opencode-agent-skill 10.0.0 → 12.0.0-beta.0

package/scripts/check-release-consistency.mjs

@@ -0,0 +1,228 @@
+#!/usr/bin/env node
+
+import { existsSync, readdirSync, readFileSync } from "node:fs"
+import path from "node:path"
+import { fileURLToPath } from "node:url"
+
+const DEFAULT_ROOT = path.resolve(path.dirname(fileURLToPath(import.meta.url)), "..")
+
+function readJson(root, relative) {
+  const file = path.join(root, relative)
+  if (!existsSync(file)) {
+    return { ok: false, error: `${relative}: file not found`, value: null }
+  }
+  try {
+    return { ok: true, error: null, value: JSON.parse(readFileSync(file, "utf8")) }
+  } catch (e) {
+    return { ok: false, error: `${relative}: invalid JSON (${e.message})`, value: null }
+  }
+}
+
+function readText(root, relative) {
+  const file = path.join(root, relative)
+  if (!existsSync(file)) {
+    return { ok: false, error: `${relative}: file not found`, value: null }
+  }
+  return { ok: true, error: null, value: readFileSync(file, "utf8") }
+}
+
+function countSkillDirs(root) {
+  const fullPath = path.join(root, "global-config", "skills")
+  if (!existsSync(fullPath)) return { ok: false, error: "global-config/skills: directory not found", value: 0 }
+  const entries = readdirSync(fullPath, { withFileTypes: true })
+  const count = entries.filter((entry) => entry.isDirectory() && existsSync(path.join(fullPath, entry.name, "SKILL.md"))).length
+  return { ok: true, error: null, value: count }
+}
+
+function countDir(root, dirPath, filter) {
+  const fullPath = path.join(root, dirPath)
+  if (!existsSync(fullPath)) {
+    return { ok: false, error: `${dirPath}: directory not found`, value: 0 }
+  }
+  const entries = readdirSync(fullPath, { withFileTypes: true })
+  const count = filter ? entries.filter(filter).length : entries.length
+  return { ok: true, error: null, value: count }
+}
+
+export function checkReleaseConsistency(root) {
+  root = root || DEFAULT_ROOT
+  const errors = []
+  const warnings = []
+
+  function rJson(relative) {
+    return readJson(root, relative)
+  }
+  function rText(relative) {
+    return readText(root, relative)
+  }
+  function rCount(dirPath, filter) {
+    return countDir(root, dirPath, filter)
+  }
+
+  // 1. package.json version == package-lock.json version
+  const pkg = rJson("package.json")
+  const lock = rJson("package-lock.json")
+  if (pkg.ok && lock.ok) {
+    const pkgVersion = pkg.value.version
+    const lockVersion = lock.value.version
+    if (pkgVersion !== lockVersion) {
+      errors.push(`package.json version (${pkgVersion}) != package-lock.json version (${lockVersion})`)
+    }
+  } else {
+    if (!pkg.ok) errors.push(pkg.error)
+    if (!lock.ok) errors.push(lock.error)
+  }
+
+  // 2. Count skills, commands, subagents
+  const skillRes = countSkillDirs(root)
+  const commandRes = rCount("global-config/commands", (e) => e.isFile() && e.name.endsWith(".md"))
+  const agentRes = rCount("global-config/agents", (e) => e.isFile() && e.name.endsWith(".md"))
+  const skillCount = skillRes.ok ? skillRes.value : 0
+  const commandCount = commandRes.ok ? commandRes.value : 0
+  const agentCount = agentRes.ok ? agentRes.value : 0
+  if (!skillRes.ok) errors.push(skillRes.error)
+  if (!commandRes.ok) errors.push(commandRes.error)
+  if (!agentRes.ok) errors.push(agentRes.error)
+
+  const expectedVersion = pkg.ok ? pkg.value.version : "unknown"
+  const routing = rJson("evals/routing.json")
+  const routerTriggers = rJson("evals/router-triggers.json")
+  const staticScenarioCount = routing.ok && Array.isArray(routing.value.scenarios) ? routing.value.scenarios.length : 0
+  const routerCaseCount = routerTriggers.ok && Array.isArray(routerTriggers.value.cases) ? routerTriggers.value.cases.length : 0
+  if (!routing.ok) errors.push(routing.error)
+  if (!routerTriggers.ok) errors.push(routerTriggers.error)
+
+  // 3. Check README current version block
+  const readme = rText("README.md")
+  if (readme.ok) {
+    const versionMatch = readme.value.match(/Phiên bản hiện tại:\s*\n```text\n(\S+)/)
+    if (versionMatch && versionMatch[1] !== expectedVersion) {
+      errors.push(`README.md: current version says ${versionMatch[1]}, expected ${expectedVersion}`)
+    } else if (!versionMatch) {
+      errors.push("README.md: could not find current version block")
+    }
+    if (staticScenarioCount && !readme.value.includes("**" + staticScenarioCount + " static skill-routing scenarios**")) {
+      errors.push("README.md: static routing scenario count drift (actual: " + staticScenarioCount + ")")
+    }
+    if (routerCaseCount && !readme.value.includes("**" + routerCaseCount + " V2 router cases**")) {
+      errors.push("README.md: router case count drift (actual: " + routerCaseCount + ")")
+    }
+  } else {
+    errors.push(readme.error)
+  }
+
+  // 4. Check V11 docs for stale status markers
+  const v11Docs = ["docs/V11-PERCEPTION-ADAPTIVE.md", "docs/V11-PERCEPTION-ADAPTIVE-EXECUTION.md"]
+  for (const doc of v11Docs) {
+    const content = rText(doc)
+    if (!content.ok) {
+      errors.push(content.error)
+      continue
+    }
+    if (content.value.includes("Status: development")) {
+      errors.push(`${doc}: still marked as development`)
+    }
+    if (content.value.includes("11.0.0-dev.")) {
+      errors.push(`${doc}: still references dev version 11.0.0-dev.*`)
+    }
+    if (content.value.includes("npm `latest` remains V10")) {
+      errors.push(`${doc}: still says V10 remains npm latest`)
+    }
+  }
+
+  // 5. Verify docs reflect actual counts (skip historical sections)
+  const docsToCheck = ["README.md", "docs/ENGINEERING-DESIGN.md", "docs/OPENCODE-COMPAT.md"]
+  for (const doc of docsToCheck) {
+    const content = rText(doc)
+    if (!content.ok) {
+      errors.push(content.error)
+      continue
+    }
+    const sections = content.value.split(/\n(?=#{1,6}\s)/)
+    for (const section of sections) {
+      const isHistorical = /^\s*#{1,6}\s+.*(V\d+\.|UES\s+\d+\.|historical|Historical)/im.test(section)
+      if (isHistorical) continue
+      if (section.includes("39 skills") || section.includes("39 namespaced skills")) {
+        errors.push(`${doc}: current section still references 39 skills (actual: ${skillCount})`)
+      }
+      if (section.includes("10 namespaced subagents") || section.includes("10 subagents")) {
+        errors.push(`${doc}: current section still references 10 subagents (actual: ${agentCount})`)
+      }
+      if (section.includes("34 static") && section.includes("scenarios")) {
+        errors.push(`${doc}: current section still references 34 static scenarios (actual: ${staticScenarioCount})`)
+      }
+    }
+  }
+
+  // 6. Check CI workflow
+  const ciYaml = rText(".github/workflows/ci.yml")
+  if (ciYaml.ok) {
+    if (!ciYaml.value.includes("evals:v11:validate")) {
+      errors.push(".github/workflows/ci.yml: missing evals:v11:validate job")
+    }
+    if (!/^\s*name:\s*CI Gate\s*$/m.test(ciYaml.value)) errors.push(".github/workflows/ci.yml: missing CI Gate aggregate job name")
+    if (!/needs:\s*\[\s*static\s*,\s*unit\s*,\s*package\s*\]/m.test(ciYaml.value)) errors.push(".github/workflows/ci.yml: CI Gate must depend on static, unit and package")
+    if (!/if:\s*always\(\)/m.test(ciYaml.value)) errors.push(".github/workflows/ci.yml: aggregate gate must use if: always()")
+    if (!ciYaml.value.includes("docs:check")) errors.push(".github/workflows/ci.yml: missing docs:check job")
+    for (const check of ["evals:v12:validate","evals:repo-scale:validate"]) {
+      if (!ciYaml.value.includes(check)) errors.push(".github/workflows/ci.yml: missing " + check + " job")
+    }
+  } else {
+    errors.push(ciYaml.error)
+  }
+
+  // 7. Check Security workflow
+  const securityYaml = rText(".github/workflows/security.yml")
+  if (securityYaml.ok) {
+    if (!/^\s*name:\s*Security Gate\s*$/m.test(securityYaml.value)) errors.push(".github/workflows/security.yml: missing Security Gate aggregate job name")
+    if (!/needs:\s*\[\s*codeql\s*,\s*dependency-review\s*\]/m.test(securityYaml.value)) errors.push(".github/workflows/security.yml: Security Gate must depend on codeql and dependency-review")
+  } else {
+    errors.push(securityYaml.error)
+  }
+
+  // 8. Check publish workflow idempotency
+  const publishYaml = rText(".github/workflows/publish.yml")
+  if (publishYaml.ok) {
+    if (!publishYaml.value.includes("already published")) {
+      errors.push(".github/workflows/publish.yml: missing idempotency check for existing versions")
+    }
+  } else {
+    errors.push(publishYaml.error)
+  }
+
+  // 9. Check npm script docs:check exists
+  if (pkg.ok) {
+    const pkgScripts = pkg.value.scripts || {}
+    if (!pkgScripts["docs:check"]) {
+      warnings.push("package.json: missing docs:check npm script")
+    }
+  }
+
+  return {
+    pass: errors.length === 0,
+    errors,
+    warnings,
+    version: expectedVersion,
+    skillCount,
+    commandCount,
+    subagentCount: agentCount,
+    staticScenarioCount,
+    routerCaseCount,
+  }
+}
+
+if (process.argv[1] === fileURLToPath(import.meta.url)) {
+  const result = checkReleaseConsistency(process.env.UES_BUNDLE_ROOT || DEFAULT_ROOT)
+  if (result.warnings.length) {
+    console.warn("Warnings:")
+    for (const w of result.warnings) console.warn(`  WARN: ${w}`)
+  }
+  if (result.errors.length) {
+    console.error("Release consistency check FAILED:")
+    for (const e of result.errors) console.error(`  - ${e}`)
+    process.exit(1)
+  }
+  console.log(
+    `Release consistency check PASS: package=${result.version}, skills=${result.skillCount}, commands=${result.commandCount}, subagents=${result.subagentCount}`,
+  )
+}

package/scripts/eval-ablation.mjs

@@ -14,7 +14,7 @@ function positional() {
   const values = []
   for (let index = 0; index < args.length; index += 1) {
     if (args[index].startsWith("--")) {
-      if (["--pass-rate-tolerance", "--min-initial-reduction", "--max-token-ratio", "--max-duration-ratio"].includes(args[index])) index += 1
+      if (["--pass-rate-tolerance", "--min-initial-reduction", "--max-token-ratio", "--max-duration-ratio", "--min-cacheable-ratio", "--min-evidence-reuse-ratio", "--max-repeated-stable-ratio"].includes(args[index])) index += 1
       continue
     }
     values.push(args[index])
@@ -38,6 +38,9 @@ const report = compareEvalSummaries(reference, candidate, {
   minInitialInputReduction: Number(option("--min-initial-reduction", "0.10")),
   maxTotalTokenRatio: Number(option("--max-token-ratio", "1.05")),
   maxDurationRatio: Number(option("--max-duration-ratio", "1.10")),
+  minCacheableRatio: option("--min-cacheable-ratio", null) == null ? null : Number(option("--min-cacheable-ratio", null)),
+  minEvidenceReuseRatio: option("--min-evidence-reuse-ratio", null) == null ? null : Number(option("--min-evidence-reuse-ratio", null)),
+  maxRepeatedStableRatio: option("--max-repeated-stable-ratio", null) == null ? null : Number(option("--max-repeated-stable-ratio", null)),
 })
 
 console.log(JSON.stringify(report, null, 2))

package/scripts/validate-repo-scale-suite.mjs

@@ -0,0 +1,27 @@
+#!/usr/bin/env node
+import { mkdtemp, readFile, rm } from "node:fs/promises"
+import os from "node:os"
+import path from "node:path"
+import { fileURLToPath } from "node:url"
+import { generateRepoScaleFixture } from "../lib/repo-scale-fixture.mjs"
+
+const root = path.resolve(path.dirname(fileURLToPath(import.meta.url)), "..")
+const suite = JSON.parse(await readFile(path.join(root, "evals", "repo-scale", "tasks.json"), "utf8"))
+const errors = []
+if (!Array.isArray(suite.tasks) || suite.tasks.length < 4) errors.push("repo-scale suite must define at least 4 tasks")
+for (const task of suite.tasks || []) {
+  if (!task.id || !task.objective || task.objective.length < 40) errors.push((task.id || "<missing>") + ": objective too weak")
+  if (!Array.isArray(task.requiredFiles) || task.requiredFiles.length < 2) errors.push((task.id || "<missing>") + ": requiredFiles must contain at least 2 paths")
+  if (!Array.isArray(task.acceptance) || task.acceptance.length < 2) errors.push((task.id || "<missing>") + ": acceptance must contain at least 2 checks")
+}
+const tmp = await mkdtemp(path.join(os.tmpdir(), "ues-repo-scale-"))
+try {
+  const generated = await generateRepoScaleFixture(tmp)
+  if (generated.generatedModules < Number(suite.minimumGeneratedModules || 300)) errors.push("generated repo too small: " + generated.generatedModules + " modules")
+} finally { await rm(tmp, { recursive: true, force: true }) }
+if (errors.length) {
+  console.error("Repo-scale suite validation failed:")
+  for (const error of errors) console.error("- " + error)
+  process.exit(1)
+}
+console.log("Validated repo-scale suite: " + suite.tasks.length + " tasks, >=" + suite.minimumGeneratedModules + " generated modules.")

package/scripts/validate-v11-suite.mjs

@@ -0,0 +1,58 @@
+import { existsSync } from "node:fs"
+import { readFile } from "node:fs/promises"
+import path from "node:path"
+import { fileURLToPath } from "node:url"
+
+const root = path.resolve(path.dirname(fileURLToPath(import.meta.url)), "..")
+const file = path.join(root, "evals", "v11", "tasks.json")
+const suite = JSON.parse(await readFile(file, "utf8"))
+const errors = []
+
+const REQUIRED_V11_FILES = [
+  "lib/context-engine-v11.mjs",
+  "lib/evidence-store.mjs",
+  "lib/evidence-budget.mjs",
+  "lib/prompt-cache.mjs",
+  "lib/capability-registry.mjs",
+  "lib/browser-adapter.mjs",
+  "lib/browser-runtime.mjs",
+  "lib/png-diff.mjs",
+  "lib/visual-spec.mjs",
+  "lib/dynamic-workflow.mjs",
+  "lib/skill-quality.mjs",
+  "lib/ui-inspector.mjs",
+  "lib/v11-metrics.mjs",
+  "global-config/agents/visual-verifier.md",
+  "global-config/agents/merge-arbiter.md",
+]
+for (const relative of REQUIRED_V11_FILES) {
+  if (!existsSync(path.join(root, relative))) errors.push("missing V11 runtime file: " + relative)
+}
+const ids = new Set()
+const categories = new Set()
+
+if (!Array.isArray(suite.tasks) || suite.tasks.length < 10) errors.push("V11 suite must contain at least 10 tasks")
+
+for (const task of suite.tasks || []) {
+  if (!task.id || ids.has(task.id)) errors.push("missing/duplicate id: " + (task.id || "<missing>"))
+  ids.add(task.id)
+  if (!task.category) errors.push((task.id || "<missing>") + ": missing category")
+  categories.add(task.category)
+  if (!task.objective || task.objective.length < 30) errors.push((task.id || "<missing>") + ": objective is too weak")
+  if (!Array.isArray(task.requiredFiles) || !task.requiredFiles.length) errors.push((task.id || "<missing>") + ": requiredFiles missing")
+  for (const relative of task.requiredFiles || []) {
+    if (!existsSync(path.join(root, relative))) errors.push((task.id || "<missing>") + ": missing required file " + relative)
+  }
+}
+
+for (const category of ["context","routing","visual","browser","workflow","sidecar"]) {
+  if (!categories.has(category)) errors.push("V11 suite missing category: " + category)
+}
+
+if (errors.length) {
+  console.error("V11 suite validation failed:")
+  for (const error of errors) console.error("- " + error)
+  process.exit(1)
+}
+
+console.log("Validated " + suite.tasks.length + " V11 contract tasks across " + categories.size + " categories and " + REQUIRED_V11_FILES.length + " required runtime files.")

package/scripts/validate-v12-foundation.mjs

@@ -0,0 +1,24 @@
+#!/usr/bin/env node
+import { existsSync } from "node:fs"
+import { readFile } from "node:fs/promises"
+import path from "node:path"
+import { fileURLToPath } from "node:url"
+
+const root = path.resolve(path.dirname(fileURLToPath(import.meta.url)), "..")
+const errors = []
+const required = [
+  "lib/model-performance.mjs","lib/context-quality.mjs","lib/work-plan-scope.mjs",
+  "lib/decision-policy.mjs","lib/repo-scale-fixture.mjs","evals/repo-scale/tasks.json",
+  "scripts/validate-repo-scale-suite.mjs",
+]
+for (const relative of required) if (!existsSync(path.join(root, relative))) errors.push("missing V12 foundation file: " + relative)
+const pkg = JSON.parse(await readFile(path.join(root, "package.json"), "utf8"))
+for (const script of ["evals:v12:validate","evals:repo-scale:validate"]) if (!pkg.scripts?.[script]) errors.push("package.json missing script " + script)
+const tasks = JSON.parse(await readFile(path.join(root, "evals", "repo-scale", "tasks.json"), "utf8"))
+if ((tasks.tasks || []).length < 4) errors.push("V12 repo-scale suite needs at least 4 contract tasks")
+if (errors.length) {
+  console.error("V12 foundation validation failed:")
+  for (const error of errors) console.error("- " + error)
+  process.exit(1)
+}
+console.log("Validated V12 weak-model intelligence foundation files and repo-scale contracts.")

package/scripts/validate.mjs

@@ -87,9 +87,12 @@ for (const entry of await readdir(agentsRoot, { withFileTypes: true })) {
   if (!/mode:\s*subagent/.test(source)) errors.push(`${entry.name}: agent must use mode: subagent`)
 }
 
-if (ids.size < 39) errors.push(`expected at least 39 skills, found ${ids.size}`)
+const V11_REQUIRED_SKILLS = ["visual-fidelity","browser-qa","design-source","responsive-verification","component-visual-testing","browser-security","skill-authoring","skill-evaluation","dynamic-workflow"]
+for (const id of V11_REQUIRED_SKILLS) if (!ids.has(id)) errors.push(`missing V11 skill ${id}`)
+
+if (ids.size < 48) errors.push(`expected at least 48 skills for V11, found ${ids.size}`)
 if (commands < 11) errors.push(`expected at least 11 commands, found ${commands}`)
-if (agents < 10) errors.push(`expected at least 10 subagents, found ${agents}`)
+if (agents < 12) errors.push(`expected at least 12 subagents for V11, found ${agents}`)
 
 const routerIndex = path.join(pluginsRoot, "ues-router", "index.js")
 const routerCore = path.join(pluginsRoot, "ues-router", "router.js")
@@ -115,6 +118,15 @@ if (existsSync(routerIndex)) {
   if (!source.includes('name: "task_policy"')) errors.push("v8 router plugin must expose adaptive task policy")
   if (!source.includes('name: "cancel_task"')) errors.push("v8 router plugin must expose executor cancellation")
   if (!source.includes('name: "recover_task"')) errors.push("v8 router plugin must expose task-scoped recovery")
+  if (!source.includes('name: "capability_requirements"')) errors.push("v11 router plugin must expose capability requirements")
+  if (!source.includes('name: "evidence_get"')) errors.push("v11 router plugin must expose bounded evidence retrieval")
+  if (!source.includes('name: "browser_plan"')) errors.push("v11 router plugin must expose browser verification planning")
+  if (!source.includes('name: "browser_inspect"')) errors.push("v11 router plugin must expose bounded browser inspection")
+  if (!source.includes('name: "visual_geometry"')) errors.push("v11 router plugin must expose visual geometry receipts")
+  if (!source.includes('name: "visual_compare"')) errors.push("v11 router plugin must expose deterministic PNG comparison")
+  if (!source.includes('name: "workflow_plan"')) errors.push("v11 router plugin must expose dynamic workflow planning")
+  if (!source.includes('name: "ui_tokens"')) errors.push("v11 router plugin must expose compact design-token extraction")
+  if (!source.includes('name: "ui_layout"')) errors.push("v11 router plugin must expose responsive UI layout verification")
   if (!source.includes("ctx.session.interrupt")) errors.push("v8 task dispatch must interrupt timed-out executors")
   if (!source.includes('"work", "heartbeat"')) errors.push("v8 task dispatch must refresh task leases")
 }
@@ -138,11 +150,11 @@ if (existsSync(plainInstallSmoke)) {
   }
 }
 
-for (const name of ["process-runner.mjs","evidence-receipt.mjs","gate-receipt.mjs","runtime-events.mjs","context-manifest.mjs","orchestrator-policy.mjs","worktree-sandbox.mjs","learning-engine.mjs","hermes-bridge.mjs","control-center.mjs"]) {
+for (const name of ["process-runner.mjs","evidence-receipt.mjs","gate-receipt.mjs","runtime-events.mjs","context-manifest.mjs","orchestrator-policy.mjs","worktree-sandbox.mjs","learning-engine.mjs","hermes-bridge.mjs","control-center.mjs","evidence-store.mjs","evidence-budget.mjs","prompt-cache.mjs","capability-registry.mjs","visual-spec.mjs","png-diff.mjs","browser-adapter.mjs","browser-runtime.mjs","dynamic-workflow.mjs","skill-quality.mjs","ui-inspector.mjs","context-engine-v11.mjs","v11-metrics.mjs"]) {
   if (!existsSync(path.join(root, "lib", name))) errors.push(`missing V8 core module ${name}`)
 }
 
-for (const name of ["codebase-mapper.md","plan-checker.md","executor.md","integration-verifier.md"]) {
+for (const name of ["codebase-mapper.md","plan-checker.md","executor.md","integration-verifier.md","visual-verifier.md","merge-arbiter.md"]) {
   if (!existsSync(path.join(agentsRoot, name))) errors.push(`missing V6 subagent ${name}`)
 }