args.slice(1)); return; }
   if (args[0] === 'eval') { const { main } = await import('../../eval/src/cli.mjs'); await main(args.slice(1)); return; }
   if (!args.length || args.includes('--help') || args.includes('-h')) { console.log(help); return; }
   if (args.shift() !== 'dash') throw new Error('Unknown command. Run openmerit --help.');