{"bin": "64_token_ish", "content_sha256": "f59731cc305b5fb24bb2ab683264f7859047fb9b52932ae7bd0efa5b2f708f6e", "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/hub/systems/system_manager.go", "end": 10837, "example_id": "0000028d15d22379705968eaadc3ff06fafbee99dc94c6ae0531a499d2c84161", "language": "go", "prefix": ".Id) {\n\t\t_ = sm.RemoveSystem(record.Id)\n\t}\n\n\t// Create new system if none provided\n\tif system == nil {\n\t\tsystem = sm.NewSystem(record.Id)\n\t}\n\n\t// Populate system from record\n\tsystem.Status = record.GetString(\"status\")\n\tsystem.Host = record.GetString(\"host\"", "repo": "henrygd/beszel", "span_codepoints": 256, "start": 10581, "suffix": " The system is immediately added to monitoring with the provided connection and version info.\nfunc (sm *SystemManager) AddWebSocketSystem(systemId string, agentVersion semver.Version, wsConn *ws.WsConn) error {\n\tsystemRecord, err := sm.hub.FindRecordById(\"", "target": ")\n\tsystem.Port = record.GetString(\"port\")\n\n\treturn sm.AddSystem(system)\n}\n\n// AddWebSocketSystem creates and adds a system with an established WebSocket connection.\n// This method is called when an agent connects via WebSocket with valid authentication.\n//"}
{"bin": "32_token_ish", "content_sha256": "4225aecbb3bb3e4d52de1a7301857329ec58bfb7663b4b47703e9fd999d6004b", "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/define.sh", "end": 13369, "example_id": "00000a2112b544b721e9fad8364263b4e23dfb2a35ba037e4cc5c3c119133633", "language": "shell", "prefix": " \"$input\" == \"thai\" ]] && id=\"th\"\n short=\"th\"\n lang=\"Thai\"\n culture=\"th-TH\" ;;\n \"tr\" | \"tr-\"* | \"turkish\" | \"türk\" | \"turk\" )\n [[ \"$input\" == \"turkish\" || \"$input\" == \"türk\" || \"$input\" == \"turk\" ]] && id=\"tr\"\n short=\"tr\"\n ", "repo": "dockur/windows", "span_codepoints": 128, "start": 13241, "suffix": "== \"ukrainian\" ]] && id=\"uk\"\n short=\"uk\"\n lang=\"Ukrainian\"\n culture=\"uk-UA\" ;;\n \"hk\" | \"zh-hk\" | \"cn-hk\" )\n short=\"hk\"\n lang=\"Chinese (Traditional)\"\n desc=\"Chinese HK\"\n culture=\"zh-TW\" ;;\n \"tw\" | \"zh-tw\" | \"cn-tw\" )", "target": "lang=\"Turkish\"\n culture=\"tr-TR\" ;;\n \"ua\" | \"ua-\"* | \"uk\" | \"uk-\"* | \"ukrainian\" )\n [[ \"$input\" == \"ua\" || \"$input\" "}
{"bin": "64_token_ish", "content_sha256": "7710f0c3f8a841937588aa777aa88e7c65df3bfbca88158aa2f93fbc65ca96d9", "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/__tests__/auth-commands.test.ts", "end": 4878, "example_id": "00000bc7fd2c22505103e798222a0377d3940e7d45ece775c228973be9c2442e", "language": "typescript", "prefix": "alue(\"valid-token\");\n vi.stubGlobal(\n \"fetch\",\n vi.fn().mockResolvedValue({\n ok: true,\n json: () =>\n Promise.resolve({\n success: true,\n name: \"Test User\",\n email: \"test@example.com\",\n ", "repo": "upstash/context7", "span_codepoints": 256, "start": 4622, "suffix": "(l) => l.includes(\"test@example.com\"))).toBe(true);\n });\n\n test(\"shows session expired hint when fetch fails\", async () => {\n mockGetValidAccessToken.mockResolvedValue(\"valid-token\");\n vi.stubGlobal(\n \"fetch\",\n vi.fn().mockResolvedValue({", "target": " teamspace: null,\n }),\n })\n );\n\n await runCommand(\"whoami\");\n expect(logOutput.some((l) => l.includes(\"Logged in\"))).toBe(true);\n expect(logOutput.some((l) => l.includes(\"Test User\"))).toBe(true);\n expect(logOutput.some("}
{"bin": "16_token_ish", "content_sha256": "433a345a279c2d54be51864ef77c0a7b19d0f8604b9a441ce0a1eded31f113e8", "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:src/hooks/caveman-stats.js", "end": 18962, "example_id": "00000cfe352bfffb49fac0bfae60bea56878a65c1c2773fd15849d59f3cd1878", "language": "javascript", "prefix": "d count against Pro/Max limits) are untouched by caveman —\n // any session-usage % would overstate real limit relief. See\n // docs/HONEST-NUMBERS.md.\n footer += ' Reduction is of output tokens only; input/cache usage is unchanged.';\n savings = ", "repo": "JuliusBrussee/caveman", "span_codepoints": 64, "start": 18898, "suffix": " `Est. tokens saved: ${estSaved.toLocaleString()} (~${Math.round(ratio * 100)}% of output)\\n` +\n usdLine).replace(/\\n$/, '');\n } else if (mode && mode !== 'off') {\n savings = `No savings estimate for '${mode}' mode — only 'ful", "target": "(`Est. without caveman: ${estNormal.toLocaleString()}\\n` +\n "}
{"bin": "8_token_ish", "content_sha256": "f27ac893dc3f6befb569083a96dc3001948855d41eaed82b8cdb1c5ec633c10c", "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/dwarf/dwarf_expr.c", "end": 12826, "example_id": "0000100154add4adb4a7aff2ed15531429d40ad04ee2b13e6bead264049900b0", "language": "c", "prefix": "BReg25: case DW_ExprOp_BReg26: case DW_ExprOp_BReg27:\n case DW_ExprOp_BReg28: case DW_ExprOp_BReg29: case DW_ExprOp_BReg30: case DW_ExprOp_BReg31:\n {reg_code_dw = (opcode - DW_ExprOp_BReg0);}goto based_reg_read;\n case DW_ExprOp_BRegX:\n ", "repo": "EpicGames/raddebugger", "span_codepoints": 32, "start": 12794, "suffix": "u64[0];}goto based_reg_read;\n based_reg_read:;\n {\n ARCH_RegCode reg_code = arch_reg_code_from_dw(arch, reg_code_dw);\n Rng1U16 reg_rng = arch_info->reg_code_rng_table[reg_code];\n U64 read_size = dim_1u16(reg_rng);\n read", "target": "{reg_code_dw = operands[0].u512."}
{"bin": "16_token_ish", "content_sha256": "00bf56c318de8dd5a39de90b845ac6771a0348a7efebe39dd8c2e5736ac45c8d", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converters/_rss_converter.py", "end": 4540, "example_id": "000014107c7810d777488a669d341beca74f3693a6a201c49c2d7e8b82f30245", "language": "python", "prefix": " def _parse_rss_type(self, doc: Document) -> DocumentConverterResult:\n \"\"\"Parse the type of an RSS feed.\n\n Returns None if the feed type is not recognized or something goes wrong.\n \"\"\"\n root = doc.getElementsByTagName(\"rss\")[0]\n", "repo": "microsoft/markitdown", "span_codepoints": 64, "start": 4476, "suffix": " if not channel_list:\n raise ValueError(\"No channel found in RSS feed\")\n channel = channel_list[0]\n channel_title = self._get_data_by_tag_name(channel, \"title\")\n channel_description = self._get_data_by_tag_name(channel, \"", "target": " channel_list = root.getElementsByTagName(\"channel\")\n "}
{"bin": "64_token_ish", "content_sha256": "d5426d932b8f49c499da40a69b8b75b3f66055136cc701832bb40b9d33221fd6", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py", "end": 10979, "example_id": "0000141497b55f45b161b296a6d0b647fd182056b5fd4682c19b2ad111d07fc1", "language": "python", "prefix": " markdown_content.append(item[\"text\"])\n else: # image\n ocr_text = item[\"ocr_text\"]\n img_marker = (\n ", "repo": "microsoft/markitdown", "span_codepoints": 256, "start": 10723, "suffix": "regular text\n text_content = page.extract_text() or \"\"\n if text_content.strip():\n markdown_content.append(text_content.strip())\n else:\n ", "target": " f\"\\n\\n*[Image OCR]\\n{ocr_text}\\n[End OCR]*\\n\"\n )\n markdown_content.append(img_marker)\n else:\n # No images detected - just extract "}
{"bin": "64_token_ish", "content_sha256": "39d5269c2895517ab7c1c054aec392c7dfcd27d59a9e6a69107bbd63a304a8c8", "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/hooks/pre_commit_hooks/check_xml.rs", "end": 4323, "example_id": "00001c8d070f19f7b1919aca0b9648b7970a2af416e4efe7b7b9ea6babebda1a", "language": "rust", "prefix": ").await?;\n let (code, output) = check_file(Path::new(\"\"), &file_path).await?;\n assert_eq!(code, 1);\n assert!(!output.is_empty());\n Ok(())\n }\n\n #[tokio::test]\n async fn test_invalid_xml_syntax_error() -> Result<()> {\n ", "repo": "j178/prek", "span_codepoints": 256, "start": 4067, "suffix": "let (code, output) = check_file(Path::new(\"\"), &file_path).await?;\n assert_eq!(code, 1);\n assert!(!output.is_empty());\n Ok(())\n }\n\n #[tokio::test]\n async fn test_invalid_xml_trailing_text() -> Result<()> {\n let dir = te", "target": " let dir = tempdir()?;\n let content = br#\"\n\n text\n\"#;\n let file_path = create_test_file(&dir, \"syntax_error.xml\", content).await?;\n "}
{"bin": "64_token_ish", "content_sha256": "41f333c036d3e7c5d742f81da42534ef63ce6c1c25b2237145029d55248000f3", "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/image.sh", "end": 3676, "example_id": "00001e663d647d69f709de8a46835eda20ddc245556efdf42aeccb85c45f71fb", "language": "shell", "prefix": " [[ \"$edition\" == \"$prefix\"* ]] || continue\n score=\"${#pattern}\"\n elif [ \"$edition\" = \"$pattern\" ]; then\n score=\"${#pattern}\"\n else\n continue\n fi\n\n if (( score > best_score )); then\n result=\"$priority\"\n ", "repo": "dockur/windows", "span_codepoints": 256, "start": 3420, "suffix": "_name\"\n local -n bases_ref=\"$bases_name\"\n local -n groups_ref=\"$groups_name\"\n local -n indexes_ref=\"$indexes_name\"\n\n local count image image_index\n local display product platform\n local edition_id install_type\n local candidate flags i\n\n versions_re", "target": " best_score=\"$score\"\n fi\n\n done\n\n done\n\n echo \"$result\"\n return 0\n}\n\ngetVersions() {\n\n local xml=\"$1\"\n local versions_name=\"$2\"\n local bases_name=\"$3\"\n local groups_name=\"$4\"\n local indexes_name=\"$5\"\n local -n versions_ref=\"$versions"}
{"bin": "8_token_ish", "content_sha256": "8e220fb270b050bf1ece82efad6ae81ac5a9a1bdb9962fd7414e5d47b209737f", "document_id": "nicbarker/clay@e6cc36941ab2af5d81107617039d6f527a1c660b:renderers/GLES3/clay_renderer_gles3.h", "end": 5427, "example_id": "00001f2340009515c4e34da8eb18e3702913829ac33d3a1e2b7242d6fe5d4e47", "language": "c", "prefix": "\" // Border thicknesses\\n\"\n \" float L = vBorderWidths.x;\\n\"\n \" float R = vBorderWidths.y;\\n\"\n \" float T = vBorderWidths.z;\\n\"\n \" float B = vBorderWidths.w;\\n\"\n \" bool CLAY_BORDERS_ARE_INSET = true; // it is true\\n\"\n \" ", "repo": "nicbarker/clay", "span_codepoints": 32, "start": 5395, "suffix": " 0.0 || T > 0.0 || B > 0.0);\\n\"\n \" float outerAlpha = 1.0;\\n\"\n \" // If it is not a border but rect or image, then it only has outer border what is provided\\n\"\n \" // Otherwise it increases the outter border, but the provided borde is the i", "target": " bool isBorder = (L > 0.0 || R >"}
{"bin": "32_token_ish", "content_sha256": "a2aed2930510f336d4c741954ba889652e6d51fa7896e117c1928cc2f08be559", "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/languages/python/uv.rs", "end": 18968, "example_id": "000023fce37735448079bec0773c9fd696f5e69c6f2cc2617cb4e6a80f8ee059", "language": "rust", "prefix": "acquire(uv_dir.join(\".lock\"), \"uv\").await?;\n\n if uv_path.is_file() {\n match validate_uv_binary(&uv_path) {\n Ok(_) => {\n trace!(uv = %uv_path.display(), \"Found compatible managed uv\");\n ", "repo": "j178/prek", "span_codepoints": 128, "start": 18840, "suffix": ", error = %err, \"Skipping incompatible managed uv\");\n }\n }\n }\n\n let source = if let Some(uv_source) = uv_source_from_env(&EnvVars) {\n uv_source\n } else {\n Self::select_source().await?\n ", "target": "return Ok(Self::new(uv_path));\n }\n Err(err) => {\n warn!(uv = %uv_path.display()"}
{"bin": "16_token_ish", "content_sha256": "0c1b6668c25c53f3726ae586a89b69d62c3032532207e5e702e02c928a10f680", "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:compose/chain_branch_test.go", "end": 6805, "example_id": "00002c6c298a128a3a61af4f1399182fd076288463a313c097fe53c9a0be1f0d", "language": "go", "prefix": "\tsw.Close()\n\t\t\t}()\n\n\t\t\treturn sr, nil\n\t\t}))\n\t\tc.AppendBranch(NewStreamChainBranch(streamCon).AddLambda(\"one_key\", CollectableLambda(func(ctx context.Context, in *schema.StreamReader[string]) (output string, err error) {\n\t\t\tdefer in.Close()\n\t\t\tfor {\n\t\t\t\tv, ", "repo": "cloudwego/eino", "span_codepoints": 64, "start": 6741, "suffix": "}\n\n\t\t\t\tif err != nil {\n\t\t\t\t\treturn \"\", err\n\t\t\t\t}\n\n\t\t\t\toutput += v\n\t\t\t}\n\n\t\t\treturn output + output, nil\n\t\t})).\n\t\t\tAddLambda(\"two_key\", CollectableLambda(func(ctx context.Context, in *schema.StreamReader[string]) (output string, err error) {\n\t\t\t\tdefer in.Clo", "target": "err := in.Recv()\n\t\t\t\tif errors.Is(err, io.EOF) {\n\t\t\t\t\tbreak\n\t\t\t\t"}
{"bin": "16_token_ish", "content_sha256": "c7b8119f0c956a69abf4cf48d23de9667d47f54b68c51ba9fb9e3762758a81f8", "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/migrations/0_collections_snapshot_0_19_0_dev_1.go", "end": 12993, "example_id": "000034b4443170dd16c07b3da496459e23288467147b8f290567f2f81165bb33", "language": "go", "prefix": "alse,\n\t\t\t\t\"id\": \"autodate3332085495\",\n\t\t\t\t\"name\": \"updated\",\n\t\t\t\t\"onCreate\": true,\n\t\t\t\t\"onUpdate\": true,\n\t\t\t\t\"presentable\": false,\n\t\t\t\t\"system\": false,\n\t\t\t\t\"type\": \"autodate\"\n\t\t\t}\n\t\t],\n\t\t\"indexes\": [\n\t\t\t\"CREATE UNIQUE INDEX ` + \"`\" + `idx_30Lwgf2` + \"`\" + ", "repo": "henrygd/beszel", "span_codepoints": 64, "start": 12929, "suffix": " + `)\"\n\t\t],\n\t\t\"system\": false\n\t},\n\t{\n\t\t\"id\": \"2hz5ncl8tizk5nx\",\n\t\t\"listRule\": null,\n\t\t\"viewRule\": null,\n\t\t\"createRule\": null,\n\t\t\"updateRule\": null,\n\t\t\"deleteRule\": null,\n\t\t\"name\": \"systems\",\n\t\t\"type\": \"base\",\n\t\t\"fields\": [\n\t\t\t{\n\t\t\t\t\"autogeneratePattern\": \"", "target": "` ON ` + \"`\" + `user_settings` + \"`\" + ` (` + \"`\" + `user` + \"`\""}
{"bin": "32_token_ish", "content_sha256": "58db8045145b385dc288be7faa24820813d36d5d39171370af1ce50ecd968256", "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/spiders/test_cache.py", "end": 3594, "example_id": "000034c5ce475f0e3f88a8300bccb61a3fb1bea86b48758e75ad42d16c20664a", "language": "python", "prefix": " fp = b\"\\xaa\" * 20\n corrupt_path = Path(tmpdir) / f\"{fp.hex()}.json\"\n corrupt_path.write_text(\"not valid json{{{\")\n\n result = await cache.get(fp)\n assert result is None\n\n @pytest.mark.anyio\n async def test_", "repo": "D4Vinci/Scrapling", "span_codepoints": 128, "start": 3466, "suffix": "fp1 = b\"\\x01\" * 20\n fp2 = b\"\\x02\" * 20\n\n await cache.put(fp1, _make_response(url=\"https://a.com\"), \"GET\")\n await cache.put(fp2, _make_response(url=\"https://b.com\"), \"GET\")\n\n assert await cache.get(fp1) is not Non", "target": "clear(self):\n with tempfile.TemporaryDirectory() as tmpdir:\n cache = ResponseCacheManager(tmpdir)\n "}
{"bin": "32_token_ish", "content_sha256": "55cb9fb5c350dda7373c4699fcb729abccb37d8198ea158278eccba44efe3f0a", "document_id": "nicbarker/clay@e6cc36941ab2af5d81107617039d6f527a1c660b:examples/clay-official-website/main.c", "end": 27804, "example_id": "00003563289337af64345d2b7f112cba207ec2a0cd0db37d1b0f8c2fac4a3158", "language": "c", "prefix": " .layout = { .sizing = { CLAY_SIZING_PERCENT(0.5) }, .layoutDirection = CLAY_TOP_TO_BOTTOM, .childGap = 8 } }) {\n CLAY_TEXT(CLAY_STRING(\"Integrated Debug Tools\"), CLAY_TEXT_CONFIG({ .fontSize = 52, .fontId = FONT_ID_TITLE_56, .textColor = COLOR_", "repo": "nicbarker/clay", "span_codepoints": 128, "start": 27676, "suffix": " CLAY_TEXT(CLAY_STRING(\"Clay includes built in \\\"Chrome Inspector\\\"-style debug tooling.\"), CLAY_TEXT_CONFIG({ .fontSize = 28, .fontId = FONT_ID_BODY_36, .textColor = COLOR_LIGHT }));\n CLAY_TEXT(CLAY_STRING(\"View your layout hierarchy and confi", "target": "LIGHT }));\n CLAY(CLAY_ID(\"DebuggerSpacer\"), { .layout = { .sizing = { CLAY_SIZING_GROW(.max = 16) }} }) {}\n "}
{"bin": "32_token_ish", "content_sha256": "96c7d7dfa1d78c78e511c69062a8eaa0ad654af338473162f90e4f932480cbe4", "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:browser_use/llm/groq/chat.py", "end": 2020, "example_id": "0000379728e07eb6826e1d7110fc0f3d4fc171bfe4f483c674d9f5d1d9f4edec", "language": "python", "prefix": "ation\n\tmodel: GroqVerifiedModels | str\n\n\t# Model params\n\ttemperature: float | None = None\n\tservice_tier: Literal['auto', 'on_demand', 'flex'] | None = None\n\ttop_p: float | None = None\n\tseed: int | None = None\n\n\t# Client initialization parameters\n\tapi_key: ", "repo": "browser-use/browser-use", "span_codepoints": 128, "start": 1892, "suffix": "# Increase default retries for automation reliability\n\n\tdef get_client(self) -> AsyncGroq:\n\t\treturn AsyncGroq(api_key=self.api_key, base_url=self.base_url, timeout=self.timeout, max_retries=self.max_retries)\n\n\t@property\n\tdef provider(self) -> str:\n\t\treturn", "target": "str | None = None\n\tbase_url: str | URL | None = None\n\ttimeout: float | Timeout | NotGiven | None = None\n\tmax_retries: int = 10 "}
{"bin": "64_token_ish", "content_sha256": "63486d6505ad24addef3dd5ab280e52e6b8b1825a498961478c31c4f318bdef0", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converters/_zip_converter.py", "end": 3316, "example_id": "0000420d496e16be0e552b9cba72395ed7d84df8230e881864b6833c018c1640", "language": "python", "prefix": "try:\n z_file_stream = io.BytesIO(zipObj.read(name))\n z_file_stream_info = StreamInfo(\n extension=os.path.splitext(name)[1],\n filename=os.path.basename(name),\n ", "repo": "microsoft/markitdown", "span_codepoints": 256, "start": 3060, "suffix": " md_content += f\"## File: {name}\\n\\n\"\n md_content += result.markdown + \"\\n\\n\"\n except UnsupportedFormatException:\n pass\n except FileConversionException:\n pass\n\n ", "target": " )\n result = self._markitdown.convert_stream(\n stream=z_file_stream,\n stream_info=z_file_stream_info,\n )\n if result is not None:\n "}
{"bin": "8_token_ish", "content_sha256": "4225aecbb3bb3e4d52de1a7301857329ec58bfb7663b4b47703e9fd999d6004b", "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/define.sh", "end": 13072, "example_id": "00004215dce64872071487fa994f9917c3b9145d4eef8b56bae8491d08d0e32f", "language": "shell", "prefix": "svenska\" )\n [[ \"$input\" == \"se\" || \"$input\" == \"swedish\" || \"$input\" == \"svenska\" ]] && id=\"sv\"\n short=\"sv\"\n lang=\"Swedish\"\n culture=\"sv-SE\" ;;\n \"th\" | \"th-\"* | \"thai\" )\n [[ \"$input\" == \"thai\" ]] && id=\"th\"\n short=\"th\"\n ", "repo": "dockur/windows", "span_codepoints": 32, "start": 13040, "suffix": "TH\" ;;\n \"tr\" | \"tr-\"* | \"turkish\" | \"türk\" | \"turk\" )\n [[ \"$input\" == \"turkish\" || \"$input\" == \"türk\" || \"$input\" == \"turk\" ]] && id=\"tr\"\n short=\"tr\"\n lang=\"Turkish\"\n culture=\"tr-TR\" ;;\n \"ua\" | \"ua-\"* | \"uk\" | \"uk-\"* | \"ukrainian\"", "target": " lang=\"Thai\"\n culture=\"th-"}
{"bin": "64_token_ish", "content_sha256": "e191ce730fc08df89719c6c568529d86eb786e2395518ed9c12562358c33ddd3", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/commands/artifact-workflow.test.ts", "end": 23576, "example_id": "0000466647f0184b85a2c3891d61fb48bed84a42e9161e8b669d94f37148a417", "language": "typescript", "prefix": " // Overwrite tasks with all completed\n await fs.writeFile(\n path.join(changeDir, 'tasks.md'),\n '## Tasks\\n- [x] Task 1\\n- [x] Task 2'\n );\n\n const result = await runCLI(['instructions', 'apply', '--change', 'done-apply'], {", "repo": "Fission-AI/OpenSpec", "span_codepoints": 256, "start": 23320, "suffix": " () => {\n // Create a spec-driven style change with all artifacts\n await createTestChange('apply-schema-test', ['proposal', 'design', 'specs', 'tasks']);\n\n const result = await runCLI(\n ['instructions', 'apply', '--change', 'apply-sch", "target": "\n cwd: tempDir,\n });\n expect(result.exitCode).toBe(0);\n expect(result.stdout).toContain('complete ✓');\n expect(result.stdout).toContain('ready to be archived');\n });\n\n it('uses spec-driven schema apply configuration', async"}
{"bin": "32_token_ish", "content_sha256": "0755713adc0a8eb76a9ce758a89666fc1af72833fcdf5f497d1d293ce1ee55bf", "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:skills/open-source/references/agent.md", "end": 4277, "example_id": "000053b67256125c484e6da2799b156fe342aa443e9d8482ba7ea1352f6c8456", "language": "markdown", "prefix": "ons\nhistory.errors() # Errors (None for clean steps)\nhistory.model_actions() # All actions with parameters\nhistory.model_outputs() # All model outputs\nhistory.last_action() # Last action\n\n# Analysis\nhistory.", "repo": "browser-use/browser-use", "span_codepoints": 128, "start": 4149, "suffix": "successful() # Completed successfully? (None if not done)\nhistory.has_errors() # Any errors?\nhistory.model_thoughts() # Reasoning (AgentBrain objects)\nhistory.action_results() # All ActionResult objects\nhistory.acti", "target": "final_result() # Final extracted content (last step)\nhistory.is_done() # Agent completed?\nhistory.is_"}
{"bin": "32_token_ish", "content_sha256": "d8bd95dc0fae7abc7673552f70df4fc356cb9e81527483f06c07043098e8784f", "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/gpu_test.go", "end": 2139, "example_id": "000055a9821fb80f40ecc1234b6ecc9656e7de214120ec74b3b12e4d75939f51", "language": "go", "prefix": " 62.35,\n\t\t\t\t\tCount: 1,\n\t\t\t\t},\n\t\t\t\t\"2\": {\n\t\t\t\t\tName: \"A10\",\n\t\t\t\t\tTemperature: 44.0,\n\t\t\t\t\tMemoryUsed: 21700.0 / 1.024,\n\t\t\t\t\tMemoryTotal: 23028.0 / 1.024,\n\t\t\t\t\tUsage: 0.0,\n\t\t\t\t\tPower: 59.57,\n\t\t\t\t\tCount: 1,\n\t\t\t\t},\n\t\t\t\t\"3\": {\n\t", "repo": "henrygd/beszel", "span_codepoints": 128, "start": 2011, "suffix": ": 0.0,\n\t\t\t\t\tPower: 61.76,\n\t\t\t\t\tCount: 1,\n\t\t\t\t},\n\t\t\t},\n\t\t\twantValid: true,\n\t\t},\n\t\t{\n\t\t\tname: \"empty input\",\n\t\t\tinput: \"\",\n\t\t\twantData: map[string]system.GPUData{},\n\t\t\twantValid: false,\n\t\t},\n\t\t{\n\t\t\tname: \"malformed data\",\n\t\t\t", "target": "\t\t\t\tName: \"A10\",\n\t\t\t\t\tTemperature: 45.0,\n\t\t\t\t\tMemoryUsed: 18222.0 / 1.024,\n\t\t\t\t\tMemoryTotal: 23028.0 / 1.024,\n\t\t\t\t\tUsage"}
{"bin": "64_token_ish", "content_sha256": "1e8c05cf577f582439d8bbe8b090f854d0f784829ad07dcf2cc4acdb993c5b1b", "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/samba.sh", "end": 4033, "example_id": "00005dcba43fca5c402da84a358d54c9cca9c9c7d2fecf38f838ea1902934657", "language": "shell", "prefix": " guest account = nobody\"\n echo \" map to guest = Bad User\"\n echo \" server min protocol = NT1\"\n echo \" follow symlinks = yes\"\n echo \" wide links = yes\"\n echo \" unix extensions = no\"\n echo \" inherit owner = yes\"\n echo \" ", "repo": "dockur/windows", "span_codepoints": 256, "start": 3777, "suffix": " services\"\n echo \" load printers = no\"\n echo \" printing = bsd\"\n echo \" printcap name = /dev/null\"\n echo \" disable spoolss = yes\"\n } > \"$SAMBA_CONFIG\"; then\n error \"Failed to write Samba config \\\"$SAMBA_CONFIG\\\" !\"\n return 1\n ", "target": " create mask = 0666\"\n echo \" directory mask = 02777\"\n echo \" force user = root\"\n echo \" force group = root\"\n echo \" force create mode = 0666\"\n echo \" force directory mode = 02777\"\n echo \"\"\n echo \" # Disable printing"}
{"bin": "32_token_ish", "content_sha256": "ab5c97cd2d97c4a83a2b8ece386dbdbb1508dd350a483fd12612262ed89cca04", "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/tools-ai-sdk/src/index.test.ts", "end": 5854, "example_id": "00006329e52596b802a19b8dd7fd2d4ff1dc491595df159b81531ee568b9d669", "language": "typescript", "prefix": ",\n }),\n execute: async ({ input }) => ({ result: `processed: ${input}` }),\n });\n\n const agent = new Context7Agent({\n model: bedrock(\"anthropic.claude-3-haiku-20240307-v1:0\"),\n tools: {\n customTool,\n },\n", "repo": "upstash/context7", "span_codepoints": 128, "start": 5726, "suffix": " const agent = new Context7Agent({\n model: bedrock(\"anthropic.claude-3-haiku-20240307-v1:0\"),\n stopWhen: stepCountIs(5),\n });\n\n const result = await agent.generate({\n prompt: \"Find the React library and get documentation ", "target": " });\n\n expect(agent).toBeDefined();\n });\n\n test(\"should generate response using agent workflow\", async () => {\n "}
{"bin": "16_token_ish", "content_sha256": "e37c60a0804564c1029273344d1ca7916ebd7cfc8a8e6b2bcd4175b0266fa455", "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/bilibili/download.test.js", "end": 4027, "example_id": "000065dbb85b0f4c0773132fd21534f5ca0f153a9906c61d43678323776db279", "language": "javascript", "prefix": "ts.toSatisfy(\n (err) => err instanceof CommandExecutionError && /paid-content metadata/.test(err.message),\n );\n expect(mockDownloadMedia).not.toHaveBeenCalled();\n });\n\n it('skips pre-check entirely with --force', async () => {\n const rows =", "repo": "jackwener/OpenCLI", "span_codepoints": 64, "start": 3963, "suffix": " quality: 'best', force: true });\n\n expect(rows[0].status).toBe('success');\n expect(mockApiGet).not.toHaveBeenCalled();\n expect(mockDownloadMedia).toHaveBeenCalledTimes(1);\n });\n\n it('does not block download when the pre-check API itself fails',", "target": " await command.func(page, { bvid: 'BV1xx411c7mD', output: './o',"}
{"bin": "64_token_ish", "content_sha256": "5e1ddd128c8a824eb2905880e165b59d6818baf2a14501b76d361b956e74f3d6", "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:crates/rig-core/src/providers/openai/mod.rs", "end": 6541, "example_id": "00006aa241a711358684b88dddcb54ab5e114f283fed62feed1508976397c50e", "language": "rust", "prefix": " \"b\": { \"type\": \"number\" }\n }\n });\n\n sanitize_schema(&mut schema);\n\n let required = schema[\"required\"].as_array().unwrap();\n assert!(required.contains(&json!(\"a\")));\n assert!(required.contains(&json!(\"b\"", "repo": "0xPlaygrounds/rig", "span_codepoints": 256, "start": 6285, "suffix": " ]\n });\n\n sanitize_schema(&mut schema);\n\n assert!(schema.get(\"oneOf\").is_none());\n assert!(schema[\"anyOf\"].as_array().is_some());\n }\n\n #[test]\n fn test_sanitize_recurses_into_nested_objects() {\n let mut schema = ", "target": ")));\n assert_eq!(required.len(), 2);\n }\n\n #[test]\n fn test_sanitize_converts_one_of_to_any_of() {\n let mut schema = json!({\n \"oneOf\": [\n { \"type\": \"string\" },\n { \"type\": \"number\" }\n "}
{"bin": "64_token_ish", "content_sha256": "d8bd95dc0fae7abc7673552f70df4fc356cb9e81527483f06c07043098e8784f", "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/gpu_test.go", "end": 47641, "example_id": "00006ea91d4086735cb5b3fa19e8b991c5fd9ecfecc2a197a4e4e106dca6f8d2", "language": "go", "prefix": " (B)\": \"10737418240\", \"VRAM Total Used Memory (B)\": \"1073741824\", \"Card Series\": \"Radeon RX 6800\"}}`),\n\t\t\t\t[]byte(`{\"card0\": {\"GUID\": \"34756\", \"Temperature (Sensor edge) (C)\": \"60.0\", \"Current Socket Graphics Package Power (W)\": \"150.0\", \"GPU use (%)\": \"40", "repo": "henrygd/beszel", "span_codepoints": 256, "start": 47385, "suffix": "\", \"GPU use (%)\": \"50\", \"VRAM Total Memory (B)\": \"10737418240\", \"VRAM Total Used Memory (B)\": \"3221225472\", \"Card Series\": \"Radeon RX 6800\"}}`),\n\t\t\t},\n\t\t\tparser: func(gm *GPUManager) func([]byte) bool {\n\t\t\t\treturn gm.parseAmdData\n\t\t\t},\n\t\t\texpectedValues: m", "target": "\", \"VRAM Total Memory (B)\": \"10737418240\", \"VRAM Total Used Memory (B)\": \"2147483648\", \"Card Series\": \"Radeon RX 6800\"}}`),\n\t\t\t\t[]byte(`{\"card0\": {\"GUID\": \"34756\", \"Temperature (Sensor edge) (C)\": \"70.0\", \"Current Socket Graphics Package Power (W)\": \"200.0"}
{"bin": "64_token_ish", "content_sha256": "8546a18bbe8a04fd2d86495a665834aeb952f55c860586210e5f03b43ed95298", "document_id": "OpenCut-app/OpenCut@4d8c49ed0706c4dc145361e01c6b1f1a87cbb863:apps/web/src/components/ui/context-menu.tsx", "end": 2015, "example_id": "00006efb28b7114c084f3ea02254a8ee74d3d85b4053248c9adc3b1d5a13297c", "language": "typescript", "prefix": "h-(--available-height) min-w-32 origin-(--transform-origin) overflow-x-hidden overflow-y-auto rounded-lg bg-popover p-1 text-popover-foreground shadow-md ring-1 ring-foreground/10 duration-100 outline-none data-[side=bottom]:slide-in-from-top-2 data-[side=", "repo": "OpenCut-app/OpenCut", "span_codepoints": 256, "start": 1759, "suffix": "95 data-closed:animate-out data-closed:fade-out-0 data-closed:zoom-out-95\", className )}\n {...props}\n />\n \n \n )\n}\n\nfunction ContextMenuGroup({ ...props }: ContextMenuP", "target": "inline-end]:slide-in-from-left-2 data-[side=inline-start]:slide-in-from-right-2 data-[side=left]:slide-in-from-right-2 data-[side=right]:slide-in-from-left-2 data-[side=top]:slide-in-from-bottom-2 data-open:animate-in data-open:fade-in-0 data-open:zoom-in-"}
{"bin": "16_token_ish", "content_sha256": "632ce87a34d6fee432909ff25310b13c5a844a9fd0d52ddd5a8c6447648a4858", "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/server_test.go", "end": 9995, "example_id": "0000718b39717c14cbe9781ef5d848cb6ecc481fdec5060dfa0c270dead519b1", "language": "go", "prefix": "ntVersion: \"SSH-2.0-beszel\",\n\t\t\texpectError: true,\n\t\t},\n\t\t{\n\t\t\tname: \"empty version string\",\n\t\t\tclientVersion: \"\",\n\t\t\texpectError: true,\n\t\t},\n\t\t{\n\t\t\tname: \"version string with underscore but no version\",\n\t\t\tclientVersion: \"beszel_", "repo": "henrygd/beszel", "span_codepoints": 64, "start": 9931, "suffix": "\tname: \"version with patch and build metadata\",\n\t\t\tclientVersion: \"SSH-2.0-beszel_1.2.3+build.123\",\n\t\t\texpectedVersion: \"1.2.3+build.123\",\n\t\t\texpectError: false,\n\t\t},\n\t}\n\n\tfor _, tt := range tests {\n\t\tt.Run(tt.name, func(t *testing.T) {\n\t\t", "target": "\",\n\t\t\texpectedVersion: \"\",\n\t\t\texpectError: true,\n\t\t},\n\t\t{\n\t\t"}
{"bin": "16_token_ish", "content_sha256": "06f26bb3c51ea4c51fbae2011a47c06440f2c1d43820a6eb65732476abc3450c", "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:sqlite-vec-rescore.c", "end": 1863, "example_id": "000075cda754ba8ace22fb5ae264e513e9a51e669655b1c6246263a338200d8f", "language": "c", "prefix": "loat vector table (rowid-keyed for fast random access)\n zSql = sqlite3_mprintf(\n \"CREATE TABLE \\\"%w\\\".\\\"%w_rescore_vectors%02d\\\"\"\n \"(rowid INTEGER PRIMARY KEY, vector BLOB NOT NULL)\",\n p->schemaName, p->tableName, i);\n if (!zSql)", "repo": "asg017/sqlite-vec", "span_codepoints": 64, "start": 1799, "suffix": ", -1, &stmt, 0);\n sqlite3_free(zSql);\n if ((rc != SQLITE_OK) || (sqlite3_step(stmt) != SQLITE_DONE)) {\n *pzErr = sqlite3_mprintf(\n \"Could not create '_rescore_vectors%02d' shadow table: %s\", i,\n sqlite3_errmsg(db));\n sqlit", "target": "\n return SQLITE_NOMEM;\n rc = sqlite3_prepare_v2(db, zSql"}
{"bin": "32_token_ish", "content_sha256": "2672a14a62dc3390d2f1249555e6befe2308ca0479a1e0e2006980170ba0396c", "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:engineering-book/src/ch09-no-std-and-feature-verification.md", "end": 6029, "example_id": "00007a04c7d0c159ae4d3003d2c50f41cd4c2222b822527746868e94f3b13bd6", "language": "markdown", "prefix": "──────────────────────────────────────────────────────────┘\n```\n\n**What you lose without `std`:**\n- No `HashMap` (requires a hasher — use `BTreeMap` from `alloc`, or `hashbrown`)\n- No `println!()` (requires stdout — use `core::fmt::Write` to a buffer)\n- No", "repo": "microsoft/RustTraining", "span_codepoints": 128, "start": 5901, "suffix": ", no threads (unless provided by a platform HAL)\n- No `Mutex` (use `spin::Mutex` or platform-specific locks)\n\n### Building a `no_std` Crate\n\n```rust\n// src/lib.rs — a no_std library crate\n#![no_std]\n\n// Optionally use heap allocation\nextern crate alloc;\nus", "target": " `std::error::Error` (stabilized in `core` since Rust 1.81, but many\n ecosystems haven't migrated)\n- No file I/O, no networking"}
{"bin": "16_token_ish", "content_sha256": "ad9dcc71789a56c70695c623f4be10a42594d43505ce3a6fff323ee7743ec106", "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/linker/pdb_ext/pdb_builder.c", "end": 5585, "example_id": "00007f305e339d69a5183876dc2b6700c967dc878e5f3846fcd64d00c81f92f9", "language": "c", "prefix": "[i], buckets[i]->key, buckets[i]->value, pack_ud); }\n\n // compute count of present words that are needed\n U64 present_word_count = 0;\n U64 present_msb = bit_array_scan_right_to_left32(ht->present_bits, 0, ht->present_bits.count*32, 1);\n if (present_msb", "repo": "EpicGames/raddebugger", "span_codepoints": 64, "start": 5521, "suffix": " / 32 + 1; }\n\n // compute count of deleted words that are needed\n U64 deleted_word_count = 0;\n U64 deleted_msb = bit_array_scan_right_to_left32(ht->deleted_bits, 0, ht->deleted_bits.count*32, 1);\n if (deleted_msb < ht->deleted_bits.count*32) { deleted_", "target": " < ht->present_bits.count*32) { present_word_count = present_msb"}
{"bin": "32_token_ish", "content_sha256": "f675d6d404617e1e1689184e44da357b529068183e076c753bbc1f3b4aab9a6f", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/_test_vectors.py", "end": 8242, "example_id": "000089892b6f564782b95e6cdce20bd252b687529644af3b1267fe0af6d427fe", "language": "python", "prefix": "Test Author\",\n \"A test EPUB document for MarkItDown testing\",\n \"# Chapter 1: Test Content\",\n \"This is a **test** paragraph with some formatting\",\n \"* A bullet point\",\n \"* Another point\",\n \"#", "repo": "microsoft/markitdown", "span_codepoints": 128, "start": 8114, "suffix": " must_not_include=[],\n ),\n]\n\n\nDATA_URI_TEST_VECTORS = [\n FileTestVector(\n filename=\"test.docx\",\n mimetype=\"application/vnd.openxmlformats-officedocument.wordprocessingml.document\",\n charset=None,\n url=None,\n must_in", "target": " Chapter 2: More Content\",\n \"*different* style\",\n \"> This is a blockquote for testing\",\n ],\n "}
{"bin": "16_token_ish", "content_sha256": "d5426d932b8f49c499da40a69b8b75b3f66055136cc701832bb40b9d33221fd6", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py", "end": 1425, "example_id": "000098f3e3e8c6d24899e066f3b2a9819db9fccabe9eb97ff0ce377f0212e45a", "language": "python", "prefix": "ge.images\n\n # Method 2: If no images found, try underlying PDF objects\n if not images and hasattr(page, \"objects\") and \"image\" in page.objects:\n images = page.objects.get(\"image\", [])\n\n # Method 3: Try filtering all objects ", "repo": "microsoft/markitdown", "span_codepoints": 64, "start": 1361, "suffix": "\"):\n all_objs = page.objects\n for obj_type in all_objs.keys():\n if \"image\" in obj_type.lower() or \"xobject\" in obj_type.lower():\n potential_imgs = all_objs.get(obj_type, [])\n if pot", "target": "for image types\n if not images and hasattr(page, \"objects"}
{"bin": "8_token_ish", "content_sha256": "fba7f4080f31b16dc86517fd452cefa8f10e1dc3391cadffe4df598b627b2c06", "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:examples/rag_dynamic_tools_multi_turn/src/main.rs", "end": 4498, "example_id": "000099966f304afa66a5c502122c2c00c38dc689c15047fccde6053fe4b27d21", "language": "rust", "prefix": "ext prompt and a dynamic tool source\n let calculator_rag = openai_client\n .agent(openai::GPT_4)\n .preamble(\n \"You are a calculator here to help the user perform arithmetic operations.\n Use the tools provided to answer", "repo": "0xPlaygrounds/rig", "span_codepoints": 32, "start": 4466, "suffix": "do any math on your own.\",\n )\n // Add a dynamic tool source with a sample rate of 2 (i.e.: only\n // 2 additional tool will be added to prompts)\n .retrieved_tools(2, index, toolset)\n .build();\n\n // Prompt the agent and ", "target": " the user's question and do not "}
{"bin": "8_token_ish", "content_sha256": "e37c60a0804564c1029273344d1ca7916ebd7cfc8a8e6b2bcd4175b0266fa455", "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/bilibili/download.test.js", "end": 2126, "example_id": "00009b70d9b014a4229eca917786eb4daa30fbbe77b938d7fea415fdb0e4bd26", "language": "javascript", "prefix": "wnloadMedia).toHaveBeenCalledTimes(1);\n });\n\n it('throws PAID_CONTENT for member-only bangumi when account has no vip', async () => {\n mockApiGet\n .mockResolvedValueOnce(viewPayload({ rights: { pay: 1 } })) // view\n .mockResolvedValueOnce({ ", "repo": "jackwener/OpenCLI", "span_codepoints": 32, "start": 2094, "suffix": "}); // nav\n\n await expect(\n command.func(page, { bvid: 'BV1xx411c7mD', output: './o', quality: 'best', force: false }),\n ).rejects.toSatisfy((err) => err instanceof CliError && err.code === 'PAID_CONTENT');\n expect(mockDownloadMedia).not.toHa", "target": "code: 0, data: { vipStatus: 0 } "}
{"bin": "8_token_ish", "content_sha256": "bfb61792348d0e569cedf1c2b3307d237c6c2ecebbf76db01f09e4a0c8922f38", "document_id": "TecharoHQ/anubis@34badc646c39af3d9f1f70757474b141316f23ad:cmd/robots2policy/main.go", "end": 6236, "example_id": "00009b883ad7e630ca41a5fefd782cb9459926225c09f31d782234cc9d45612d", "language": "go", "prefix": "erAgents) > 0 && value != \"\" {\n\t\t\t\tcurrentAllows = append(currentAllows, value)\n\t\t\t}\n\n\t\tcase \"crawl-delay\":\n\t\t\tif len(currentUserAgents) > 0 {\n\t\t\t\tif delay, err := parseIntSafe(value); err == nil {\n\t\t\t\t\tcurrentCrawlDelay = delay\n\t\t\t\t}\n\t\t\t}\n\t\t}\n\t}\n\n\t// Don'", "repo": "TecharoHQ/anubis", "span_codepoints": 32, "start": 6204, "suffix": "\n\tif len(currentUserAgents) > 0 {\n\t\trule := createRuleFromAccumulated(currentUserAgents, currentDisallows, currentAllows, currentCrawlDelay)\n\t\trules = append(rules, rule)\n\t}\n\n\t// Mark blacklisted user agents (those with \"Disallow: /\")\n\tfor i := range rules", "target": "t forget the last group of rules"}
{"bin": "64_token_ish", "content_sha256": "f47fe2e6440578eeb20408bc3131b63fb8e1ae4f6ea26dbdcca33e7901e5ee8c", "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:src/hooks/caveman-config.js", "end": 8745, "example_id": "0000a012307d86631cf97ed5d3ef927a00d4a4b3b6a8b95309c923711644b58f", "language": "javascript", "prefix": "turn null;\n\n const O_NOFOLLOW = typeof fs.constants.O_NOFOLLOW === 'number' ? fs.constants.O_NOFOLLOW : 0;\n const flags = fs.constants.O_RDONLY | O_NOFOLLOW;\n let fd;\n let out;\n try {\n fd = fs.openSync(flagPath, flags);\n const buf ", "repo": "JuliusBrussee/caveman", "span_codepoints": 256, "start": 8489, "suffix": "(!VALID_MODES.includes(raw)) return null;\n return raw;\n } catch (e) {\n return null;\n }\n}\n\n// Symlink-safe append. Same parent-dir + symlink-target rules as safeWriteFlag,\n// but opens with O_APPEND so concurrent writers from different sessions don'", "target": "= Buffer.alloc(MAX_FLAG_BYTES);\n const n = fs.readSync(fd, buf, 0, MAX_FLAG_BYTES, 0);\n out = buf.slice(0, n).toString('utf8');\n } finally {\n if (fd !== undefined) fs.closeSync(fd);\n }\n\n const raw = out.trim().toLowerCase();\n if "}
{"bin": "32_token_ish", "content_sha256": "69cc8ae62cec8ea6a5108b8505b4a4d8816dc8e835610424e9ca7f0504f11d70", "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/xianyu/publish.test.js", "end": 3731, "example_id": "0000ad40c66202fd12b203a339c2cd3a70f879cc3bf192af25fc1226526407b6", "language": "javascript", "prefix": "filled: ['title', 'description', 'price', 'condition'], missing: [] },\n { ok: true },\n { status: 'published', item_id: '123456789012', url: 'https://www.goofish.com/item?id=123456789012' },\n ],\n });\n\n ", "repo": "jackwener/OpenCLI", "span_codepoints": 128, "start": 3603, "suffix": " item_id: '123456789012',\n title: 'MacBook Pro',\n price: '¥5999.99',\n condition: '轻微使用',\n url: 'https://www.goofish.com/item?id=123456789012',\n message: '发布成功',\n }]);\n });\n\n it('uses", "target": "const rows = await publishCommand.func(page, validArgs);\n\n expect(rows).toEqual([{\n status: 'published',\n "}
{"bin": "16_token_ish", "content_sha256": "e6a3afe46f95ebf1b7e2059c7f0f07a9f8699cae7d7f775def63b542b03ec689", "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/answer.sh", "end": 20814, "example_id": "0000af6b4b34f21a1d5dbd00fc6d7eff9ec6f1432c0ba962f1579ec72b28d089", "language": "shell", "prefix": " local user_xml\n user_xml=$(escapeXMLSed \"$user\") || return 1\n\n sed -i \"s|-name \\\"Docker\\\"|-name \\\"\\$env:USERNAME\\\"|g\" \"$asset\" || return 1\n sed -i 's|where name=\"Docker\"|where name=\"%USERNAME%\"|g' \"$asset\" || return 1\n sed -i \"s|Docker|$user_xml|g\" \"$asset\" || return 1\n sed -i \"s|Docker|$user_xml|g\" \"$asset\" || return 1\n fi\n\n local pass=\"${PASSWORD:-admin}\"\n local pw adm", "target": ">Docker|$user_xml|g\" \"$asset\" || return 1\n "}
{"bin": "8_token_ish", "content_sha256": "7f6bee86702a488d29ef0dcaabf424bbe2aca345a6a642319d43a1fe0276792e", "document_id": "DietrichGebert/ponytail@16f29800fd2681bdf24f3eb4ccffe38be3baec6b:hooks/ponytail-subagent.js", "end": 366, "example_id": "0000b128a4b537563823c872fcdeb69a913133e1d2893e56b9ffcd0fa1c69381", "language": "javascript", "prefix": "Start context is parent-thread only and never reaches subagents, so\n// without this every Task-spawned agent runs ponytail-unaware (issue #252).\n// When ponytail mode is active, inject the same ruleset into each subagent.\n//\n// Scoping (opt-in, issue #506)", "repo": "DietrichGebert/ponytail", "span_codepoints": 32, "start": 334, "suffix": "to a regex and\n// the ruleset is injected only into subagents whose agent_type matches. The\n// regex is unanchored and case-insensitive — \"explore|general\" matches either,\n// \"^general$\" is exact. Unset means inject into every subagent, as before.\n\nconst {", "target": ": set PONYTAIL_SUBAGENT_MATCHER "}
{"bin": "64_token_ish", "content_sha256": "fcf067fceb8e3428fdac592012b5de635307730e203700ca40e6347925a555a9", "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:async-book/src/ch12-common-pitfalls.md", "end": 8707, "example_id": "0000b262d7f3fa9e6ae5dc2587e54db72b2dd37850ac7b2f4cc265a4da153934", "language": "markdown", "prefix": " let b = fetch(\"url_b\").await; // 1 second (waits for a to finish first!)\n}\n\n// ✅ CONCURRENT: Takes 1 second total\nasync fn fast() {\n let (a, b) = tokio::join!(\n fetch(\"url_a\"), // Both start immediately\n fetch(\"url_b\"),\n );\n}\n\n// ✅ ", "repo": "microsoft/RustTraining", "span_codepoints": 256, "start": 8451, "suffix": "```\n\n> **Trap**: `let a = fetch(url).await; let b = fetch(url).await;` is sequential!\n> The second `.await` doesn't start until the first finishes. Use `join!` or\n> `spawn` for concurrency.\n\n## Case Study: Debugging a Hung Production Service\n\nA real-world ", "target": "ALSO CONCURRENT: Using let + join\nasync fn also_fast() {\n let fut_a = fetch(\"url_a\"); // Create future (lazy — not started yet)\n let fut_b = fetch(\"url_b\"); // Create future\n let (a, b) = tokio::join!(fut_a, fut_b); // NOW both run concurrently\n}\n"}
{"bin": "16_token_ish", "content_sha256": "795fe7db5dc234e3b2e008ebe3a1508b1640f35ec8988cffbc9587732a2a28b1", "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:tests/providers/openrouter/cassette/agent_tool_sessions.rs", "end": 4002, "example_id": "0000b7423aef7f0f13943b93fd243d89c699e48b5a0d874ab98949b627b658fb", "language": "rust", "prefix": "rror(\"session tool error\")]\nstruct SessionToolError;\n\nimpl Tool for PingEmpty {\n const NAME: &'static str = \"ping_empty\";\n type Error = SessionToolError;\n type Args = EmptyArgs;\n type Output = String;\n\n fn description(&self) -> String {\n ", "repo": "0xPlaygrounds/rig", "span_codepoints": 64, "start": 3938, "suffix": "\n }\n\n fn parameters(&self) -> serde_json::Value {\n json!({\n \"type\": \"object\",\n \"properties\": {},\n \"required\": []\n })\n }\n\n async fn call(\n &self,\n _context: &mut rig::tool::ToolContext", "target": " \"Return EMPTY-OK. This tool takes no arguments.\".to_string()"}
{"bin": "64_token_ish", "content_sha256": "b0c2e7dbc7a768fb843fb80037bde82e6746cf7c4017e1c801f828cf827a45cc", "document_id": "modelcontextprotocol/java-sdk@fd004989b9484c9b81be6b03463396797b354804:mcp-test/src/main/java/io/modelcontextprotocol/client/AbstractMcpAsyncClientTests.java", "end": 24097, "example_id": "0000be41e39c796fdf1c5f3f6922db37d1fe1731ed7c84bb8ee75c1cfccf716a", "language": "java", "prefix": "lete();\n\t\t\t\t});\n\t}\n\n\t@Test\n\tvoid testInitializeWithElicitationCapability() {\n\t\tClientCapabilities capabilities = ClientCapabilities.builder().elicitation().build();\n\t\tElicitResult elicitResult = ElicitResult.builder(ElicitResult.Action.ACCEPT)\n\t\t\t.content(", "repo": "modelcontextprotocol/java-sdk", "span_codepoints": 256, "start": 23841, "suffix": "::nonNull).verifyComplete();\n\t\t\t\t});\n\t}\n\n\t@Test\n\tvoid testInitializeWithAllCapabilities() {\n\t\tvar capabilities = ClientCapabilities.builder()\n\t\t\t.experimental(Map.of(\"feature\", Map.of(\"featureFlag\", true)))\n\t\t\t.roots(true)\n\t\t\t.sampling()\n\t\t\t.build();\n\n\t\tFu", "target": "Map.of(\"foo\", \"bar\"))\n\t\t\t.build();\n\t\twithClient(createMcpTransport(),\n\t\t\t\tbuilder -> builder.capabilities(capabilities).elicitation(request -> Mono.just(elicitResult)),\n\t\t\t\tclient -> {\n\t\t\t\t\tStepVerifier.create(client.initialize()).expectNextMatches(Objects"}
{"bin": "32_token_ish", "content_sha256": "ad9dcc71789a56c70695c623f4be10a42594d43505ce3a6fff323ee7743ec106", "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/linker/pdb_ext/pdb_builder.c", "end": 57279, "example_id": "0000cbaf92b3f47bc0e7eb0d50ce4d5e32b6c6af53768f067889226e666767b5", "language": "c", "prefix": "sed_bucket_arr[0]) * build.compressed_bucket_count;\n U64 gsi_size = sizeof(build.header) + hash_record_arr_size + bitmap_size + compressed_bucket_arr_size;\n \n ProfBeginV(\"Reserve %M for GSI hash table\", gsi_size);\n msf_stream_reserve(", "repo": "EpicGames/raddebugger", "span_codepoints": 128, "start": 57151, "suffix": "symbols_sn, build.symbol_data.size);\n ProfEnd();\n\n ProfBegin(\"Write GSI header\");\n msf_stream_write_struct(msf, gsi_sn, &build.header);\n ProfEnd();\n\n ProfBegin(\"Write hash records [%M]\", hash_record_arr_size);\n msf_stream_write_parallel(tp, msf, gsi_", "target": "msf, gsi_sn, gsi_size);\n ProfEnd();\n\n ProfBeginV(\"Reserve %M for symbols\", build.symbol_data.size);\n msf_stream_reserve(msf, "}
{"bin": "32_token_ish", "content_sha256": "20d0c254b23a5b09ef7d3c07ac1d45e381cfd1c069fdfe8a85db113539d02f3c", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/commands/store-root-selection.test.ts", "end": 19555, "example_id": "0000cec7bedcc3348c73f92ef3e17d37d4d3839bfdb11f60d592a65b5fae1a7b", "language": "typescript", "prefix": " ...env,\n XDG_DATA_HOME: path.join(tempDir, 'data-empty'),\n };\n\n const result = await runCLI(['status', '--json'], { cwd: appRepo, env: isolatedEnv });\n expect(result.exitCode).toBe(0);\n const json = parseJson(result);\n ", "repo": "Fission-AI/OpenSpec", "span_codepoints": 128, "start": 19427, "suffix": "non-interactive', () => {\n it('fails without a change name instead of opening a picker', async () => {\n createChange(storeRoot, 'store-change');\n\n const result = await runCLI(['archive', '--store', 'team-context', '--json'], {\n cwd: app", "target": "expect(json.changes).toEqual([]);\n expect(json.root.source).toBe('implicit');\n });\n });\n\n describe('archive --json is "}
{"bin": "16_token_ish", "content_sha256": "7e4ac7074d0ac6faa1be629b5e4866a53f4ef03be33239de567338dd8dcffb53", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_pdf_tables.py", "end": 44319, "example_id": "0000d1e7694c9f47766ff7758f90c54d77f3bd3b669ca20f8bb7945cb6039d0e", "language": "python", "prefix": "has at least one column (pipe-separated content)\n for row_idx, row in enumerate(table):\n assert (\n len(row) >= 1\n ), f\"{pdf_file}: Table {table_idx}, row {row_idx} has no columns\"\n", "repo": "microsoft/markitdown", "span_codepoints": 64, "start": 44255, "suffix": " row_content = \" \".join(cell.strip() for cell in row)\n assert (\n len(row_content.strip()) > 0\n ), f\"{pdf_file}: Table {table_idx}, row {row_idx} is empty\"\n\n def test_borderless_", "target": "\n # Verify the row has non-empty content\n "}
{"bin": "32_token_ish", "content_sha256": "a9f203c76c3a7fcbff7d6b23b9f36e1f3fa9fa21a02f1998003a0710ca39e608", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/completions/installers/powershell-installer.test.ts", "end": 20399, "example_id": "0000dc082a8f0c8673a1d5edcf6af7a9c3dcc030814e922617f10951164d4f03", "language": "typescript", "prefix": ");\n const result = await spacedInstaller.install(mockCompletionScript);\n\n expect(result.success).toBe(true);\n expect(result.installedPath).toContain('openspec powershell test');\n\n // Cleanup\n await fs.rm(spacedHomeDir, { recursive:", "repo": "Fission-AI/OpenSpec", "span_codepoints": 128, "start": 20271, "suffix": "/ Windows uses ACLs which Node.js chmod doesn't control\n it.skipIf(process.platform === 'win32')('should return failure on permission error', async () => {\n const targetPath = installer.getInstallationPath();\n const targetDir = path.dirname(ta", "target": " true, force: true });\n });\n\n // Skip on Windows: fs.chmod() on directories doesn't restrict write access on Windows\n /"}
{"bin": "8_token_ish", "content_sha256": "f675d6d404617e1e1689184e44da357b529068183e076c753bbc1f3b4aab9a6f", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/_test_vectors.py", "end": 6079, "example_id": "0000dfd5628ca91e4d63717a64e69ad65c1ec21713c5ffc900d2b83fd44a4cc4", "language": "python", "prefix": "\"test_rss.xml\",\n mimetype=\"text/xml\",\n charset=\"utf-8\",\n url=None,\n must_include=[\n \"# The Official Microsoft Blog\",\n \"## Ignite 2024: Why nearly 70% of the Fortune 500 now use Microsoft 365 Copilot\",\n ", "repo": "microsoft/markitdown", "span_codepoints": 32, "start": 6047, "suffix": " absolutely true that the industry is moving incredibly fast\",\n ],\n must_not_include=[\" {\n trackEvent(\"command\", { name: \"upgrade\" });\n\n const ", "repo": "upstash/context7", "span_codepoints": 256, "start": 4352, "suffix": " return;\n }\n\n if (!info.updateAvailable) {\n log.success(`ctx7 is up to date (${pc.bold(`v${VERSION}`)})`);\n return;\n }\n\n log.blank();\n log.info(\n `Update available: ${pc.bold(`v${info.currentVersion}`)} ${pc.dim(\"->\")} ${pc.bold(`v${info.lat", "target": "info = await checkForUpdates({ force: true });\n const plan = info?.upgradePlan ?? getUpgradePlan();\n\n if (!info) {\n log.warn(\"Couldn't check for updates right now.\");\n log.info(`Try again later or run ${pc.cyan(plan.displayCommand)} manually.`);\n "}
{"bin": "64_token_ish", "content_sha256": "b5605939a6cb527522511e86e34ab8818263cf47ff3b9d0ec6e4dea481e3fd65", "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/engines/_browsers/_base.py", "end": 3634, "example_id": "0000ee13063f41473104bb0659f9b21c7bd534336b0f06a668f105ada4c85ca7", "language": "python", "prefix": "o cover\n \"\"\"Get a new page to use\"\"\"\n # No need to check if a page is available or not in sync code because the code blocked before reaching here till the page closed, ofc.\n ctx = context if context is not None else self.context\n ", "repo": "D4Vinci/Scrapling", "span_codepoints": 256, "start": 3378, "suffix": "_headers)\n\n if disable_resources or blocked_domains:\n page.route(\"**/*\", create_intercept_handler(disable_resources, blocked_domains))\n page_info = self.page_pool.add_page(page)\n page_info.mark_busy()\n return page_inf", "target": " assert ctx is not None, \"Browser context not initialized\"\n page = ctx.new_page()\n page.set_default_navigation_timeout(timeout)\n page.set_default_timeout(timeout)\n if extra_headers:\n page.set_extra_http_headers(extra"}
{"bin": "8_token_ish", "content_sha256": "40d218b913bdf11f10a2906adf24bb1815076e549923d62c67b7a1dcb94e0ab6", "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:c-cpp-book/src/ch05-data-structures.md", "end": 2319, "example_id": "0000f0f14f75a0308e863838f42d9a34b3d35f52b3ae48eaa07bdab1d818fdbb", "language": "markdown", "prefix": "ue);\n let u : (u32, bool) = (43, false);\n println!(\"{}, {}\", t.0, t.1);\n println!(\"{}, {}\", u.0, u.1);\n let (num, flag) = get_tuple(); // Tuple destructuring\n println!(\"{num}, {flag}\");\n}\n```\n\n### Rust references\n- References in Rust are roughly ", "repo": "microsoft/RustTraining", "span_codepoints": 32, "start": 2287, "suffix": " some key differences\n - It is legal to have any number of read-only (immutable) references to a variable at any point of time. A reference cannot outlive the variable scope (this is a key concept called **lifetime**; discussed in detail later)\n - On", "target": "equivalent to pointers in C with"}
{"bin": "16_token_ish", "content_sha256": "35d3bac200ce605ab32a55e6d873c36bd652ca3ec57136de120b0870f450cb79", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/validation.test.ts", "end": 48660, "example_id": "0000fe36cc7630ff8bfd59e0cd9b1ed99807ad1def552f0378cf107da37b57f3", "language": "typescript", "prefix": " const delta = `# Test Spec\n\n## ADDED Requirements\n\n### Requirement: Notes as scenario\nThe system SHALL accept any level-4 child, matching the spec path.\n\n#### Notes\nThe spec path treats every level-4 child of a requirement as a scenario.`;\n\n const ", "repo": "Fission-AI/OpenSpec", "span_codepoints": 64, "start": 48596, "suffix": "\n const report = await new Validator(true).validateChangeDeltaSpecs(changeDir);\n\n // The spec path (parseScenarios) counts every level-4 child with content\n // as a scenario, so the delta counter deliberately does the same.\n expect(repo", "target": "changeDir = await writeChangeDelta('fidelity-h4-parity', delta);"}
{"bin": "32_token_ish", "content_sha256": "08627035eea96b25c22866667d6a9dba8ee9c7094d1da26da90ce4e645a6c6f6", "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/__tests__/github.test.ts", "end": 2403, "example_id": "0001003a66a029649aef2acc0d8701f8fa6f4e5ec3be81580e57104747df27c8", "language": "typescript", "prefix": "\n\n expect(execFileSync).not.toHaveBeenCalled();\n expect(result).toEqual({ status: \"ok\", skills: [] });\n expect(vi.mocked(fetch).mock.calls[0][1]).toMatchObject({\n headers: expect.objectContaining({ Authorization: \"token env-token\" }),\n });", "repo": "upstash/context7", "span_codepoints": 128, "start": 2275, "suffix": " const result = await listSkillsFromGitHub(\"upstash/context7\");\n\n expect(execFileSync).not.toHaveBeenCalled();\n expect(result).toEqual({ status: \"ok\", skills: [] });\n expect(vi.mocked(fetch).mock.calls[0][1]).toMatchObject({\n headers: expec", "target": "\n });\n\n test(\"falls back to GH_TOKEN when GITHUB_TOKEN is unset\", async () => {\n vi.stubEnv(\"GH_TOKEN\", \"gh-env-token\");\n\n "}
{"bin": "32_token_ish", "content_sha256": "351fad53d9e0661c25cd3b4e6d9b3a6f281b9bad45046ce3e7c67d425c4421d3", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_module_misc.py", "end": 20402, "example_id": "0001014694996590991e4e9376e3cc59509f33e341c85df633c8bdffffffec04", "language": "python", "prefix": "PPTX file\n markitdown.convert(os.path.join(TEST_FILES_DIR, \"test.pptx\"))\n\n # Verify the prompt was passed to the OpenAI API for PPTX images too\n assert mock_client.chat.completions.create.called\n call_args = mock_client.chat.completions.create.", "repo": "microsoft/markitdown", "span_codepoints": 128, "start": 20274, "suffix": "test_prompt\n\n\n@pytest.mark.skipif(\n skip_llm,\n reason=\"do not run llm tests without a key\",\n)\ndef test_markitdown_llm() -> None:\n client = openai.OpenAI()\n markitdown = MarkItDown(llm_client=client, llm_model=\"gpt-4o\")\n\n result = markitdown.", "target": "call_args\n messages = call_args[1][\"messages\"]\n assert len(messages) == 1\n assert messages[0][\"content\"][0][\"text\"] == "}
{"bin": "16_token_ish", "content_sha256": "a497dee4dafc4abf3240125d7c0de66f8773905518ca138257a2987dd64837dd", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_cu_converter.py", "end": 17747, "example_id": "000104b36b518663e0912134d36371f44ef3c447e8728199fa96cde5ea10f84e", "language": "python", "prefix": "r\n\n with patch(\"markitdown.converters._cu_converter.to_llm_input\", return_value=\"\"):\n conv.convert(\n io.BytesIO(b\"fake pdf\"),\n StreamInfo(extension=\".pdf\", mimetype=\"application/pdf\"),\n )\n\n ", "repo": "microsoft/markitdown", "span_codepoints": 64, "start": 17683, "suffix": "assert call_args.kwargs[\"analyzer_id\"] == \"prebuilt-documentSearch\"\n\n @pytest.mark.parametrize(\n (\"mimetype\", \"expected_analyzer\"),\n [\n (\"video/mp4\", \"prebuilt-videoSearch\"),\n (\"video/x-m4v\", \"prebuilt-videoSearch\"),\n", "target": "call_args = conv._client.begin_analyze_binary.call_args\n "}
{"bin": "8_token_ish", "content_sha256": "b5605939a6cb527522511e86e34ab8818263cf47ff3b9d0ec6e4dea481e3fd65", "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/engines/_browsers/_base.py", "end": 21967, "example_id": "000113965b6ae5f3778f5de690a09b33c14310118a8067f85aeb9c36ca80906a", "language": "python", "prefix": "ing the detected Cloudflare challenge type, if\n found. Returns None if no challenge matches.\n \"\"\"\n challenge_types = (\n \"non-interactive\",\n \"managed\",\n \"interactive\",\n )\n for ctype", "repo": "D4Vinci/Scrapling", "span_codepoints": 32, "start": 21935, "suffix": " if f\"cType: '{ctype}'\" in page_content:\n return ctype\n\n # Check if turnstile captcha is embedded inside the page (Usually inside a closed Shadow iframe)\n selector = Selector(content=page_content)\n if selector.css('scrip", "target": " in challenge_types:\n "}
{"bin": "64_token_ish", "content_sha256": "4e2675f18f3be6437130d04b91e962aaa3cc5198e5c9372d24e6241b57977be8", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converters/_doc_intel_converter.py", "end": 2662, "example_id": "00011bf120324cbfa079b0275b14017958321f2bf9e0199fa2424a040d0b598f", "language": "python", "prefix": " )\n elif type_ == DocumentIntelligenceFileType.PPTX:\n prefixes.append(\n \"application/vnd.openxmlformats-officedocument.presentationml\"\n )\n elif type_ == DocumentIntelligenceFileType.XLSX:\n ", "repo": "microsoft/markitdown", "span_codepoints": 256, "start": 2406, "suffix": "/xhtml+xml\")\n elif type_ == DocumentIntelligenceFileType.PDF:\n prefixes.append(\"application/pdf\")\n prefixes.append(\"application/x-pdf\")\n elif type_ == DocumentIntelligenceFileType.JPEG:\n prefixes.append(\"image", "target": " prefixes.append(\n \"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet\"\n )\n elif type_ == DocumentIntelligenceFileType.HTML:\n prefixes.append(\"text/html\")\n prefixes.append(\"application"}
{"bin": "8_token_ish", "content_sha256": "39572d3bbe924bf0194220bee109d7d5271e39aa5deb24c96318573d48bcb7ac", "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/parser/test_ancestor_navigation.py", "end": 2155, "example_id": "00011dd1b5ef84cfa78a0097f8e329ac69aaa7ec50e98b96f6e058586c070726", "language": "python", "prefix": "or_returns_none_when_not_found(self, nested_page):\n \"\"\"find_ancestor() should return None if no ancestor matches\"\"\"\n target = nested_page.css(\"#target\")[0]\n result = target.find_ancestor(lambda el: el.has_class(\"nonexistent-class\"))\n ", "repo": "D4Vinci/Scrapling", "span_codepoints": 32, "start": 2123, "suffix": " def test_iterancestors_on_text_node_is_empty(self, nested_page):\n \"\"\"iterancestors() on a text node should yield nothing (not raise)\"\"\"\n text_node = nested_page.css(\"#target::text\")[0]\n ancestors = list(text_node.iterancestors())\n ", "target": " assert result is None\n\n "}
{"bin": "64_token_ish", "content_sha256": "5848aafed458a6248492caf5cdd329b541eed38118fca6da78487163e2a246d3", "document_id": "TecharoHQ/anubis@34badc646c39af3d9f1f70757474b141316f23ad:lib/policy/policy_test.go", "end": 1405, "example_id": "00011e85a1cc0115905936da60a0d70aa2f25d0c4d6819bcd0ac25ab633ede00", "language": "go", "prefix": " *testing.T) {\n\t\t\t\tfin, err := os.Open(filepath.Join(\"..\", \"config\", \"testdata\", \"good\", st.Name()))\n\t\t\t\tif err != nil {\n\t\t\t\t\tt.Fatal(err)\n\t\t\t\t}\n\t\t\t\tdefer fin.Close() //nolint:errcheck\n\n\t\t\t\tctx := thothmock.WithMockThoth(t)\n\t\t\t\tif _, err := ParseConfig(ctx", "repo": "TecharoHQ/anubis", "span_codepoints": 256, "start": 1149, "suffix": "{\n\t\t\t\t\tt.Fatal(err)\n\t\t\t\t}\n\t\t\t\tdefer fin.Close() //nolint:errcheck\n\n\t\t\t\tif _, err := ParseConfig(t.Context(), fin, fin.Name(), anubis.DefaultDifficulty, \"info\", false); err != nil {\n\t\t\t\t\tt.Fatal(err)\n\t\t\t\t}\n\t\t\t})\n\t\t})\n\t}\n}\n\nfunc TestBadConfigs(t *testing.T) ", "target": ", fin, fin.Name(), anubis.DefaultDifficulty, \"info\", false); err != nil {\n\t\t\t\t\tt.Fatal(err)\n\t\t\t\t}\n\t\t\t})\n\n\t\t\tt.Run(\"without-thoth\", func(t *testing.T) {\n\t\t\t\tfin, err := os.Open(filepath.Join(\"..\", \"config\", \"testdata\", \"good\", st.Name()))\n\t\t\t\tif err != nil "}
{"bin": "32_token_ish", "content_sha256": "9c282f5f84cc19c9b451d8b4d08a9ad8e651ca2b81ffc41e8aa98463cb3fd0f4", "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/commands/auth.ts", "end": 637, "example_id": "0001282a42f3b25b647fffda076f3eedd359e57cc84b5cc1fc78ba1cda19b704", "language": "typescript", "prefix": "FAULT_DEVICE_POLL_INTERVAL_SECONDS,\n} from \"../utils/auth.js\";\n\nimport { trackEvent } from \"../utils/tracking.js\";\nimport { CLI_CLIENT_ID } from \"../constants.js\";\nimport { getBaseUrl } from \"../utils/api.js\";\n\nlet baseUrl = \"https://context7.com\";\n\nexport", "repo": "upstash/context7", "span_codepoints": 128, "start": 509, "suffix": "\n program\n .command(\"login\")\n .description(\"Log in to Context7\")\n .option(\"--no-browser\", \"Don't open browser automatically\")\n .action(async (options) => {\n await loginCommand(options);\n });\n\n program\n .command(\"logout\")\n .descr", "target": " function setAuthBaseUrl(url: string): void {\n baseUrl = url;\n}\n\nexport function registerAuthCommands(program: Command): void {"}
{"bin": "32_token_ish", "content_sha256": "1c106518cee9163d5cb2953f0160d6fe4cecbc83a2b7dd6c904e8eb7713c52f9", "document_id": "Netflix/maestro@abdbdadf8f075b8fa488c9efb386b468c709a63c:maestro-common/src/main/java/com/netflix/maestro/models/parameter/BooleanParamDefinition.java", "end": 2633, "example_id": "000141386a968b123eb8bbb48a9543cb8c9462ed8ca92cee5296ebd99e09ece6", "language": "java", "prefix": "}\n\n @Override\n public ParamType getType() {\n return ParamType.BOOLEAN;\n }\n\n @Override\n public BooleanParamDefinition asBooleanParamDef() {\n return this;\n }\n\n @Override\n public Parameter toParameter() {\n return BooleanParameter.builder()\n ", "repo": "Netflix/maestro", "span_codepoints": 128, "start": 2505, "suffix": " .tags(getTags())\n .mode(getMode())\n .meta(getMeta())\n .build();\n }\n\n @Override\n public ParamDefinition copyAndUpdate(\n Object updatedValue,\n String expression,\n ParamMode mode,\n Map meta,\n ", "target": " .name(getName())\n .value(getValue())\n .expression(getExpression())\n .validator(getValidator())\n "}
{"bin": "16_token_ish", "content_sha256": "0ade33ba18b5de7898b0031c737185a5bc944d529b58ba3661e833f930a77ade", "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:adk/filesystem/backend_inmemory_test.go", "end": 5587, "example_id": "000146366d8ee634ef0a0f23589de11c54e752c3b8cb7379791c78862011191d", "language": "go", "prefix": ", err := backend.LsInfo(ctx, &LsInfoRequest{Path: \"/\"})\n\t\tif err != nil {\n\t\t\tt.Fatalf(\"LsInfo failed: %v\", err)\n\t\t}\n\n\t\tfor _, info := range infos {\n\t\t\tif strings.Contains(info.Path, \"/\") {\n\t\t\t\tt.Errorf(\"Path should be filename only, got: %s\", info.Path)\n\t\t", "repo": "cloudwego/eino", "span_codepoints": 64, "start": 5523, "suffix": "(\"Expected directory name 'dir1', got: %s\", info.Path)\n\t\t\t\t}\n\t\t\t} else {\n\t\t\t\tif info.Path != \"file1.txt\" && info.Path != \"file2.txt\" {\n\t\t\t\t\tt.Errorf(\"Expected filename 'file1.txt' or 'file2.txt', got: %s\", info.Path)\n\t\t\t\t}\n\t\t\t}\n\t\t}\n\t})\n\n\tt.Run(\"Subdirector", "target": "\t}\n\t\t\tif info.IsDir {\n\t\t\t\tif info.Path != \"dir1\" {\n\t\t\t\t\tt.Errorf"}
{"bin": "8_token_ish", "content_sha256": "412b98dd4784b2e2ddbd8291fd29bf324cdc15c9d99f415ba201d43125e3d5e4", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown-ocr/tests/test_xlsx_converter.py", "end": 5633, "example_id": "00014bbf9f72cdb209ce5a5e54de64cda5d73498e6b6cb23e85d4b0867182a20", "language": "python", "prefix": "\\n[End OCR]*\\n\\n\"\n \"*[Image OCR]\\nMOCK_OCR_TEXT_12345\\n[End OCR]*\\n\\n\"\n \"## Details\\n\\n\"\n \"| Detailed Metrics |\\n\"\n \"| --- |\\n\"\n \"| System Health |\\n\\n\"\n \"### Images in this sheet:\\n\\n\"\n \"*[Image OCR]\\nMOCK_", "repo": "microsoft/markitdown", "span_codepoints": 32, "start": 5601, "suffix": " \"## Summary\\n\\n\"\n \"| Quarter Summary |\\n\"\n \"| --- |\\n\"\n \"| Overall Performance |\\n\\n\"\n \"### Images in this sheet:\\n\\n\"\n \"*[Image OCR]\\nMOCK_OCR_TEXT_12345\\n[End OCR]*\"\n )\n assert _convert(\"xlsx_multiple_imag", "target": "OCR_TEXT_12345\\n[End OCR]*\\n\\n\"\n"}
{"bin": "64_token_ish", "content_sha256": "ad9dcc71789a56c70695c623f4be10a42594d43505ce3a6fff323ee7743ec106", "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/linker/pdb_ext/pdb_builder.c", "end": 89282, "example_id": "00015101db4aec4a7bd989d0c13ed65f090ff77751cb810305f57307e6994ee6", "language": "c", "prefix": " += 1;\n count_16[digit_16] += 1;\n }\n ProfEnd();\n\n //\n // sort on section offset\n //\n\n ProfBegin(\"Offsets\");\n U32 offset_8lo = 0;\n U32 offset_8hi = 0;\n for (U64 i = 1; i <= ArrayCount(count_8lo); i += 1) {\n U32 current_8lo = count_8lo[i - 1];", "repo": "EpicGames/raddebugger", "span_codepoints": 256, "start": 89026, "suffix": " U32 current_16 = count_16[i - 1];\n count_16[i - 1] = offset_16;\n offset_16 += current_16;\n }\n ProfEnd();\n\n count_8lo[0] = 0;\n count_8hi[0] = 0;\n count_16[0] = 0;\n\n ProfBegin(\"Order 8 Lo\");\n for (U64 i = 0; i < sc_count; i += 1) {\n PDB_Dbi", "target": "\n U32 current_8hi = count_8hi[i - 1];\n count_8lo[i - 1] = offset_8lo;\n count_8hi[i - 1] = offset_8hi;\n offset_8lo += current_8lo;\n offset_8hi += current_8hi;\n }\n\n U32 offset_16 = 0;\n for (U64 i = 1; i <= ArrayCount(count_16); i += 1) {\n "}
{"bin": "32_token_ish", "content_sha256": "15c2f6475fc8450120c113d13ffb66e41a1689602376c09acdbe67d34f8c0567", "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/engines/_browsers/_controllers.py", "end": 1344, "example_id": "00015603170a7be7ddcf713cc092cef91b1e0e368d304e44cc5dfb68029d61f7", "language": "python", "prefix": "wser_options\",\n \"_user_data_dir\",\n \"_headers_keys\",\n \"max_pages\",\n \"page_pool\",\n \"_max_wait_for_page\",\n \"playwright\",\n \"context\",\n )\n\n def __init__(self, **kwargs: Unpack[PlaywrightSession]):\n \"", "repo": "D4Vinci/Scrapling", "span_codepoints": 128, "start": 1216, "suffix": "directory.\n\n :param headless: Run the browser in headless/hidden (default), or headful/visible mode.\n :param disable_resources: Drop requests for unnecessary resources for a speed boost.\n Requests dropped are of type `font`, `image", "target": "\"\"A Browser session manager with page pooling, it's using a persistent browser Context by default with a temporary user profile "}
{"bin": "64_token_ish", "content_sha256": "bcc202c2f3745a7c508423db9b7e6656ee7d0a7bc37f032f7ca61497e6f5a70d", "document_id": "steipete/agent-scripts@bb3688355a4c1894dd53b4ed867d1600918fadf0:skills/clawsweeper-status/scripts/clawsweeper-status.sh", "end": 3022, "example_id": "00015d53dcaa0868a7c835242732849bc891590f66c5c717751aef6ac9afe7e9", "language": "shell", "prefix": "_page=${status_page_size}\" \\\n --jq '.workflow_runs | map({\n databaseId: .id,\n name,\n event,\n status,\n conclusion,\n createdAt: .created_at,\n url: .html_url\n })' >\"$output\"\n}\n\nfetch_activity_page() {\n local endpoint_", "repo": "steipete/agent-scripts", "span_codepoints": 256, "start": 2766, "suffix": "page_size\" -eq 1 ]; then\n cat \"$error_file\" >&2\n return 1\n fi\n page_size=$((page_size / 2))\n [ \"$page_size\" -lt 1 ] && page_size=1\n done\n}\n\n: >\"$all_runs_jsonl\"\ngh run list --repo \"$clawsweeper_repo\" --limit \"$run_limit\" \\\n --json data", "target": "template=\"$1\"\n local output=\"$2\"\n local page_size=\"$activity_page_size\"\n local error_file=\"$tmpdir/activity-error\"\n\n while :; do\n if gh api \"${endpoint_template/__PAGE__/$page_size}\" >\"$output\" 2>\"$error_file\"; then\n return 0\n fi\n if [ \"$"}
{"bin": "8_token_ish", "content_sha256": "7e4ac7074d0ac6faa1be629b5e4866a53f4ef03be33239de567338dd8dcffb53", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_pdf_tables.py", "end": 6076, "example_id": "000165c985a3d908d55e45d6a3383cf49ffad5172c69a37662d33ab7e60dde84", "language": "python", "prefix": "rs\n second_table_headers = [\n \"Category\",\n \"Unit Cost\",\n \"Total Value\",\n \"Last Audit\",\n \"Notes\",\n ]\n for header in second_table_headers:\n assert header in text_content, ", "repo": "microsoft/markitdown", "span_codepoints": 32, "start": 6044, "suffix": "}'\"\n\n # Validate second table has all expected SKUs (10 products)\n second_table_skus = [\n \"SKU-8847\",\n \"SKU-9201\",\n \"SKU-4563\",\n \"SKU-7728\",\n \"SKU-3345\",\n \"SKU-5512\",\n ", "target": "f\"Should contain header '{header"}
{"bin": "64_token_ish", "content_sha256": "a9f203c76c3a7fcbff7d6b23b9f36e1f3fa9fa21a02f1998003a0710ca39e608", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/completions/installers/powershell-installer.test.ts", "end": 12450, "example_id": "000167092350f415d0d6b029b89213baa297a4ef33890f6427335fc8bd6f4f78", "language": "typescript", "prefix": "fs.readFile(profilePath, 'utf-8');\n expect(content).toBe('# My custom config\\nWrite-Host \"Hello\"');\n });\n\n it('should remove content between markers', async () => {\n const profilePath = installer.getProfilePath();\n await fs.mkdir(path.", "repo": "Fission-AI/OpenSpec", "span_codepoints": 256, "start": 12194, "suffix": " '# My config',\n ].join('\\n');\n\n await fs.writeFile(profilePath, initialContent);\n\n const result = await installer.removeProfileConfig();\n\n expect(result).toBe(true);\n const content = await fs.readFile(profilePath, 'utf-8');\n ", "target": "dirname(profilePath), { recursive: true });\n\n const initialContent = [\n '# OPENSPEC:START',\n '# OpenSpec completions',\n 'if (Test-Path \"/path\") {',\n ' . \"/path\"',\n '}',\n '# OPENSPEC:END',\n '',\n "}
{"bin": "64_token_ish", "content_sha256": "6799887379de0dcc229a02897ab44d1ad774b2cbe6ce7cad59832e42feb0129c", "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/hub/heartbeat/heartbeat_test.go", "end": 6601, "example_id": "0001683de5c2998da4db924d0317f7c2b53d56c1f8d2a3adff377a8d1b202d51", "language": "go", "prefix": "Paused)\n\t\t\tassert.Equal(t, tt.expectPending, req.payload.Systems.Pending)\n\t\t})\n\t}\n}\n\nfunc newTestHub(t *testing.T) *beszeltests.TestHub {\n\tt.Helper()\n\tapp, err := beszeltests.NewTestHub(t.TempDir())\n\trequire.NoError(t, err)\n\tt.Cleanup(app.Cleanup)\n\treturn ", "repo": "henrygd/beszel", "span_codepoints": 256, "start": 6345, "suffix": " *beszeltests.TestHub, userID, name, host, status string) *core.Record {\n\tt.Helper()\n\tsystem, err := beszeltests.CreateRecord(app.App, \"systems\", map[string]any{\n\t\t\"name\": name,\n\t\t\"host\": host,\n\t\t\"port\": \"45876\",\n\t\t\"users\": []string{userID},\n\t\t\"stat", "target": "app\n}\n\nfunc createTestUser(t *testing.T, app *beszeltests.TestHub) *core.Record {\n\tt.Helper()\n\tuser, err := beszeltests.CreateUser(app.App, \"admin@example.com\", \"password123\")\n\trequire.NoError(t, err)\n\treturn user\n}\n\nfunc createTestSystem(t *testing.T, app"}
{"bin": "16_token_ish", "content_sha256": "443080798372388ca8503e5d13da7c26dd80cec5ecf33246437cefd3f08219ef", "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/cli/run/run.rs", "end": 20140, "example_id": "00016f52ac0b0c13e6300f3c841ecf64b573622101db8ed156559eaae5db9011", "language": "rust", "prefix": " verbose,\n success: true,\n file_modified: false,\n }\n }\n\n fn render_project_header(\n &mut self,\n project: &Project,\n failed: bool,\n show_project_headers: bool,\n ) -> Result<()> {\n ", "repo": "j178/prek", "span_codepoints": 64, "start": 20076, "suffix": " }\n\n self.reporter.suspend(|| {\n writeln!(\n self.status_printer.printer().stdout(),\n \"{} {}\",\n project_status_marker(failed),\n project.display_name().cyan().bold()\n )\n", "target": " if !show_project_headers {\n return Ok(());\n "}
{"bin": "32_token_ish", "content_sha256": "092f291eeb5bb00cc23a8c942300169b7249d123bc4820e2fff0af1cff1f4d71", "document_id": "OpenCut-app/OpenCut@4d8c49ed0706c4dc145361e01c6b1f1a87cbb863:apps/web/src/components/ui/empty.tsx", "end": 2075, "example_id": "00017099ee46aa49286ac4bb0183714c0c5ab33ee328bf702a9b219d89bf4572", "language": "typescript", "prefix": "ption({ className, ...props }: React.ComponentProps<\"p\">) {\n return (\n a]:underline [&>a]:underline-offset-4 [&>a:hover]:text-primary\",\n ", "repo": "OpenCut-app/OpenCut", "span_codepoints": 128, "start": 1947, "suffix": ") {\n return (\n \n )\n}\n\nexport {\n Empty,\n Empt", "target": " className\n )}\n {...props}\n />\n )\n}\n\nfunction EmptyContent({ className, ...props }: React.ComponentProps<\"div\">"}
{"bin": "8_token_ish", "content_sha256": "e6a3afe46f95ebf1b7e2059c7f0f07a9f8699cae7d7f775def63b542b03ec689", "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/answer.sh", "end": 12631, "example_id": "0001712825d1b6446f145e2bdc1ff8f3c97e7d145bbaa58bf4bb0e135a700835", "language": "shell", "prefix": "fi\n\n if ! tmp=$(mktemp -p /run/assets \".${id}.XXXXXX\"); then\n error \"Failed to create a temporary $type answer file!\"\n return 1\n fi\n\n local expressions\n\n if [ \"$type\" = \"evaluation\" ]; then\n expressions=(\n -e '/.*<\\/ProductKey", "repo": "dockur/windows", "span_codepoints": 32, "start": 12599, "suffix": "\\/ProductKey>/d'\n )\n else\n expressions=(\n -e '/.*<\\/InstallFrom>/d'\n -e '/.*<\\/ProductKey>/d'\n -e '//,/<\\/InstallFrom>/d'\n -e '//,/<\\/ProductKey>/d'\n )\n fi\n\n if ! sed \"${expr", "target": ">/d'\n -e '//,/<"}
{"bin": "32_token_ish", "content_sha256": "a9cbe88ad1942abf948ad9f3ca3dc064f9d63ed3a0fe95cbecc794f45e2662c9", "document_id": "unitycatalog/unitycatalog@ed504deea31b30c3e7d27e360372077cce04a509:server/src/test/java/io/unitycatalog/server/utils/PopulateTestDatabase.java", "end": 11146, "example_id": "000172aa9e564556ec61b54a66db7ca8ea064c9e9855002a82eb224fd117f9f0", "language": "java", "prefix": "n session = factory.openSession()) {\n Transaction tx = session.beginTransaction();\n session.persist(externalTableInfoDAO);\n session.persist(p11);\n session.persist(p21);\n tx.commit();\n }\n\n // Create external partitioned table.", "repo": "unitycatalog/unitycatalog", "span_codepoints": 128, "start": 11018, "suffix": "/ - first_name\n // - age\n // - country (partition column)\n // All the data in this table are fake and were generated by tool Faker.\n // Partition column has three unique values / partitions.\n // Data is stored in DELTA format.\n System.out", "target": "\n // This table represents an example of how Unity handles partitioned tables.\n // The table contains three columns:\n /"}
{"bin": "8_token_ish", "content_sha256": "bff1a37c65382e95aaf6b69ce0941b4fb00e070421ae28b386642f1d79cb78fd", "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/mcp/src/index.ts", "end": 19728, "example_id": "0001739d015ba3bcadf92562d7a7f3f98116b9699e3013f3ac1d69c2c04b6347", "language": "typescript", "prefix": " // headers, even though the per-tool timeout is much higher.\n const transport = new StreamableHTTPServerTransport({\n sessionIdGenerator: undefined,\n enableJsonResponse: false,\n });\n\n const server = createMcpServer();", "repo": "upstash/context7", "span_codepoints": 32, "start": 19696, "suffix": "\n transport.close();\n server.close();\n });\n\n installTransportArgAliasing(transport);\n await server.connect(transport);\n\n await requestContext.run(context, async () => {\n await transport.handleRequest(r", "target": "\n res.on(\"close\", () => {"}
{"bin": "32_token_ish", "content_sha256": "ac0c1e1489a77d30b7183e060e379f5cbba13f9b6a8beb0cae1a5990ec5ca00c", "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:browser_use/llm/ollama/chat.py", "end": 2001, "example_id": "000175a91c1b6d96ff044222fe9f410a4e8407f9c3e849a90954b84912bdb192", "language": "python", "prefix": "tion[str]: ...\n\n\t@overload\n\tasync def ainvoke(self, messages: list[BaseMessage], output_format: type[T], **kwargs: Any) -> ChatInvokeCompletion[T]: ...\n\n\tasync def ainvoke(\n\t\tself, messages: list[BaseMessage], output_format: type[T] | None = None, **kwargs", "repo": "browser-use/browser-use", "span_codepoints": 128, "start": 1873, "suffix": "messages)\n\n\t\ttry:\n\t\t\tif output_format is None:\n\t\t\t\tresponse = await self.get_client().chat(\n\t\t\t\t\tmodel=self.model,\n\t\t\t\t\tmessages=ollama_messages,\n\t\t\t\t\toptions=self.ollama_options,\n\t\t\t\t)\n\n\t\t\t\treturn ChatInvokeCompletion(completion=response.message.content o", "target": ": Any\n\t) -> ChatInvokeCompletion[T] | ChatInvokeCompletion[str]:\n\t\tollama_messages = OllamaMessageSerializer.serialize_messages("}
{"bin": "64_token_ish", "content_sha256": "f11925640560580736567c2764d22f2a3b38131f8a648ba9f694fa0e6f39d437", "document_id": "DataWithBaraa/sql-data-warehouse-project@92406686380cde6eca208c8b43e6fa40ecd26344:tests/quality_checks_silver.sql", "end": 3429, "example_id": "0001775bb70543fc89ed13821fe3f7b64ec5b3b2c394996c08877f61a5b45c47", "language": "sql", "prefix": "t \n OR sls_order_dt > sls_due_dt;\n\n-- Check Data Consistency: Sales = Quantity * Price\n-- Expectation: No Results\nSELECT DISTINCT \n sls_sales,\n sls_quantity,\n sls_price \nFROM silver.crm_sales_details\nWHERE sls_sales != sls_quantity * sls_price\n ", "repo": "DataWithBaraa/sql-data-warehouse-project", "span_codepoints": 256, "start": 3173, "suffix": "=====\n-- Checking 'silver.erp_cust_az12'\n-- ====================================================================\n-- Identify Out-of-Range Dates\n-- Expectation: Birthdates between 1924-01-01 and Today\nSELECT DISTINCT \n bdate \nFROM silver.erp_cust_az12\nWH", "target": " OR sls_sales IS NULL \n OR sls_quantity IS NULL \n OR sls_price IS NULL\n OR sls_sales <= 0 \n OR sls_quantity <= 0 \n OR sls_price <= 0\nORDER BY sls_sales, sls_quantity, sls_price;\n\n-- ==============================================================="}
{"bin": "16_token_ish", "content_sha256": "a1b49fc9a53a294c1dce664aadc988e730fa31a69962fb26bf28faeba060eea0", "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/spiders/spider.py", "end": 11762, "example_id": "000177a09b46001bbc4ffbcc85129b78c6775fee0f77d4ba39905b7404ef0775", "language": "python", "prefix": " one as they are scraped.\n Access `spider.stats` during iteration for real-time statistics.\n\n Note: SIGINT handling for pause/resume is not available in stream mode.\n \"\"\"\n token = set_logger(self.logger)\n try:\n ", "repo": "D4Vinci/Scrapling", "span_codepoints": 64, "start": 11698, "suffix": "crawldir, self._interval)\n async for item in self._engine:\n yield item\n finally:\n self._engine = None\n reset_logger(token)\n if self.log_file:\n for handler in self.logger.handl", "target": " self._engine = CrawlerEngine(self, self._session_manager, self."}
{"bin": "64_token_ish", "content_sha256": "3f0e691dc253a9f329dc0a630983dc2ea5bc1c1f9814d71ea50a66c7451a0dd2", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/_markitdown.py", "end": 5533, "example_id": "00017b1d02d1c4743fbc3129855d720001a6bb61c6a57d3d6468a1746beea603", "language": "python", "prefix": " \"/usr/bin\",\n \"/usr/local/bin\",\n \"/opt\",\n \"/opt/bin\",\n \"/opt/local/bin\",\n \"/opt/homebrew/bin\",\n ", "repo": "microsoft/markitdown", "span_codepoints": 256, "start": 5277, "suffix": " # Register converters for successful browsing operations\n # Later registrations are tried first / take higher priority than earlier registrations\n # To this end, the most specific converters should appear below the most generi", "target": " \"C:\\\\Windows\\\\System32\",\n \"C:\\\\Program Files\",\n \"C:\\\\Program Files (x86)\",\n ]\n ):\n self._exiftool_path = candidate\n\n "}
{"bin": "64_token_ish", "content_sha256": "027a493bd355747f514515346e6f509b641e2e4b44923b5ba82ba5fac582a8cd", "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/security/test_domain_filtering.py", "end": 12890, "example_id": "000180a1d5f05bb2521618cf29f2bb4c4ba94ffbb10c92d513f9432753bc2d46", "language": "python", "prefix": "wser.watchdogs.security_watchdog import SecurityWatchdog\n\n\t\tbrowser_profile = BrowserProfile(allowed_domains=['example.com'], headless=True, user_data_dir=None)\n\t\tbrowser_session = BrowserSession(browser_profile=browser_profile)\n\t\tevent_bus = EventBus()\n\t\t", "repo": "browser-use/browser-use", "span_codepoints": 256, "start": 12634, "suffix": "watchdog._is_root_domain('site.net') is True\n\n\t\t# Subdomains (more than 1 dot) - should return False\n\t\tassert watchdog._is_root_domain('www.example.com') is False\n\t\tassert watchdog._is_root_domain('mail.example.com') is False\n\t\tassert watchdog._is_root_dom", "target": "watchdog = SecurityWatchdog(browser_session=browser_session, event_bus=event_bus)\n\n\t\t# Simple root domains (1 dot) - should return True\n\t\tassert watchdog._is_root_domain('example.com') is True\n\t\tassert watchdog._is_root_domain('test.org') is True\n\t\tassert "}
{"bin": "64_token_ish", "content_sha256": "0f13b1a10d5b81f30188542997d570c2e1b7c6514cc862fae1a74145aefb8d8f", "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/spiders/request.py", "end": 4138, "example_id": "0001811e37ea493f535528d8c25796a94d260f0bc98281a3f2e18ec5ee56b7b8", "language": "python", "prefix": " tuple(sorted(filtered_kwargs.items()))\n\n if include_headers:\n headers = self._session_kwargs.get(\"headers\") or self._session_kwargs.get(\"extra_headers\") or {}\n processed_headers = {}\n # Some header normalization\n ", "repo": "D4Vinci/Scrapling", "span_codepoints": 256, "start": 3882, "suffix": ", option=orjson.OPT_SORT_KEYS), usedforsecurity=False).digest()\n self._fp = fp\n return fp\n\n def __repr__(self) -> str:\n callback_name = getattr(self.callback, \"__name__\", None) or \"None\"\n return f\" = str::from_utf8(&output.stdout)?\n .lines()\n .filter_map(parse_toolchain_line)\n .collect();\n\n let infos: Vec = futures_util::stream::iter(entries)\n .map(async move |(name, path)| toolchain", "repo": "j178/prek", "span_codepoints": 256, "start": 7213, "suffix": " None\n }\n })\n .collect()\n .await;\n\n Ok(infos)\n }\n\n /// List system-installed Rust toolchains.\n pub(crate) async fn list_system_toolchains(&self) -> Result> {\n ", "target": "_info(name, path).await)\n .buffer_unordered(8)\n .filter_map(async move |result| match result {\n Ok(info) => Some(info),\n Err(e) => {\n warn!(\"Skipping invalid toolchain: {e:#}\");\n "}
{"bin": "64_token_ish", "content_sha256": "e9a7e9eb6b087e60e2fed07e61370fbd1bfca76b16bb95c86170cffedcebff96", "document_id": "DietrichGebert/ponytail@16f29800fd2681bdf24f3eb4ccffe38be3baec6b:benchmarks/robustness-audit.js", "end": 9044, "example_id": "00018c19ec6cd6268ff622433c230273c65d27194fc99ef1c2c01ba172f8ddaa", "language": "javascript", "prefix": " and \"@\" in a' },\n { name: 'url', arity: 1, names: ['validate_url', 'is_valid_url', 'is_url', 'validate', 'is_valid'],\n prompt: 'Write a Python function that validates whether a string is a valid HTTP or HTTPS URL.',\n cases: [[['https://example.com'", "repo": "DietrichGebert/ponytail", "span_codepoints": 256, "start": 8788, "suffix": " p = urlparse(u)\\n return p.scheme in (\"http\",\"https\") and bool(p.netloc)',\n bad: 'from urllib.parse import urlparse\\ndef validate_url(u):\\n return bool(urlparse(u))' },\n { name: 'creditcard', arity: 1, names: ['validate_credit_card', 'is_valid_", "target": "], true], [['http://a.b/c'], true], [['https://x.io/p?q=1'], true], [['garbage'], false], [[''], false], [['example.com'], false], [['ftp://example.com'], false], [['http://'], false]],\n good: 'from urllib.parse import urlparse\\ndef validate_url(u):\\n "}
{"bin": "16_token_ish", "content_sha256": "8546a18bbe8a04fd2d86495a665834aeb952f55c860586210e5f03b43ed95298", "document_id": "OpenCut-app/OpenCut@4d8c49ed0706c4dc145361e01c6b1f1a87cbb863:apps/web/src/components/ui/context-menu.tsx", "end": 8047, "example_id": "000194e11e98367a2ae854875177155019195656bb34855ce2de06a7b759ec20", "language": "typescript", "prefix": "e)}\n {...props}\n />\n )\n}\n\nfunction ContextMenuShortcut({\n className,\n ...props\n}: React.ComponentProps<\"span\">) {\n return (\n \n )\n}\n\nexport {\n ContextMenu,\n ContextMenuTrigger,\n ContextMenuContent,\n ContextMenuItem,\n ContextMenuCheckboxItem,\n ContextMenuRadioItem,\n ContextMenuLabel,\n ContextMenuSeparator,\n C", "target": "text-muted-foreground group-focus/context-menu-item:text-accent-"}
{"bin": "8_token_ish", "content_sha256": "c7b29f83a2da158b5ba141012a008e84236cc3111f22ab4303bf9d49bbdeb7e9", "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:crates/rig-core/src/memory.rs", "end": 17104, "example_id": "000196ae625e1c188bef211ccbd45fb06f6d0747f15d06d9c601fe1ffdd245cf", "language": "rust", "prefix": "filter_transforms_loaded_messages() {\n let mem = InMemoryConversationMemory::new()\n .with_filter(|msgs: Vec| msgs.into_iter().rev().take(2).collect());\n\n mem.append(\n \"c\",\n vec![user(\"1\"), assistant(\"", "repo": "0xPlaygrounds/rig", "span_codepoints": 32, "start": 17072, "suffix": "\n )\n .await\n .unwrap();\n\n let loaded = mem.load(\"c\").await.unwrap();\n assert_eq!(loaded.len(), 2, \"filter should retain only 2 messages\");\n }\n\n #[tokio::test]\n async fn arc_conversation_memory_forwards_to_inner()", "target": "2\"), user(\"3\"), assistant(\"4\")],"}
{"bin": "64_token_ish", "content_sha256": "443080798372388ca8503e5d13da7c26dd80cec5ecf33246437cefd3f08219ef", "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/cli/run/run.rs", "end": 17329, "example_id": "00019a2493031a63656d1fc1b4f92d8efb41c709fe8d74beb7453705ca5e1a54", "language": "rust", "prefix": " .run_project_level(project_runs, input, file_index, clean_baseline)\n .await?;\n let mut stop_after_level = false;\n\n for project_result in project_results {\n stop_after_level |= session.finish_project_run(project", "repo": "j178/prek", "span_codepoints": 256, "start": 17073, "suffix": "impl<'a> ProjectDepthGroups<'a> {\n fn new(projects: &'a [Arc]) -> Self {\n Self { projects, idx: 0 }\n }\n}\n\nimpl<'a> Iterator for ProjectDepthGroups<'a> {\n type Item = &'a [Arc];\n\n fn next(&mut self) -> Option", "target": "_result, show_project_headers)?;\n }\n\n if stop_after_level {\n break;\n }\n }\n\n session.finish(workspace, show_diff_on_failure).await\n}\n\nstruct ProjectDepthGroups<'a> {\n projects: &'a [Arc],\n idx: usize,\n}\n\n"}
{"bin": "8_token_ish", "content_sha256": "3f0e691dc253a9f329dc0a630983dc2ea5bc1c1f9814d71ea50a66c7451a0dd2", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/_markitdown.py", "end": 11281, "example_id": "00019ac49a0d512885fd05258c8106e572ec35262bb923fe0845988ab9826967", "language": "python", "prefix": " return self.convert_uri(source, stream_info=stream_info, **_kwargs)\n else:\n return self.convert_local(source, stream_info=stream_info, **kwargs)\n # Path object\n elif isinstance(source, Path):\n ", "repo": "microsoft/markitdown", "span_codepoints": 32, "start": 11249, "suffix": ", stream_info=stream_info, **kwargs)\n # Request response\n elif isinstance(source, requests.Response):\n return self.convert_response(source, stream_info=stream_info, **kwargs)\n # Binary stream\n elif (\n hasat", "target": "return self.convert_local(source"}
{"bin": "8_token_ish", "content_sha256": "d5426d932b8f49c499da40a69b8b75b3f66055136cc701832bb40b9d33221fd6", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py", "end": 12866, "example_id": "00019e2349eef4d6ec801403ef25b46e9b1357d34fcebede68e6a840877acfce", "language": "python", "prefix": " page_num: Page number (1-indexed)\n\n Returns:\n List of image info dicts with 'stream', 'bbox', 'name', 'y_pos'\n \"\"\"\n images = []\n\n try:\n pdf_bytes.seek(0)\n with pdfplumber.open(pdf_bytes) as pdf:", "repo": "microsoft/markitdown", "span_codepoints": 32, "start": 12834, "suffix": "len(pdf.pages):\n page = pdf.pages[page_num - 1] # 0-indexed\n images = _extract_images_from_page(page)\n except Exception:\n pass\n\n # Sort by vertical position (top to bottom)\n images.sort", "target": "\n if page_num <= "}
{"bin": "8_token_ish", "content_sha256": "cb3d208f51c444f5138a34fef6e37356f75471e10c238df4ee018e7b3d896a6c", "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/test_browser_use_skill_install_docs.py", "end": 2848, "example_id": "00019eab1322d7d6ca994bad03353a06b272d0ca7b2eec7923e9ae5bd1b25ac7", "language": "python", "prefix": "\n\tenv['PYTHONPATH'] = os.pathsep.join(part for part in (str(ROOT), env.get('PYTHONPATH', '')) if part)\n\tenv['UV_TOOL_INSTALL_ARGS_FILE'] = str(uv_args)\n\n\tresult = subprocess.run(\n\t\t[sys.executable, '-m', 'browser_use.cli', 'skill', 'install'],\n\t\tcwd=ROOT,\n", "repo": "browser-use/browser-use", "span_codepoints": 32, "start": 2816, "suffix": ",\n\t\ttext=True,\n\t\ttimeout=10,\n\t)\n\n\tassert result.returncode == 0, result.stderr\n\tassert uv_args.read_text(encoding='utf-8') == 'tool install --python 3.12 --upgrade --force browser-use'\n\texpected = (\n\t\t'---\\n'\n\t\t'name: browser-use\\n'\n\t\t'description: \"Direct", "target": "\t\tenv=env,\n\t\tcapture_output=True"}
{"bin": "16_token_ish", "content_sha256": "a9f203c76c3a7fcbff7d6b23b9f36e1f3fa9fa21a02f1998003a0710ca39e608", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/completions/installers/powershell-installer.test.ts", "end": 25476, "example_id": "0001a0c3df3128bcd1fd6231bd56ccba20580d693948557540ff72c09dff082c", "language": "typescript", "prefix": "ofilePath, '# My profile\\n');\n\n const result = await installer.configureProfile(mockScriptPath);\n expect(result).toBe(true);\n\n const raw = await fs.readFile(profilePath);\n expect(raw[0]).toBe(0xef);\n expect(raw[1]).toBe(0xbb);\n ", "repo": "Fission-AI/OpenSpec", "span_codepoints": 64, "start": 25412, "suffix": "(3).toString('utf-8');\n expect(content).toContain('# My profile');\n expect(content).toContain('# OPENSPEC:START');\n });\n\n it('should skip UTF-16 BE profile and leave it unchanged', async () => {\n delete process.env.OPENSPEC_NO_AUTO_CON", "target": " expect(raw[2]).toBe(0xbf);\n\n const content = raw.subarray"}
{"bin": "32_token_ish", "content_sha256": "b3ad41b0689c17cd7c1de3e0a08f5011bda7d693370008413492e2125b91773f", "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/disk_test.go", "end": 4610, "example_id": "0001a87218e35b65426753fb2b2ca2830c550ed06deaf5d12695f9c47f70072e", "language": "go", "prefix": "\tdiskIoCounters: map[string]disk.IOCountersStat{\n\t\t\t\t\t\"ada0\": {Name: \"ada0\", ReadBytes: 1000, WriteBytes: 1000},\n\t\t\t\t},\n\t\t\t},\n\t\t)\n\n\t\tassert.True(t, ok)\n\t\tassert.Equal(t, \"ada0\", key)\n\t\tassert.True(t, stats.Root)\n\t\tassert.Equal(t, \"/\", stats.Mountpoint)\n\t})", "repo": "henrygd/beszel", "span_codepoints": 128, "start": 4482, "suffix": "]*system.FsStats{},\n\t\t\t\"overlay\",\n\t\t\t\"/\",\n\t\t\ttrue,\n\t\t\t\"\",\n\t\t\tfsRegistrationContext{\n\t\t\t\tfilesystem: \"nvme0n1p2\",\n\t\t\t\tisWindows: false,\n\t\t\t\tdiskIoCounters: map[string]disk.IOCountersStat{\n\t\t\t\t\t\"nvme0n1\": {Name: \"nvme0n1\", ReadBytes: 1000, WriteBytes: 1000}", "target": "\n\n\tt.Run(\"uses filesystem setting as root fallback\", func(t *testing.T) {\n\t\tkey, _, ok := registerFilesystemStats(\n\t\t\tmap[string"}
{"bin": "16_token_ish", "content_sha256": "37dea31db4757ee41e18bf6e82526d2c4e421cd01cf03ba56b2f4a0f64b26cc7", "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/pdb/pdb_parse.c", "end": 1595, "example_id": "0001aeb9b55ef5f0b7c749096853185a783cb0edfa9582e5db10e073a4d63f76", "language": "c", "prefix": "names_len_off + 4;\n U32 names_base_opl = names_base_off + names_len;\n \n // table layout: hash table\n U32 hash_table_count_off = names_base_opl;\n U32 hash_table_max_off = hash_table_count_off + 4;\n \n U32 hash_table_count =", "repo": "EpicGames/raddebugger", "span_codepoints": 64, "start": 1531, "suffix": " 4 <= data.size){\n hash_table_count = *(U32*)(data.str + hash_table_count_off);\n hash_table_max = *(U32*)(data.str + hash_table_max_off);\n }\n \n // table layout: words\n U32 num_present_words_off = hash_table_max_off + 4;\n ", "target": " 0;\n U32 hash_table_max = 0;\n if (hash_table_max_off +"}
{"bin": "64_token_ish", "content_sha256": "9efd8c49e5b4bf7132f59fb450ea26db8ef4b27ada37df95ae1e1761fd8231d0", "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/core/shell.py", "end": 25642, "example_id": "0001b1298a3165d4fa6e19ce5eaa6e6fa12b102ec258772e47a4c2d119c92a61", "language": "python", "prefix": "lse cast(Selectors, page.css(css_selector))\n for page in pages:\n match extraction_type:\n case \"markdown\":\n yield cls._convert_to_markdown(page.html_content)\n case \"html\"", "repo": "D4Vinci/Scrapling", "span_codepoints": 256, "start": 25386, "suffix": " )\n for s in (\n \"\\n\",\n \"\\r\",\n \"\\t\",\n \" \",\n ):\n # Remove consecutive", "target": ":\n yield page.html_content\n case \"text\":\n txt_content = page.get_all_text(\n strip=True, ignore_tags=(\"script\", \"style\", \"noscript\", \"svg\", \"iframe\")\n "}
{"bin": "16_token_ish", "content_sha256": "f759cbf40824426107b527127b7a79b6efb613fc85f0c162d4a24cad7789d7ef", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/__main__.py", "end": 3679, "example_id": "0001b154b03f755e757ff38d9424e634c36d75371b62d83c99ce2eb1ccffde4d", "language": "python", "prefix": " parser.add_argument(\n \"--list-plugins\",\n action=\"store_true\",\n help=\"List installed 3rd-party plugins. Plugins are loaded when using the -p or --use-plugin option.\",\n )\n\n parser.add_argument(\n \"--keep-data-uris\",\n ", "repo": "microsoft/markitdown", "span_codepoints": 64, "start": 3615, "suffix": "encoded images) in the output. By default, data URIs are truncated.\",\n )\n\n parser.add_argument(\"filename\", nargs=\"?\")\n args = parser.parse_args()\n\n # Parse the extension hint\n extension_hint = args.extension\n if extension_hint is not None", "target": " action=\"store_true\",\n help=\"Keep data URIs (like base64-"}
{"bin": "32_token_ish", "content_sha256": "24179f119e6fef8863e7a291d43e708a7917286c42c8682df5d5d3302f4ab8c2", "document_id": "steipete/agent-scripts@bb3688355a4c1894dd53b4ed867d1600918fadf0:skills/npm/scripts/reserve-packages.sh", "end": 1410, "example_id": "0001b189a89a84bd87332fdf2c440f8b60620926ba70253305beb4477f2f89ec", "language": "shell", "prefix": "t}\"\n shift 2\n ;;\n --item)\n ITEM=\"${2:?missing item}\"\n ITEM_EXPLICIT=1\n shift 2\n ;;\n --account)\n ACCOUNT=\"${2:?missing account}\"\n shift 2\n ;;\n -h | --help)\n usage\n exit 0\n ;;\n --)\n ", "repo": "steipete/agent-scripts", "span_codepoints": 128, "start": 1282, "suffix": ";;\n *)\n PACKAGES+=(\"$1\")\n shift\n ;;\n esac\ndone\n\n# Desktop fallback keeps the legacy item name unless one was named explicitly.\nif [ -n \"$ACCOUNT\" ] && [ \"$ITEM_EXPLICIT\" -eq 0 ]; then\n ITEM=\"npmjs\"\nfi\n\nif [ \"${#PACKAGES[@]}\" -eq 0 ]; th", "target": " shift\n PACKAGES+=(\"$@\")\n break\n ;;\n -*)\n echo \"unknown flag: $1\" >&2\n usage >&2\n exit 2\n "}
{"bin": "16_token_ish", "content_sha256": "b3a0c69c32b557a7b1dd00b93eb466752d5ffbc6da40065dfebc1d6d27b25795", "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/1688/download.js", "end": 1731, "example_id": "0001b9d95a79302ab075a10a4a722719875867d7f61421302470ce0ee53dc441", "language": "javascript", "prefix": " name: 'download',\n access: 'read',\n description: '批量下载 1688 商品页可提取的图片和视频素材',\n domain: 'www.1688.com',\n strategy: Strategy.COOKIE,\n args: [\n {\n name: 'input',\n required: true,\n positional: true,\n ", "repo": "jackwener/OpenCLI", "span_codepoints": 64, "start": 1667, "suffix": "\n { name: 'output', default: './1688-downloads', help: '输出目录' },\n ],\n columns: ['index', 'type', 'status', 'size'],\n func: async (page, kwargs) => {\n const assets = await extractAssetsForInput(page, String(kwargs.input ?? ''));\n ", "target": " help: '1688 商品 URL 或 offer ID（如 887904326744）',\n },"}
{"bin": "32_token_ish", "content_sha256": "b599f78a00beae75851f82323500929bc374b82d8b697e18a7f33febf782c222", "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/xiaoe/courses.js", "end": 3985, "example_id": "0001c201cc003ed80057ffef4ee68162229cfe989b17051832f21631f9df764f", "language": "javascript", "prefix": "ts;\n})()`;\n}\n\nasync function getXiaoeCourses(page) {\n let rows;\n try {\n await page.goto('https://study.xiaoe-tech.com/', { waitUntil: 'load', settleMs: 8000 });\n rows = await page.evaluate(buildCoursesScript());\n } catch (error) {\n ", "repo": "jackwener/OpenCLI", "span_codepoints": 128, "start": 3857, "suffix": " `Failed to list xiaoe courses: ${message}`,\n 'page may not have rendered or auth may be required',\n );\n }\n if (!Array.isArray(rows) || rows.length === 0) {\n throw new EmptyResultError(\n 'xiaoe/courses',\n ", "target": " const message = error instanceof Error ? error.message : String(error);\n throw new CommandExecutionError(\n "}
{"bin": "32_token_ish", "content_sha256": "4a917370dfb68dcf981252756ee4ff2e2915a27993a583dd0d43e61977a62609", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/commands/store.ts", "end": 16282, "example_id": "0001c5c640409b6332fc0139f537ce593ce4294398e982400fac2668307c1ad3", "language": "typescript", "prefix": " error\n );\n }\n }\n\n async unregister(id: string, options: StoreJsonOptions = {}): Promise {\n try {\n const payload = toCleanupOutput(await unregisterStore({ id }));\n\n if (options.json) {\n printJson(payload);\n ", "repo": "Fission-AI/OpenSpec", "span_codepoints": 128, "start": 16154, "suffix": " options.json,\n { store: null, registry: null, files: null, status: [] },\n error\n );\n }\n }\n\n async remove(id: string, options: StoreRemoveOptions = {}): Promise {\n try {\n const target = await prepareStoreCleanup({ id ", "target": " return;\n }\n\n printCleanupHuman('Unregistered store', payload);\n } catch (error) {\n this.handleFailure(\n "}
{"bin": "8_token_ish", "content_sha256": "a2aed2930510f336d4c741954ba889652e6d51fa7896e117c1928cc2f08be559", "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/languages/python/uv.rs", "end": 8561, "example_id": "0001d8623d53091e1c2247271d12e146d458cff3a0d04ffd9be7a2f178966f1e", "language": "rust", "prefix": "e'll fall back to simple API approach\n _ => return self.install_from_simple_api(store, target, source).await,\n };\n\n debug!(\"Fetching uv metadata from: {}\", api_url);\n let response = REQWEST_CLIENT\n .get(&api_url)\n", "repo": "j178/prek", "span_codepoints": 32, "start": 8529, "suffix": "/*\")\n .send()\n .await\n .and_then(reqwest::Response::error_for_status)\n .with_context(|| format!(\"Failed to fetch uv metadata from PyPI at {api_url}\"))?;\n\n let metadata: serde_json::Value = response.json().", "target": " .header(\"Accept\", \"*"}
{"bin": "16_token_ish", "content_sha256": "a4cb101371d1dc25246d0a71f0c6e85ec2291d0c3c9fa0a9dbaf267bc5f38914", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py", "end": 5472, "example_id": "0001dfb8590035c6892b1a5f377ccd73b50b5a2cdd887b56d88802069767a037", "language": "python", "prefix": "shape.has_text_frame:\n if shape == title:\n md_content += \"# \" + shape.text.lstrip() + \"\\\\n\"\n else:\n md_content += shape.text + \"\\\\n\"\n\n # Group Shapes\n ", "repo": "microsoft/markitdown", "span_codepoints": 64, "start": 5408, "suffix": "GROUP:\n sorted_shapes = sorted(\n shape.shapes,\n key=lambda x: (\n float(\"-inf\") if not x.top else x.top,\n float(\"-inf\") if not x.left else", "target": " if shape.shape_type == pptx.enum.shapes.MSO_SHAPE_TYPE."}
{"bin": "8_token_ish", "content_sha256": "ad9dcc71789a56c70695c623f4be10a42594d43505ce3a6fff323ee7743ec106", "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/linker/pdb_ext/pdb_builder.c", "end": 84779, "example_id": "0001e20c114eecd5a7fdba265b3e8b7a1c3296bb2b5d55f46c4164aed065f7fa", "language": "c", "prefix": "ush_array_no_zero(arena, U16, mod_list.count);\n task.source_file_name_offset_arr = source_file_name_offsets_arr;\n tp_for_parallel(tp, 0, mod_arr_count, dbi_build_file_info_assign_file_offsets_task, &task);\n\n // pack strings\n String8 string_buffer = cv_", "repo": "EpicGames/raddebugger", "span_codepoints": 32, "start": 84747, "suffix": ", string_ht);\n\n // layout file info sections\n String8List file_info_srl = {0};\n str8_serial_begin(arena, &file_info_srl);\n str8_serial_push_u16(arena, &file_info_srl, mod_count16);\n str8_serial_push_u16(arena, &file_info_srl, total_source_file_count16", "target": "pack_string_hash_table(arena, tp"}
{"bin": "32_token_ish", "content_sha256": "5a5272472557744e1616060b62948523e7c1710eee94906d9d0c4d369bdaa756", "document_id": "OpenCut-app/OpenCut@4d8c49ed0706c4dc145361e01c6b1f1a87cbb863:apps/web/src/components/ui/calendar.tsx", "end": 6897, "example_id": "0001e22249f32dc42c0e36c74d263473a2556f9bc9dd7db71fcb9fff45476994", "language": "typescript", "prefix": "\n className,\n day,\n modifiers,\n locale,\n ...props\n}: React.ComponentProps & { locale?: Partial }) {\n const defaultClassNames = getDefaultClassNames()\n\n const ref = React.useRef(null)\n React.useEffect(() ", "repo": "OpenCut-app/OpenCut", "span_codepoints": 128, "start": 6769, "suffix": " size=\"icon\"\n data-day={day.date.toLocaleDateString(locale?.code)}\n data-selected-single={\n modifiers.selected &&\n !modifiers.range_start &&\n !modifiers.range_end &&\n !modifiers.range_middle\n }\n data-range-", "target": "=> {\n if (modifiers.focused) ref.current?.focus()\n }, [modifiers.focused])\n\n return (\n \n TimeTriggerWithWatermark.builder()\n .lastTriggerTimestamp(System.currentTimeMillis())\n .timeTrigger(t)\n "}
{"bin": "64_token_ish", "content_sha256": "ad49a50cdc019bba871bad85c97b1b6272cb8c44739f289d6010239be2069cd8", "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:browser_use/filesystem/file_system.py", "end": 9589, "example_id": "0001eca662f9b1f4c07e0ae94b1e6696aebf030c377f1bb9632a6a3b694058ee", "language": "python", "prefix": "ion(self) -> str:\n\t\treturn 'html'\n\n\nclass XmlFile(BaseFile):\n\t\"\"\"XML file implementation\"\"\"\n\n\t@property\n\tdef extension(self) -> str:\n\t\treturn 'xml'\n\n\nclass FileSystemState(BaseModel):\n\t\"\"\"Serializable state of the file system\"\"\"\n\n\tfiles: dict[str, dict[str", "repo": "browser-use/browser-use", "span_codepoints": 256, "start": 9333, "suffix": "Path, create_default_files: bool = True):\n\t\t# Handle the Path conversion before calling super().__init__\n\t\tself.base_dir = Path(base_dir) if isinstance(base_dir, str) else base_dir\n\t\tself.base_dir.mkdir(parents=True, exist_ok=True)\n\n\t\t# Create and use a de", "target": ", Any]] = Field(default_factory=dict) # full filename -> file data\n\tbase_dir: str\n\textracted_content_count: int = 0\n\n\nclass FileSystem:\n\t\"\"\"Enhanced file system with in-memory storage and multiple file type support\"\"\"\n\n\tdef __init__(self, base_dir: str | "}
{"bin": "64_token_ish", "content_sha256": "69b3a396d37da516b901d0b77db7129d10cdb9cd5df3c644178068ee6a57f585", "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:crates/rig-core/src/providers/gemini/interactions_api/streaming.rs", "end": 7726, "example_id": "0001ed00f0b34bf668fb5d011ad7ce94f47bc4b5dcfb45696626739c09694034", "language": "rust", "prefix": "amingChoice::FinalResponse(StreamingCompletionResponse {\n usage: final_usage.or_else(|| final_interaction.as_ref().and_then(|i| i.usage.clone())),\n interaction: final_interaction,\n model_version,\n }))", "repo": "0xPlaygrounds/rig", "span_codepoints": 256, "start": 7470, "suffix": "Vec>,\n) -> InteractionEventStream\nwhere\n T: HttpClientExt + Clone + Default + std::fmt::Debug + 'static,\n{\n let mut event_source = GenericEventSource::new(client.clone(), request);\n\n let stream = stream! {\n while let Some(event_result) ", "target": ";\n }\n .instrument(span);\n\n Ok(streaming::StreamingCompletionResponse::stream(Box::pin(\n stream,\n )))\n }\n}\n\npub(crate) fn stream_interaction_events(\n client: super::InteractionsClient,\n request: Request<"}
{"bin": "32_token_ish", "content_sha256": "1568d8bf1aa102797496685ffe371b2f7d84699167e00ff4ad5abed0fef912c6", "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/spiders/test_sitemap.py", "end": 2325, "example_id": "0001f3fa327011b1fa2329c9274f89a72ea8ca2e3186422798b79a744b81c4ff", "language": "python", "prefix": "url, sid=\"default\")\n return resp\n\n\nasync def _collect(agen: AsyncGenerator) -> list:\n return [item async for item in agen]\n\n\nclass TestSitemapSpiderFlow:\n @pytest.mark.asyncio\n async def test_urlset_dispatched_through_rules(self):\n class", "repo": "D4Vinci/Scrapling", "span_codepoints": 128, "start": 2197, "suffix": "self):\n return [CrawlRule(LinkExtractor(allow=r\"/posts/\"), callback=self.parse_post)]\n\n async def parse_post(self, response):\n yield {\"post\": response.url}\n\n spider = S()\n out = await _collect(spider._", "target": " S(SitemapSpider):\n name = \"s\"\n sitemap_urls = [\"https://example.com/sitemap.xml\"]\n\n def rules("}
{"bin": "16_token_ish", "content_sha256": "bc9427b1700107d33dade0026f858459850759ee9c148383c990965d5a2aec8b", "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:skills/cloud/references/api-v2.md", "end": 10222, "example_id": "0002007abf2e30bc4e300ee7da2b84dda781f37173eaf33c25b7a0ecee9b88b3", "language": "markdown", "prefix": "op_task_and_session` |\n| SessionStatus | `active`, `stopped` |\n| BrowserSessionStatus | `active`, `stopped` |\n| ProxyCountryCode | `us`, `uk`, `fr`, `it`, `jp`, `au`, `de`, `fi`, `ca`, `in` (+185 more) |\n| SupportedLLMs | `browser-use-llm`, `gpt-4.1`, `gpt", "repo": "browser-use/browser-use", "span_codepoints": 64, "start": 10158, "suffix": "`, `gemini-flash-latest`, `gemini-flash-lite-latest`, `gemini-3-flash-preview`, `gemini-3.1-flash-lite`, `claude-sonnet-4-20250514`, `gpt-4o`, `gpt-4o-mini`, `llama-4-maverick-17b-128e-instruct`, `claude-3-7-sonnet-20250219` |\n| UploadContentType | `image/", "target": "-4.1-mini`, `o4-mini`, `o3`, `gemini-2.5-flash`, `gemini-2.5-pro"}
{"bin": "32_token_ish", "content_sha256": "f47fe2e6440578eeb20408bc3131b63fb8e1ae4f6ea26dbdcca33e7901e5ee8c", "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:src/hooks/caveman-config.js", "end": 9802, "example_id": "0002074dce5d0a0d68d87e957ad34be8cce01756fcc3c827e29ed9804c4651f7", "language": "javascript", "prefix": "mbolicLink()) {\n realDir = fs.realpathSync(dir);\n const realStat = fs.statSync(realDir);\n if (!realStat.isDirectory()) return;\n if (typeof process.getuid === 'function') {\n if (realStat.uid !== process.getuid()) {\n ", "repo": "JuliusBrussee/caveman", "span_codepoints": 128, "start": 9674, "suffix": " return;\n }\n } else {\n const home = os.homedir();\n const normalized = path.resolve(realDir).toLowerCase();\n const normalizedHome = path.resolve(home).toLowerCase();\n if (!normalized.startsWith(normal", "target": " if (debug) process.stderr.write(`[caveman] appendFlag: symlink target ${realDir} owned by uid ${realStat.uid}\\n`);\n "}
{"bin": "16_token_ish", "content_sha256": "1e2203cf7d3137221a7ff2d1b79d5405580eea2ce4c22ba916dbeb9c689e96be", "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:tests/test-unit.c", "end": 27939, "example_id": "000207d571c2f990d0da7a7f6e68da1fcef998498ba6ee369ee08a51e0e1b91a", "language": "c", "prefix": "f(d - 2.0f) < 1e-6f);\n }\n\n printf(\" All distance_cosine_float tests passed.\\n\");\n}\n\nvoid test_distance_hamming() {\n printf(\"Starting %s...\\n\", __func__);\n float d;\n\n // Identical bitmaps: distance = 0\n {\n unsigned char a[] = {0xFF};\n unsigned ", "repo": "asg017/sqlite-vec", "span_codepoints": 64, "start": 27875, "suffix": "assert(d == 0.0f);\n }\n\n // All different: distance = 8\n {\n unsigned char a[] = {0xFF};\n unsigned char b[] = {0x00};\n d = _test_distance_hamming(a, b, 8);\n assert(d == 8.0f);\n }\n\n // Half different: 0xFF vs 0x0F = 4 bits differ\n {\n unsi", "target": "char b[] = {0xFF};\n d = _test_distance_hamming(a, b, 8);\n "}
{"bin": "16_token_ish", "content_sha256": "2672a14a62dc3390d2f1249555e6befe2308ca0479a1e0e2006980170ba0396c", "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:engineering-book/src/ch09-no-std-and-feature-verification.md", "end": 3948, "example_id": "0002098efcb58405c9a54fc6ff930a4676fe2877ccfc90df9c55cc0bb3e986b7", "language": "markdown", "prefix": "agnostic tools (before the OS loads)\n- BMC firmware diagnostics (resource-constrained ARM SoCs)\n- Kernel-level PCIe diagnostics (kernel module or eBPF probe)\n\n### `core` vs `alloc` vs `std` — The Three Layers\n\n```text\n┌─────────────────────────────────────", "repo": "microsoft/RustTraining", "span_codepoints": 64, "start": 3884, "suffix": " │\n│ Everything in core + alloc, PLUS: │\n│ • File I/O (std::fs, std::io) │\n│ • Networking (std::net) │\n│ • Threads (std::thread) ", "target": "────────────────────────┐\n│ std "}
{"bin": "8_token_ish", "content_sha256": "d8ae6660f9c30e8d3fd0285e7acc211debb9a6dc4537b11964b89d713452bb5c", "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/server.go", "end": 696, "example_id": "0002162ccba7efcc4ca7fa65d334afef3dd4085292c1179d0e95bc5767f326f1", "language": "go", "prefix": "rverOptions contains configuration options for starting the SSH server.\ntype ServerOptions struct {\n\tAddr string // Network address to listen on (e.g., \":45876\" or \"/path/to/socket\")\n\tNetwork string // Network type (\"tcp\" or \"unix\"", "repo": "henrygd/beszel", "span_codepoints": 32, "start": 664, "suffix": "SSH public keys for authentication\n}\n\n// hubVersions caches hub versions by session ID to avoid repeated parsing.\nvar hubVersions map[string]semver.Version\n\n// StartServer starts the SSH server with the provided options.\n// It configures the server with se", "target": ")\n\tKeys []gossh.PublicKey // "}
{"bin": "16_token_ish", "content_sha256": "69cc8ae62cec8ea6a5108b8505b4a4d8816dc8e835610424e9ca7f0504f11d70", "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/xianyu/publish.test.js", "end": 7244, "example_id": "00021d81d29da9eb2205a7ac5992cedca8a80b6acd604c101072f11e53021d0d", "language": "javascript", "prefix": "nceOf(CommandExecutionError);\n\n await expect(publishCommand.func(makePage({\n evaluateResults: [\n { hasPublishForm: true },\n { ok: true },\n { ok: true, missing: [] },\n { ok: true ", "repo": "jackwener/OpenCLI", "span_codepoints": 64, "start": 7180, "suffix": "(CommandExecutionError);\n });\n\n it('browser category script is async and returns typed failure reasons', async () => {\n const result = await runBrowserScript('', __test__.buildSelectCategoryEvaluate('笔记本'));\n\n ", "target": "},\n ],\n }), validArgs)).rejects.toBeInstanceOf"}
{"bin": "32_token_ish", "content_sha256": "7e4ac7074d0ac6faa1be629b5e4866a53f4ef03be33239de567338dd8dcffb53", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_pdf_tables.py", "end": 15084, "example_id": "00022453497390c8e3e46ea0a42333046be4ef203bbfc6f2772b86420ef959e0", "language": "python", "prefix": "\",\n \"Headphones - Premium Black\",\n \"AUDIO-5521\",\n \"$349.99\",\n \"$299.99\",\n # Product 2: USB-C Hub\n \"USB-C Hub 7-in-1 Adapter\",\n \"ACC-8834\",\n \"$79.99\",\n \"$159.", "repo": "microsoft/markitdown", "span_codepoints": 128, "start": 14956, "suffix": " \"$260.00\",\n # Product 4: Wireless Mouse\n \"Ergonomic Wireless Mouse\",\n \"ACC-9012\",\n \"$59.99\",\n # Product 5: Screen Cleaning Kit\n \"Screen Cleaning Kit\",\n \"CARE-1156\",\n ", "target": "98\",\n # Product 3: Portable SSD\n \"Portable SSD 2TB\",\n \"STOR-2241\",\n \"$289.00\",\n "}
{"bin": "8_token_ish", "content_sha256": "ab7d0b795cc4c53fbc05178f67b73f0d6f93fb57cd448017f2d32470a77c9546", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/core/update.ts", "end": 27468, "example_id": "0002245f825b75caf879f93df29bdd26773ded31e4cf6bcf020f9f32e4950be0", "language": "typescript", "prefix": "rkflowId) => availableCodexWorkflows.has(workflowId)));\n\n if (removableMatches.length > 0) {\n await this.performLegacyCleanup(\n projectPath,\n pickGlobalLegacyPromptFiles(\n detection,\n removableMatches.map((prompt) =>", "repo": "Fission-AI/OpenSpec", "span_codepoints": 32, "start": 27436, "suffix": "\n }\n\n const blockedMatches = getLegacyGlobalPromptMatches(detection)\n .filter((prompt) => !removableMatches.some((match) => match.path === prompt.path));\n\n if (blockedMatches.length > 0) {\n console.log(chalk.yellow('Preserved deferred gl", "target": " prompt.path)\n )\n );"}
{"bin": "8_token_ish", "content_sha256": "052d859eda206385b608aba621784a7ef7dce0e689a5dcc6b9f45f7aed596e76", "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:adk/interrupt_test.go", "end": 37442, "example_id": "000229d9136ff151dcfae1a368a9dfbc4811e4b4f58f20c4f655982bc5c680b0", "language": "go", "prefix": "utput.Message.Content, \"my agent completed with data resume sa\")\n\tevent, ok = iter.Next()\n\tassert.True(t, ok)\n\tassert.NoError(t, event.Err)\n\tassert.Equal(t, event.Output.MessageOutput.Message.Content, \"completed\")\n\t_, ok = iter.Next()\n\tassert.False(t, ok)\n", "repo": "cloudwego/eino", "span_codepoints": 32, "start": 37410, "suffix": "\treturn &myStore{\n\t\tm: map[string][]byte{},\n\t}\n}\n\ntype myStore struct {\n\tm map[string][]byte\n}\n\nfunc (m *myStore) Set(_ context.Context, key string, value []byte) error {\n\tm.m[key] = value\n\treturn nil\n}\n\nfunc (m *myStore) Get(_ context.Context, key string)", "target": "}\n\nfunc newMyStore() *myStore {\n"}
{"bin": "64_token_ish", "content_sha256": "f759cbf40824426107b527127b7a79b6efb613fc85f0c162d4a24cad7789d7ef", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/__main__.py", "end": 3466, "example_id": "00022aa34962fccab14944bb39d7d38a1850d200259d3a5b25d8455934533e1f", "language": "python", "prefix": " \"--cu-file-types\",\n type=str,\n help=\"Comma-separated list of file types to route to Content Understanding (e.g., pdf,jpeg,mp4). If omitted, all supported types are routed.\",\n )\n\n parser.add_argument(\n \"-p\",\n \"--use-", "repo": "microsoft/markitdown", "span_codepoints": 256, "start": 3210, "suffix": "3rd-party plugins. Plugins are loaded when using the -p or --use-plugin option.\",\n )\n\n parser.add_argument(\n \"--keep-data-uris\",\n action=\"store_true\",\n help=\"Keep data URIs (like base64-encoded images) in the output. By default, ", "target": "plugins\",\n action=\"store_true\",\n help=\"Use 3rd-party plugins to convert files. Use --list-plugins to see installed plugins.\",\n )\n\n parser.add_argument(\n \"--list-plugins\",\n action=\"store_true\",\n help=\"List installed "}
{"bin": "8_token_ish", "content_sha256": "7a17d8c904eab1813a220279c31ef51598214735923d178bed9beb92e9cf0230", "document_id": "DietrichGebert/ponytail@16f29800fd2681bdf24f3eb4ccffe38be3baec6b:benchmarks/correctness.js", "end": 5085, "example_id": "00022c4b8eaf1ee57d4c9dd6bc8bb6b2f651012fe95480b32675490950109e20", "language": "javascript", "prefix": "e.code}\n\n// Find the debounce function\nconst fn = typeof debounce === 'function' ? debounce\n : typeof module !== 'undefined' && typeof module.exports === 'function' ? module.exports\n : null;\n\nif (!fn) {\n console.error(\"FAIL: no debounce function found\")", "repo": "DietrichGebert/ponytail", "span_codepoints": 32, "start": 5053, "suffix": " debounced function should not fire immediately\nlet callCount = 0;\nconst debounced = fn(() => { callCount++; }, 50);\ndebounced();\ndebounced();\ndebounced();\n\nif (callCount > 0) {\n console.error(\"FAIL: debounce fired immediately (should wait)\");\n process.e", "target": ";\n process.exit(1);\n}\n\n// Test:"}
{"bin": "32_token_ish", "content_sha256": "0ade33ba18b5de7898b0031c737185a5bc944d529b58ba3661e833f930a77ade", "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:adk/filesystem/backend_inmemory_test.go", "end": 47932, "example_id": "00023495fc16db28f029eed94ab19391bf2fccf7af0db6904068793251be6a06", "language": "go", "prefix": "repRaw failed: %v\", err)\n\t\t}\n\t\tif len(matches) != 1 {\n\t\t\tt.Errorf(\"Expected 1 match, got %d\", len(matches))\n\t\t}\n\t})\n}\n\nfunc TestInMemoryBackend_GrepRaw_Concurrent(t *testing.T) {\n\tbackend := NewInMemoryBackend()\n\tctx := context.Background()\n\n\tfor i := 0; i", "repo": "cloudwego/eino", "span_codepoints": 128, "start": 47804, "suffix": " with error message\", i),\n\t\t})\n\t}\n\n\tt.Run(\"concurrent grep operations\", func(t *testing.T) {\n\t\tdone := make(chan bool)\n\t\tfor i := 0; i < 10; i++ {\n\t\t\tgo func() {\n\t\t\t\t_, err := backend.GrepRaw(ctx, &GrepRequest{\n\t\t\t\t\tPattern: \"error\",\n\t\t\t\t})\n\t\t\t\tif err != n", "target": " < 10; i++ {\n\t\tbackend.Write(ctx, &WriteRequest{\n\t\t\tFilePath: fmt.Sprintf(\"/file%d.txt\", i),\n\t\t\tContent: fmt.Sprintf(\"content%d"}
{"bin": "16_token_ish", "content_sha256": "8e220fb270b050bf1ece82efad6ae81ac5a9a1bdb9962fd7414e5d47b209737f", "document_id": "nicbarker/clay@e6cc36941ab2af5d81107617039d6f527a1c660b:renderers/GLES3/clay_renderer_gles3.h", "end": 10073, "example_id": "00023d247a24191a43935a6d59d02fdb50bb9da0afb04e5177602acec8f8aa6d", "language": "c", "prefix": "gl_Position = vec4(ndc * vec2(1.0, -1.0), 0.0, 1.0);\\n\"\n \" vUV = aUV;\\n\"\n \" vColor = aColor;\\n\"\n \" vTexSlot = aTexSlot;\\n\"\n \"}\\n\";\n\nconst char *GLES3_TEXT_FRAGMENT_SHADER =\n GLSL_VERSION\n \"\\n\"\n \"precision mediump float;\\n\"\n ", "repo": "nicbarker/clay", "span_codepoints": 64, "start": 10009, "suffix": ";\\n\"\n \"uniform sampler2D uTex0;\\n\"\n \"uniform sampler2D uTex1;\\n\"\n \"uniform sampler2D uTex2;\\n\"\n \"uniform sampler2D uTex3;\\n\"\n \"out vec4 fragColor;\\n\"\n \"void main() {\\n\"\n \" int slot = int(vTexSlot + 0.5);\\n\"\n \" float coverage;\\", "target": " \"in vec2 vUV;\\n\"\n \"in vec4 vColor;\\n\"\n \"in float vTexSlot"}
{"bin": "64_token_ish", "content_sha256": "f675d6d404617e1e1689184e44da357b529068183e076c753bbc1f3b4aab9a6f", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/_test_vectors.py", "end": 5553, "example_id": "000241141d9ec2c073ee7c0c308334211340a241c8c73a1e9714c1e09eeffa20", "language": "python", "prefix": "ml,%3Csvg%20width%3D\",\n ],\n ),\n FileTestVector(\n filename=\"test_mskanji.csv\",\n mimetype=\"text/csv\",\n charset=\"cp932\",\n url=None,\n must_include=[\n \"| 名前 | 年齢 | 住所 |\",\n \"| --- | --- | --- ", "repo": "microsoft/markitdown", "span_codepoints": 256, "start": 5297, "suffix": "\"ascii\",\n url=None,\n must_include=[\n \"5b64c88c-b3c3-4510-bcb8-da0b200602d8\",\n \"9700dc99-6685-40b4-9a3a-5e406dcb37f3\",\n ],\n must_not_include=[],\n ),\n FileTestVector(\n filename=\"test_rss.xml\",\n ", "target": "|\",\n \"| 佐藤太郎 | 30 | 東京 |\",\n \"| 三木英子 | 25 | 大阪 |\",\n \"| 髙橋淳 | 35 | 名古屋 |\",\n ],\n must_not_include=[],\n ),\n FileTestVector(\n filename=\"test.json\",\n mimetype=\"application/json\",\n charset="}
{"bin": "32_token_ish", "content_sha256": "bcc202c2f3745a7c508423db9b7e6656ee7d0a7bc37f032f7ca61497e6f5a70d", "document_id": "steipete/agent-scripts@bb3688355a4c1894dd53b4ed867d1600918fadf0:skills/clawsweeper-status/scripts/clawsweeper-status.sh", "end": 6936, "example_id": "00024a1c855fcf70c62510e5982a946ee60a5a3285357e7465828d4e28f4214e", "language": "shell", "prefix": "RL:-https://clawsweeper.openclaw.ai}/api/exact-review-queue\" \\\n >\"$exact_queue_json\" 2>/dev/null && \\\n jq -e '\n type == \"object\" and\n (.pending | type == \"number\") and\n (.dispatching | type == \"number\") and\n (.leased | type == \"number\") and", "repo": "steipete/agent-scripts", "span_codepoints": 128, "start": 6808, "suffix": "available=false\n printf '{}\\n' >\"$exact_queue_json\"\nfi\n\nactive_count=\"$(jq '[.workflow_runs[]\n | select(.status == \"in_progress\" or .status == \"pending\" or .status == \"queued\" or .status == \"waiting\" or .status == \"requested\")\n] | length' \"$runs_json\")\"\n", "target": "\n (.target_stats | type == \"array\")\n ' \"$exact_queue_json\" >/dev/null; then\n exact_queue_available=true\nelse\n exact_queue_"}
{"bin": "64_token_ish", "content_sha256": "9a3dd7879415651a061d217594d4ea9f985b2e3903c1b65cf03099cdb94dc49b", "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:crates/rig-core/src/providers/openai/embedding.rs", "end": 16754, "example_id": "0002559e9788436ed8dfd2561114618e64ed35d88ea83dc24b69edea94efd35e", "language": "rust", "prefix": "c_openai_embedding_response_requires_usage() {\n let body = r#\"{\n \"object\": \"list\",\n \"model\": \"text-embedding-3-small\",\n \"data\": [{ \"object\": \"embedding\", \"index\": 0, \"embedding\": [0.1] }]\n }\"#;\n\n assert", "repo": "0xPlaygrounds/rig", "span_codepoints": 256, "start": 16498, "suffix": "\"}\"#;\n let http_client =\n RecordingHttpClient::with_error_response(http::StatusCode::ACCEPTED, body);\n let client = CompletionsClient::builder()\n .api_key(\"test-key\")\n .http_client(http_client)\n .bu", "target": "!(serde_json::from_str::(body).is_err());\n }\n\n #[tokio::test]\n async fn embedding_preserves_raw_provider_error_json_on_api_error_envelope() {\n let body = r#\"{\"message\":\"embedding quota exceeded\",\"type\":\"insufficient_quota"}
{"bin": "16_token_ish", "content_sha256": "9df7c88562b71531d2c3276c5804a29df072b2222eaf9c85432bf7317588ccd1", "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/xiaohongshu/creator-notes-summary.js", "end": 3423, "example_id": "0002577f08991d2d1a4b3d4650df77e3401e893a4f331e2b48d802478eacdff6", "language": "javascript", "prefix": " of notes.entries()) {\n if (index > 0) {\n await page.wait({ time: 1 + Math.random() * 2 });\n }\n if (!note.id) {\n results.push({\n rank: index + 1,\n id: note", "repo": "jackwener/OpenCLI", "span_codepoints": 64, "start": 3359, "suffix": "published_at: note.date,\n views: String(note.views),\n likes: String(note.likes),\n collects: String(note.collects),\n comments: String(note.comments),\n shares: '',", "target": ".id,\n title: note.title,\n "}
{"bin": "16_token_ish", "content_sha256": "e191ce730fc08df89719c6c568529d86eb786e2395518ed9c12562358c33ddd3", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/commands/artifact-workflow.test.ts", "end": 20357, "example_id": "00025b780723224a11fb7f18b1cdb3b00153e0be83cdf5caecba786b4827adcb", "language": "typescript", "prefix": "aName).toBe('spec-driven');\n expect(json.state).toBe('ready');\n expect(json.contextFiles).toBeDefined();\n expect(typeof json.contextFiles).toBe('object');\n expect(json.contextFiles.proposal).toEqual([expectedProposalPath]);\n expect", "repo": "Fission-AI/OpenSpec", "span_codepoints": 64, "start": 20293, "suffix": " it('resolves single-star glob artifacts consistently between status and apply', async () => {\n const schemaDir = path.join(tempDir, 'openspec', 'schemas', 'glob-test');\n const templatesDir = path.join(schemaDir, 'templates');\n await fs.m", "target": "(json.contextFiles.specs).toEqual([expectedSpecPath]);\n });\n\n"}
{"bin": "32_token_ish", "content_sha256": "e6ff121105322d4915f1e730b2fabdd4e83031022c24eb8c82da405412e47089", "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:tests/test_repo_local_config.js", "end": 1910, "example_id": "000265c9533ba90be0390f91e2667dea1c5dcb61d656442a805ea02786f4f675", "language": "javascript", "prefix": " config resolution tests\\n');\n\ntest('returns \"full\" when no env, no repo config, no user config', (tmp) => {\n process.chdir(tmp);\n assert.strictEqual(getDefaultMode(), 'full');\n});\n\ntest('reads .caveman/config.json in cwd', (tmp) => {\n fs.mkdirSync(path", "repo": "JuliusBrussee/caveman", "span_codepoints": 128, "start": 1782, "suffix": "}));\n process.chdir(tmp);\n assert.strictEqual(getDefaultMode(), 'lite');\n});\n\ntest('reads .caveman.json in cwd', (tmp) => {\n fs.writeFileSync(path.join(tmp, '.caveman.json'),\n JSON.stringify({ defaultMode: 'ultra' }));\n process.chdir(tmp);\n assert.", "target": ".join(tmp, '.caveman'));\n fs.writeFileSync(path.join(tmp, '.caveman', 'config.json'),\n JSON.stringify({ defaultMode: 'lite' "}
{"bin": "32_token_ish", "content_sha256": "b5605939a6cb527522511e86e34ab8818263cf47ff3b9d0ec6e4dea481e3fd65", "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/engines/_browsers/_base.py", "end": 18381, "example_id": "00026bb30e9138495c507af885bb0d5187f4ea4e2c4618985e3659e41221dbd9", "language": "python", "prefix": " {\n \"args\": flags,\n \"headless\": config.headless,\n \"channel\": \"chrome\" if config.real_chrome else \"chromium\",\n }\n )\n if config.executable_path:\n ", "repo": "D4Vinci/Scrapling", "span_codepoints": 128, "start": 18253, "suffix": " else:\n self._browser_options = {}\n\n if config.additional_args:\n self._context_options.update(config.additional_args)\n\n def _build_context_with_proxy(self, proxy: Optional[ProxyType] = None) -> Dict[str, Any]:\n \"\"\"\n ", "target": "self._browser_options[\"executable_path\"] = config.executable_path\n\n self._user_data_dir = config.user_data_dir\n "}
{"bin": "16_token_ish", "content_sha256": "4a917370dfb68dcf981252756ee4ff2e2915a27993a583dd0d43e61977a62609", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/commands/store.ts", "end": 12441, "example_id": "000279d5423b5ce42cf086804cbda2830af7c6abe93c500c3b4d2782ad479a64", "language": "typescript", "prefix": "e.metadata.present === null) return 'unknown';\n return 'invalid';\n}\n\nfunction formatDoctorGitHuman(store: StoreDoctorOutput['stores'][number]): string {\n if (store.git.is_repository === null) return 'unknown';\n if (!store.git.is_repository) return 'not ", "repo": "Fission-AI/OpenSpec", "span_codepoints": 64, "start": 12377, "suffix": "no: string): string =>\n value === null ? 'unknown' : value ? yes : no;\n\n return `repository detected (commits: ${fact(store.git.has_commits, 'yes', 'none')}, uncommitted changes: ${fact(store.git.has_uncommitted_changes, 'yes', 'no')}, remote: ${fact(s", "target": "detected';\n\n const fact = (value: boolean | null, yes: string, "}
{"bin": "32_token_ish", "content_sha256": "06f26bb3c51ea4c51fbae2011a47c06440f2c1d43820a6eb65732476abc3450c", "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:sqlite-vec-rescore.c", "end": 4842, "example_id": "00027f91b8983c7f5ddc8b9d0e23d0e62d8cd23c3bd02b9c9606b03fbdf5edfd", "language": "c", "prefix": "OK) {\n sqlite3_finalize(stmt);\n return rc;\n }\n sqlite3_bind_int64(stmt, 1, chunk_rowid);\n sqlite3_bind_int64(stmt, 2, chunk_rowid);\n sqlite3_bind_zeroblob64(stmt, 3, blob_size);\n rc = sqlite3_step(stmt);\n sqlite3_finalize(stmt);", "repo": "asg017/sqlite-vec", "span_codepoints": 128, "start": 4714, "suffix": "=======================\n// Quantization\n// ============================================================================\n\nstatic void rescore_quantize_float_to_bit(const float *src, uint8_t *dst,\n size_t dimensions) ", "target": "\n if (rc != SQLITE_DONE)\n return rc;\n }\n return SQLITE_OK;\n}\n\n// ====================================================="}
{"bin": "64_token_ish", "content_sha256": "5308ec899ac988a3e5b27c4735c528027023dd4b5b7d58811cdb19b16d1eb657", "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/mido.sh", "end": 7761, "example_id": "00028400d9b6e80ade81a5528bcea5905209bc1f5a1a69f7f860f07a232d0c60", "language": "shell", "prefix": "rc != 0 )); then\n error \"Microsoft server gave us no download link to our request for an automated download!\"\n info \"Response: $linkJson\"\n return 1\n fi\n\n MIDO_URL=\"$link\"\n return 0\n}\n\ndownloadWindowsEval() {\n\n local id=\"$1\"\n local lang=\"$2\"\n ", "repo": "dockur/windows", "span_codepoints": 256, "start": 7505, "suffix": " type=\"iot\"\n winVer=\"windows-11-iot-enterprise-ltsc-eval\" ;;\n \"win11${PLATFORM,,}-enterprise-ltsc-eval\" )\n type=\"ltsc\"\n winVer=\"windows-11-enterprise\" ;;\n \"win2025-eval\" )\n type=\"server\"\n winVer=\"windows-server-2025\" ;;\n \"", "target": " local desc=\"$3\"\n local culture compare type\n local agent language winVer\n\n case \"${id,,}\" in\n \"win11${PLATFORM,,}-enterprise-eval\" )\n type=\"enterprise\"\n winVer=\"windows-11-enterprise\" ;;\n \"win11${PLATFORM,,}-enterprise-iot-eval\" )\n "}
{"bin": "16_token_ish", "content_sha256": "4225aecbb3bb3e4d52de1a7301857329ec58bfb7663b4b47703e9fd999d6004b", "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/define.sh", "end": 10891, "example_id": "000285ff92eb64fc2da9c0c2ee898be339357a76b1de3a8fe73bb3dece0e3e62", "language": "shell", "prefix": "g=\"Lithuanian\"\n culture=\"lt-LT\" ;;\n \"lv\" | \"lv-\"* | \"latvian\" | \"latvijas\" )\n [[ \"$input\" == \"latvian\" || \"$input\" == \"latvijas\" ]] && id=\"lv\"\n short=\"lv\"\n lang=\"Latvian\"\n culture=\"lv-LV\" ;;\n \"nb\" | \"nb-\"* | \"nn\" | \"nn-\"* | \"", "repo": "dockur/windows", "span_codepoints": 64, "start": 10827, "suffix": " || \"$input\" == \"no\" || \"$input\" == \"norwegian\" || \"$input\" == \"norsk\" ]] && id=\"nn\"\n short=\"no\"\n lang=\"Norwegian\"\n culture=\"nb-NO\" ;;\n \"nl\" | \"nl-\"* | \"dutch\" | \"nederlands\" )\n [[ \"$input\" == \"dutch\" || \"$input\" == \"nederlands\" ]] &", "target": "no\" | \"no-\"* | \"norwegian\" | \"norsk\" )\n [[ \"$input\" == \"nb\""}
{"bin": "64_token_ish", "content_sha256": "c842a5e93844d5c84714e4af06bfe88e5298f3dca13ac3af583dc1152492efe2", "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/fetchers/async/test_stealth.py", "end": 2325, "example_id": "00029a401b2efaa1aeea87c17d021e4edeae5a46e34f771d12cd3be684fdd9dc", "language": "python", "prefix": "nize=True)\n ).status == 200\n\n @pytest.mark.parametrize(\n \"kwargs\",\n [\n {\"block_webrtc\": True, \"allow_webgl\": True},\n {\"block_webrtc\": False, \"allow_webgl\": True},\n {\"block_webrtc\": True, \"allow_webgl", "repo": "D4Vinci/Scrapling", "span_codepoints": 256, "start": 2069, "suffix": " 10,\n \"cookies\": [{\"name\": \"test\", \"value\": \"123\", \"domain\": \"example.com\", \"path\": \"/\"}],\n \"google_search\": True,\n \"extra_headers\": {\"ayo\": \"\"},\n \"selector_config\": {\"keep_comments\": False, \"keep", "target": "\": False, \"disable_resources\": True},\n {\"wait_selector\": \"h1\", \"wait_selector_state\": \"attached\"},\n {\"wait_selector\": \"h1\", \"wait_selector_state\": \"visible\"},\n {\n \"network_idle\": True,\n \"wait\":"}
{"bin": "32_token_ish", "content_sha256": "c7b8119f0c956a69abf4cf48d23de9667d47f54b68c51ba9fb9e3762758a81f8", "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/migrations/0_collections_snapshot_0_19_0_dev_1.go", "end": 19364, "example_id": "00029b4edc6d2f7c9559dfe1a27124471b85c1f256d33d7ba30fcdf3eb112d5e", "language": "go", "prefix": "6}\",\n\t\t\t\t\t\t\"hidden\": false,\n\t\t\t\t\t\t\"id\": \"text3208210256\",\n\t\t\t\t\t\t\"max\": 12,\n\t\t\t\t\t\t\"min\": 6,\n\t\t\t\t\t\t\"name\": \"id\",\n\t\t\t\t\t\t\"pattern\": \"^[a-f0-9]+$\",\n\t\t\t\t\t\t\"presentable\": false,\n\t\t\t\t\t\t\"primaryKey\": true,\n\t\t\t\t\t\t\"required\": true,\n\t\t\t\t\t\t\"system\": true,\n\t\t\t\t\t\t\"type\":", "repo": "henrygd/beszel", "span_codepoints": 128, "start": 19236, "suffix": "relation3377271179\",\n\t\t\t\t\t\t\"maxSelect\": 1,\n\t\t\t\t\t\t\"minSelect\": 0,\n\t\t\t\t\t\t\"name\": \"system\",\n\t\t\t\t\t\t\"presentable\": false,\n\t\t\t\t\t\t\"required\": false,\n\t\t\t\t\t\t\"system\": false,\n\t\t\t\t\t\t\"type\": \"relation\"\n\t\t\t\t},\n\t\t\t\t{\n\t\t\t\t\t\t\"autogeneratePattern\": \"\",\n\t\t\t\t\t\t\"hidden\": fals", "target": " \"text\"\n\t\t\t\t},\n\t\t\t\t{\n\t\t\t\t\t\t\"cascadeDelete\": false,\n\t\t\t\t\t\t\"collectionId\": \"2hz5ncl8tizk5nx\",\n\t\t\t\t\t\t\"hidden\": false,\n\t\t\t\t\t\t\"id\": \""}
{"bin": "8_token_ish", "content_sha256": "2672a14a62dc3390d2f1249555e6befe2308ca0479a1e0e2006980170ba0396c", "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:engineering-book/src/ch09-no-std-and-feature-verification.md", "end": 14437, "example_id": "00029ec8b3ba13e3bddfd7eeadb976c4ccc3dab38b031c1bc737e002fffbbe63", "language": "markdown", "prefix": "features + each individually:\ncargo hack check --each-feature --workspace\ncargo check --workspace --all-features\ncargo check --workspace --no-default-features\n```\n\n\n#### 🔴 Exercise 2: Build a `no_std` Library\n\nCreate a library crate that compiles", "repo": "microsoft/RustTraining", "span_codepoints": 32, "start": 14405, "suffix": "simple stack-allocated ring buffer. Verify it compiles for `thumbv7em-none-eabihf` (ARM Cortex-M).\n\n\nSolution
\n\n```rust\n// lib.rs\n#![no_std]\n\npub struct RingBuffer {\n data: [u8; N],\n head: usize,\n len: us", "target": " with `#![no_std]`. Implement a "}
{"bin": "8_token_ish", "content_sha256": "d8bd95dc0fae7abc7673552f70df4fc356cb9e81527483f06c07043098e8784f", "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/gpu_test.go", "end": 4594, "example_id": "0002a041d079f54f9784dd585e4a62de6960a36adbaa6c6647d32784a5bd8328", "language": "go", "prefix": " (%)\": \"0\",\n\t\t\t\t\t\"VRAM Total Memory (B)\": \"536870912\",\n\t\t\t\t\t\"VRAM Total Used Memory (B)\": \"482263040\",\n\t\t\t\t\t\"Card Series\": \"Rembrandt [Radeon 680M]\"\n\t\t\t\t},\n\t\t\t\t\"card1\": {\n\t\t\t\t\t\"GUID\": \"38294\",\n\t\t\t\t\t\"Temperature (Sensor edge) (C)\": \"49.0\",\n\t\t\t\t\t\"Temperature", "repo": "henrygd/beszel", "span_codepoints": 32, "start": 4562, "suffix": "\n\t\t\t\t\t\"Temperature (Sensor memory) (C)\": \"62.0\",\n\t\t\t\t\t\"Average Graphics Package Power (W)\": \"19.0\",\n\t\t\t\t\t\"GPU use (%)\": \"20.3\",\n\t\t\t\t\t\"VRAM Total Memory (B)\": \"25753026560\",\n\t\t\t\t\t\"VRAM Total Used Memory (B)\": \"794341376\",\n\t\t\t\t\t\"Card Series\": \"Navi 31 [Radeo", "target": " (Sensor junction) (C)\": \"49.0\","}
{"bin": "64_token_ish", "content_sha256": "4225aecbb3bb3e4d52de1a7301857329ec58bfb7663b4b47703e9fd999d6004b", "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/define.sh", "end": 12067, "example_id": "0002a9a9cc67791a71e29114fde80d3d10bffb1842783627c24209fa7b503ef3", "language": "shell", "prefix": "e\"\n desc=\"Portuguese\"\n culture=\"pt-BR\" ;;\n \"pt-\"* )\n short=\"pp\"\n lang=\"Portuguese\"\n culture=\"pt-BR\" ;;\n \"ro\" | \"ro-\"* | \"romanian\" | \"română\" | \"romana\" )\n [[ \"$input\" == \"romanian\" || \"$input\" == \"română\" || \"$input\" ==", "repo": "dockur/windows", "span_codepoints": 256, "start": 11811, "suffix": "\" ;;\n \"sk\" | \"sk-\"* | \"slovak\" | \"slovenský\" | \"slovensky\" )\n [[ \"$input\" == \"slovak\" || \"$input\" == \"slovenský\" || \"$input\" == \"slovensky\" ]] && id=\"sk\"\n short=\"sk\"\n lang=\"Slovak\"\n culture=\"sk-SK\" ;;\n \"sl\" | \"sl-\"* | \"si\" | \"si-\"", "target": " \"romana\" ]] && id=\"ro\"\n short=\"ro\"\n lang=\"Romanian\"\n culture=\"ro-RO\" ;;\n \"ru\" | \"ru-\"* | \"russian\" | \"ruski\" )\n [[ \"$input\" == \"russian\" || \"$input\" == \"ruski\" ]] && id=\"ru\"\n short=\"ru\"\n lang=\"Russian\"\n culture=\"ru-RU"}
{"bin": "64_token_ish", "content_sha256": "35d3bac200ce605ab32a55e6d873c36bd652ca3ec57136de120b0870f450cb79", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/validation.test.ts", "end": 26852, "example_id": "0002ab0a674ed62f6ca4f88d144c1144ee19be2a3797dc623cecf041f0f8c6ed", "language": "typescript", "prefix": "ry.errors).toBe(0);\n expect(report.issues.some(i => i.message.includes('Example only'))).toBe(false);\n });\n\n it('does not count scenario headers inside fenced code blocks toward the required scenario count', async () => {\n const changeDir =", "repo": "Fission-AI/OpenSpec", "span_codepoints": 256, "start": 26596, "suffix": "Documentation Generator\nThe system SHALL render a delta example in its output.\n\n\\`\\`\\`markdown\n#### Scenario: Example scenario\n\\`\\`\\`\n`;\n\n const specPath = path.join(specsDir, 'spec.md');\n await fs.writeFile(specPath, deltaSpec);\n\n const val", "target": " path.join(testDir, 'test-change-fenced-scenario-only');\n const specsDir = path.join(changeDir, 'specs', 'test-spec');\n await fs.mkdir(specsDir, { recursive: true });\n\n const deltaSpec = `# Test Spec\n\n## ADDED Requirements\n\n### Requirement: "}
{"bin": "16_token_ish", "content_sha256": "6799887379de0dcc229a02897ab44d1ad774b2cbe6ce7cad59832e42feb0129c", "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/hub/heartbeat/heartbeat_test.go", "end": 6714, "example_id": "0002ab773b7b8a02ee1fed4622fbb29fed0da6b042227ef2721379a53e317266", "language": "go", "prefix": "zeltests.TestHub) *core.Record {\n\tt.Helper()\n\tuser, err := beszeltests.CreateUser(app.App, \"admin@example.com\", \"password123\")\n\trequire.NoError(t, err)\n\treturn user\n}\n\nfunc createTestSystem(t *testing.T, app *beszeltests.TestHub, userID, name, host, status", "repo": "henrygd/beszel", "span_codepoints": 64, "start": 6650, "suffix": "CreateRecord(app.App, \"systems\", map[string]any{\n\t\t\"name\": name,\n\t\t\"host\": host,\n\t\t\"port\": \"45876\",\n\t\t\"users\": []string{userID},\n\t\t\"status\": status,\n\t})\n\trequire.NoError(t, err)\n\treturn system\n}\n\nfunc createTriggeredAlert(t *testing.T, app *beszelte", "target": " string) *core.Record {\n\tt.Helper()\n\tsystem, err := beszeltests."}
{"bin": "8_token_ish", "content_sha256": "a497dee4dafc4abf3240125d7c0de66f8773905518ca138257a2987dd64837dd", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_cu_converter.py", "end": 2982, "example_id": "0002ae5a83aac0520fef26ed8a793ecfb7fd1f9725e75bebef7de71c30219fb0", "language": "python", "prefix": " \".json\",\n \".zip\",\n \".epub\",\n \".py\",\n \".rs\",\n ],\n )\n def test_rejects_unsupported_extensions(self, ext):\n conv = _make_converter()\n assert not conv.accepts(io.BytesIO(b\"\"), StreamInfo", "repo": "microsoft/markitdown", "span_codepoints": 32, "start": 2950, "suffix": "----------------------------------------------------------------\n# accepts() tests — MIME-based\n# ---------------------------------------------------------------------------\n\n\nclass TestAcceptsMime:\n \"\"\"Test accepts() for MIME type matching.\"\"\"\n\n @py", "target": "(extension=ext))\n\n\n# -----------"}
{"bin": "8_token_ish", "content_sha256": "c7b8119f0c956a69abf4cf48d23de9667d47f54b68c51ba9fb9e3762758a81f8", "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/migrations/0_collections_snapshot_0_19_0_dev_1.go", "end": 25825, "example_id": "0002aed310a0bd79bc59d0dccd1e97bcd3fafe7ee71f6474ced3b7a2165124d6", "language": "go", "prefix": "[a-z0-9]+$\",\n\t\t\t\t\"presentable\": false,\n\t\t\t\t\"primaryKey\": true,\n\t\t\t\t\"required\": true,\n\t\t\t\t\"system\": true,\n\t\t\t\t\"type\": \"text\"\n\t\t\t},\n\t\t\t{\n\t\t\t\t\"cascadeDelete\": true,\n\t\t\t\t\"collectionId\": \"_pb_users_auth_\",\n\t\t\t\t\"hidden\": false,\n\t\t\t\t\"id\": \"relation2375276105\",\n\t\t", "repo": "henrygd/beszel", "span_codepoints": 32, "start": 25793, "suffix": "\": 0,\n\t\t\t\t\"name\": \"user\",\n\t\t\t\t\"presentable\": false,\n\t\t\t\t\"required\": false,\n\t\t\t\t\"system\": false,\n\t\t\t\t\"type\": \"relation\"\n\t\t\t},\n\t\t\t{\n\t\t\t\t\"cascadeDelete\": true,\n\t\t\t\t\"collectionId\": \"2hz5ncl8tizk5nx\",\n\t\t\t\t\"hidden\": false,\n\t\t\t\t\"id\": \"relation3377271179\",\n\t\t\t\t\"ma", "target": "\t\t\"maxSelect\": 1,\n\t\t\t\t\"minSelect"}
{"bin": "64_token_ish", "content_sha256": "8ed1398aa1ca4b7885c4f0c3fe12e2f4555fb681cb73ab10cb79f3079d24870a", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/_exceptions.py", "end": 1698, "example_id": "0002d098598f02343a237ffc493c47d122e75ef19e532cd947c8b76cab53fd28", "language": "python", "prefix": "er was found for the given file.\n \"\"\"\n\n pass\n\n\nclass FailedConversionAttempt(object):\n \"\"\"\n Represents a single attempt to convert a file.\n \"\"\"\n\n def __init__(self, converter: Any, exc_info: Optional[tuple] = None):\n self.converter", "repo": "microsoft/markitdown", "span_codepoints": 256, "start": 1442, "suffix": " message: Optional[str] = None,\n attempts: Optional[List[FailedConversionAttempt]] = None,\n ):\n self.attempts = attempts\n\n if message is None:\n if attempts is None:\n message = \"File conversion failed.\"\n ", "target": " = converter\n self.exc_info = exc_info\n\n\nclass FileConversionException(MarkItDownException):\n \"\"\"\n Thrown when a suitable converter was found, but the conversion\n process fails for any reason.\n \"\"\"\n\n def __init__(\n self,\n "}
{"bin": "32_token_ish", "content_sha256": "37dea31db4757ee41e18bf6e82526d2c4e421cd01cf03ba56b2f4a0f64b26cc7", "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/pdb/pdb_parse.c", "end": 29511, "example_id": "0002d536a826a8e1f3ffc3424bb8ade09842d9886aa2b877cbd0754971712e11", "language": "c", "prefix": " // unique name\n if (compare_unique_name){\n if (lf_struct->props & CV_TypeProp_HasUniqueName) {\n U8 *unique_name_ptr = name_ptr + name.size + 1;\n String8 unique_name", "repo": "EpicGames/raddebugger", "span_codepoints": 128, "start": 29383, "suffix": " }\n }\n else{\n extracted_name = name;\n }\n }\n }\n }break;\n \n case CV_LeafKind_CLASS2:\n ", "target": " = str8_cstring_capped((char*)unique_name_ptr, (char *)(first + cap));\n extracted_name = unique_name;\n "}
{"bin": "64_token_ish", "content_sha256": "c84154be2a7e8cb5c0b350485417005c4865b86870578e24f3b773b5a82c97d3", "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/cli/install.rs", "end": 14160, "example_id": "0002d5d6d3a6c7eb6159cb3e5a0d80fdbd41e2029cfcc9f6fe9a8b0a834eb0ef", "language": "rust", "prefix": " \" {}\\n\",\n ),\n \"note:\".yellow().bold(),\n \"hint:\".yellow().bold(),\n \"git config --unset-all --global core.hooksPath\".cyan(),\n \"git config --unset-all --system core.hooksPath\".cyan(),\n ", "repo": "j178/prek", "span_codepoints": 256, "start": 13904, "suffix": "_dir().await?\n };\n\n let types: Vec = if all {\n HookType::value_variants().to_vec()\n } else {\n get_hook_types(hook_types, project.as_ref(), config.as_deref())\n };\n\n for hook_type in types {\n let hook_path = hook", "target": " \"git config --local core.hooksPath \".cyan(),\n );\n }\n\n let project = Project::discover(config.as_deref(), &CWD).ok();\n let hooks_path = if let Some(dir) = git_dir {\n dir.join(\"hooks\")\n } else {\n git::get_git_hooks"}
{"bin": "8_token_ish", "content_sha256": "1e2203cf7d3137221a7ff2d1b79d5405580eea2ce4c22ba916dbeb9c689e96be", "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:tests/test-unit.c", "end": 46181, "example_id": "0002d7a65932c0fdc18ede08e8051ca69a5a60990ce4434e062e1dceda15b523", "language": "c", "prefix": "\n\n // Error: missing BY\n {\n const char *input = \"emb float[128] INDEXED diskann(neighbor_quantizer=binary)\";\n rc = vec0_parse_vector_column(input, (int)strlen(input), &col);\n assert(rc == SQLITE_ERROR);\n }\n\n // Error: unknown algorithm\n {\n ", "repo": "asg017/sqlite-vec", "span_codepoints": 32, "start": 46149, "suffix": "128] INDEXED BY hnsw(neighbor_quantizer=binary)\";\n rc = vec0_parse_vector_column(input, (int)strlen(input), &col);\n assert(rc == SQLITE_ERROR);\n }\n\n // Error: unknown option key\n {\n const char *input = \"emb float[128] INDEXED BY diskann(neighbo", "target": " const char *input = \"emb float["}
{"bin": "8_token_ish", "content_sha256": "b3ad41b0689c17cd7c1de3e0a08f5011bda7d693370008413492e2125b91773f", "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/disk_test.go", "end": 15218, "example_id": "0002d9ede84150bc978d27d1b9ab24a5dcb6aeaca5ed6ef5108512711e4a1fd4", "language": "go", "prefix": "efPath: \"/extra-filesystems\",\n\t\t\t\tdiskIoCounters: map[string]disk.IOCountersStat{\n\t\t\t\t\t\"nvme0n1p1\": {Name: \"nvme0n1p1\"},\n\t\t\t\t\t\"nvme1n1\": {Name: \"nvme1n1\"},\n\t\t\t\t},\n\t\t\t},\n\t\t}\n\t}\n\n\tt.Run(\"registers direct child of extra-filesystems\", func(t *testing.T) {", "repo": "henrygd/beszel", "span_codepoints": 32, "start": 15186, "suffix": "(map[string]*system.FsStats)}\n\t\td := makeDiscovery(agent)\n\n\t\td.addPartitionExtraFs(disk.PartitionStat{\n\t\t\tDevice: \"/dev/nvme0n1p1\",\n\t\t\tMountpoint: \"/extra-filesystems/nvme0n1p1__caddy1-root\",\n\t\t})\n\n\t\tstats, exists := agent.fsStats[\"nvme0n1p1\"]\n\t\tassert", "target": "\n\t\tagent := &Agent{fsStats: make"}
{"bin": "8_token_ish", "content_sha256": "a9cbe88ad1942abf948ad9f3ca3dc064f9d63ed3a0fe95cbecc794f45e2662c9", "document_id": "unitycatalog/unitycatalog@ed504deea31b30c3e7d27e360372077cce04a509:server/src/test/java/io/unitycatalog/server/utils/PopulateTestDatabase.java", "end": 7481, "example_id": "0002df7ea6cf5b6da82660a53ff9025fdca2de197f5d451840dc4deb64bda0cc", "language": "java", "prefix": "d();\n addTypeTextAndJsonText(marksColumnUniform);\n\n TableInfoDAO uniformTableInfoDAO =\n TableInfoDAO.builder()\n .id(uniformTableId)\n .name(tableName + \"_uniform\")\n .schemaId(UUID.fromString(schemaId))\n ", "repo": "unitycatalog/unitycatalog", "span_codepoints": 32, "start": 7449, "suffix": " .columns(List.of(idColumnUniform, nameColumnUniform, marksColumnUniform))\n .dataSourceFormat(DataSourceFormat.DELTA.getValue())\n .type(TableType.EXTERNAL.getValue())\n .createdAt(new Date())\n .updatedAt(n", "target": " .comment(\"Uniform table\")\n "}
{"bin": "32_token_ish", "content_sha256": "79ed8d9f177c8fd734382eb386f48693117fcc6f0f849d771d5d12dd5616ffeb", "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/mcp/src/lib/auth/auth-prompt.ts", "end": 1614, "example_id": "0002e8d3f888793e0cda4b0fc62842fbc3ff97cc2b602dac1e56eb49ecc73699", "language": "typescript", "prefix": "d writes credentials into your MCP client config.\",\n \"After it finishes, disable then re-enable the Context7 MCP server in your editor so the new credentials take effect.\",\n ].join(\"\\n\");\n}\n\n// User-facing strings double as enum const values: keeps the", "repo": "upstash/context7", "span_codepoints": 128, "start": 1486, "suffix": "\nconst CHOICE_RUN_SETUP = \"I'll run the command to sign in\";\nconst CHOICE_STAY_ANON = \"Continue anonymously with smaller limits\";\n\n/**\n * Fires a form-mode elicitation that surfaces a sign-in nudge in the client UI\n * when the backend has signaled (via `X-", "target": " schema in the\n// simpler `enum: [...]` shape, which clients render more reliably than\n// `oneOf` with separate `const`/`title`."}
{"bin": "8_token_ish", "content_sha256": "9afb82603add497b23b3fc1bda6166cca0f8459d3dc1eaf52e53a6c5bb07605d", "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:adk/failover_chatmodel_test.go", "end": 16976, "example_id": "0002e9de0001d219b2f1e4825609cdaa9f626d7798dbb6baa6468a9c6fc680da", "language": "go", "prefix": "Attempt)\n\t\t\t\treturn m2, nil, nil\n\t\t\t},\n\t\t}\n\n\t\tw := newFailoverModelWrapper[*schema.Message](&failoverProxyModel{}, cfg)\n\t\tctx := withTypedChatModelAgentExecCtx(context.Background(), &chatModelAgentExecCtx{\n\t\t\tfailoverLastSuccessModel: m1,\n\t\t})\n\t\tsr, err :=", "repo": "cloudwego/eino", "span_codepoints": 32, "start": 16944, "suffix": "{schema.UserMessage(\"hi\")})\n\t\trequire.NoError(t, err)\n\t\tmsgs, err := drainMessageStream(sr)\n\t\trequire.NoError(t, err)\n\t\trequire.Len(t, msgs, 1)\n\t\trequire.Equal(t, \"final\", msgs[0].Content)\n\t\trequire.Equal(t, \"p1p2\", seenOutput.Load())\n\t\trequire.Equal(t, in", "target": " w.Stream(ctx, []*schema.Message"}
{"bin": "32_token_ish", "content_sha256": "68074fd22a569d98ccb447ed827a43637115b4b427cd5c53ef21810f1a0f66c1", "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:browser_use/observability.py", "end": 1091, "example_id": "0002edc0b76665fff1c3a2165b42611a949ea14ce552adca1314046a1d4f22a7", "language": "python", "prefix": "port Any, Literal, TypeVar, cast\n\nlogger = logging.getLogger(__name__)\nfrom dotenv import load_dotenv\n\nload_dotenv()\n\n# Type definitions\nF = TypeVar('F', bound=Callable[..., Any])\n\n\n# Check if we're in debug mode\ndef _is_debug_mode() -> bool:\n\t\"\"\"Check if ", "repo": "browser-use/browser-use", "span_codepoints": 128, "start": 963, "suffix": "lower()\n\tif lmnr_debug_mode == 'debug':\n\t\t# logger.info('Debug mode is enabled for observability')\n\t\treturn True\n\t# logger.info('Debug mode is disabled for observability')\n\treturn False\n\n\n# Try to import lmnr observe\n_LMNR_AVAILABLE = False\n_lmnr_observe =", "target": "we're in debug mode based on environment variables or logging level.\"\"\"\n\n\tlmnr_debug_mode = os.getenv('LMNR_LOGGING_LEVEL', '')."}
{"bin": "64_token_ish", "content_sha256": "06f26bb3c51ea4c51fbae2011a47c06440f2c1d43820a6eb65732476abc3450c", "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:sqlite-vec-rescore.c", "end": 15375, "example_id": "000303fa034fb62d0fbb436f22503192f8a779af6251491cbe9e72e5069c5c31", "language": "c", "prefix": " {\n rc = SQLITE_ERROR;\n goto cleanup;\n }\n // Validate blob sizes match chunk_size expectations\n if (validityBytes < (p->chunk_size + 7) / 8 ||\n rowidsBytes < p->chunk_size * (int)sizeof(i64)) {\n rc = SQLITE_ERROR;\n goto ", "repo": "asg017/sqlite-vec", "span_codepoints": 256, "start": 15119, "suffix": ";\n for (int j = 0; j < p->chunk_size; j++) {\n if (!bitmap_get(chunkValidity, j))\n continue;\n i64 rid = chunkRowids[j];\n void *found = bsearch(&rid, arrayRowidsIn->z, arrayRowidsIn->length,\n s", "target": "cleanup;\n }\n\n memset(chunk_distances, 0, p->chunk_size * sizeof(f32));\n memset(chunk_topk_idxs, 0, k_oversample * sizeof(i32));\n bitmap_copy(b, chunkValidity, p->chunk_size);\n\n if (arrayRowidsIn) {\n bitmap_clear(bmRowids, p->chunk_size)"}
{"bin": "32_token_ish", "content_sha256": "e6a3afe46f95ebf1b7e2059c7f0f07a9f8699cae7d7f775def63b542b03ec689", "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/answer.sh", "end": 14085, "example_id": "00030626ff96f77db41c9fb21538a51c8b5e4434e94532d38d4947a8e395fa2c", "language": "shell", "prefix": " \"Failed to select $type image index $index!\"\n return 1\n fi\n fi\n\n if ! markGeneratedXML \"$tmp\" ||\n ! xmllint --nonet --noout \"$tmp\"; then\n rm -f \"$tmp\"\n error \"Generated $type answer file is invalid!\"\n return 1\n fi\n\n if ! chmod 644 ", "repo": "dockur/windows", "span_codepoints": 128, "start": 13957, "suffix": " fi\n\n return 0\n}\n\ngenerateEvalXML() {\n\n # Evaluation templates are generated from their normal counterpart so\n # both variants remain identical except for evaluation-specific selectors.\n\n local id=\"$1\"\n local detected_index=\"${2:-}\"\n local normal=\"${", "target": "\"$tmp\" || ! mv -f \"$tmp\" \"$target\"; then\n rm -f \"$tmp\"\n error \"Failed to create $type answer file: $target\"\n return 1\n "}
{"bin": "8_token_ish", "content_sha256": "95383ddef7ba45f64965375a87116f32448700cc800cadba683fdbfb17a4a95e", "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/test_history_wait_time.py", "end": 3144, "example_id": "000317d756ad550db6336dba541664135c4ba5c3b68e30dc5a8b167d63c9248c", "language": "python", "prefix": "ate old format from JSON\n\told_metadata_dict = {\n\t\t'step_number': 0,\n\t\t'step_start_time': 1000.0,\n\t\t'step_end_time': 1002.5,\n\t\t# step_interval field doesn't exist (old format)\n\t}\n\n\t# Should load successfully with step_interval defaulting to None\n\tmetadata =", "repo": "browser-use/browser-use", "span_codepoints": 32, "start": 3112, "suffix": "_metadata_dict)\n\n\tassert metadata.step_number == 0\n\tassert metadata.step_start_time == 1000.0\n\tassert metadata.step_end_time == 1002.5\n\tassert metadata.step_interval is None # Default value\n\n\ndef test_duration_seconds_property_still_works():\n\t\"\"\"Test that", "target": " StepMetadata.model_validate(old"}
{"bin": "32_token_ish", "content_sha256": "7710f0c3f8a841937588aa777aa88e7c65df3bfbca88158aa2f93fbc65ca96d9", "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/__tests__/auth-commands.test.ts", "end": 8851, "example_id": "0003212c2234a0442e4f64a1a30202864c7d9d386a7067a5e9608f1ee7f3685c", "language": "typescript", "prefix": ": \"bearer\" },\n });\n\n const pending = performLogin(false);\n // First poll fires after the initial 0ms interval; slow_down then\n // bumps the interval by 5000ms before the second poll.\n await vi.advanceTimersByTimeAsync(5500);\n ", "repo": "upstash/context7", "span_codepoints": 128, "start": 8723, "suffix": "finally {\n vi.useRealTimers();\n }\n });\n\n test(\"returns null when start request throws\", async () => {\n mockStartDeviceAuthorization.mockRejectedValue(new Error(\"network down\"));\n\n expect(await performLogin(false)).toBeNull();\n expect(moc", "target": "const result = await pending;\n expect(result).toBe(\"t\");\n expect(mockPollDeviceToken).toHaveBeenCalledTimes(2);\n } "}
{"bin": "16_token_ish", "content_sha256": "c84154be2a7e8cb5c0b350485417005c4865b86870578e24f3b773b5a82c97d3", "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/cli/install.rs", "end": 11435, "example_id": "0003216bc1ca8a073368c81393f364edc11feed0e3ecc62ea6dbd497acf3e554", "language": "rust", "prefix": "))\n .replace(\"[PREK_ARGS]\", &args.join(\" \"));\n\n fs_err::OpenOptions::new()\n .write(true)\n .create(true)\n .truncate(true)\n .open(&hook_path)?\n .write_all(hook_script.as_bytes())?;\n\n #[cfg(unix)]\n {\n ", "repo": "j178/prek", "span_codepoints": 64, "start": 11371, "suffix": "hook_path.metadata()?.permissions();\n perms.set_mode(hook_mode);\n fs_err::set_permissions(&hook_path, perms)?;\n }\n\n // Unused on non-Unix platforms\n #[cfg(not(unix))]\n let _ = hook_mode;\n\n writeln!(printer.stdout(), \"{hint}\")?;", "target": "use std::os::unix::fs::PermissionsExt;\n\n let mut perms = "}
{"bin": "32_token_ish", "content_sha256": "0c1b6668c25c53f3726ae586a89b69d62c3032532207e5e702e02c928a10f680", "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:compose/chain_branch_test.go", "end": 5862, "example_id": "00032e58cde93583b30d0977a5e8ed5305ca1fd0dc676abb6951d6123c48b84e", "language": "go", "prefix": "utput, nil\n\t\t\t})))\n\n\t\tassert.Nil(t, c.err)\n\t\tcompiledChain, err := c.Compile(context.Background())\n\t\tassert.Nil(t, err)\n\n\t\tout, err := compiledChain.Invoke(context.Background(), \"one\")\n\t\tassert.Nil(t, err)\n\t\tassert.Equal(t, \"oneone\", out)\n\t})\n\n\tt.Run(\"real", "repo": "cloudwego/eino", "span_codepoints": 128, "start": 5734, "suffix": " {\n\t\t\tmsg, err := sr.Recv()\n\t\t\tif err != nil {\n\t\t\t\treturn \"\", err\n\t\t\t}\n\t\t\tdefer sr.Close()\n\n\t\t\tswitch msg {\n\t\t\tcase \"one\":\n\t\t\t\treturn \"one_key\", nil\n\t\t\tcase \"two\":\n\t\t\t\treturn \"two_key\", nil\n\t\t\tcase \"three\":\n\t\t\t\treturn \"three_key\", nil\n\t\t\tdefault:\n\t\t\t\tretur", "target": " stream\", func(t *testing.T) {\n\t\tstreamCon := func(ctx context.Context, sr *schema.StreamReader[string]) (key string, err error)"}
{"bin": "8_token_ish", "content_sha256": "06f26bb3c51ea4c51fbae2011a47c06440f2c1d43820a6eb65732476abc3450c", "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:sqlite-vec-rescore.c", "end": 1138, "example_id": "00033273f4f5185e93a8171e5f0ab036d781962e9ad133e9f7b4054af18afebb", "language": "c", "prefix": " // Quantized chunk table (same layout as _vector_chunks)\n char *zSql = sqlite3_mprintf(\n \"CREATE TABLE \\\"%w\\\".\\\"%w_rescore_chunks%02d\\\"\"\n \"(rowid PRIMARY KEY, vectors BLOB NOT NULL)\",\n p->schemaName, p->tableName, i);\n if (!zSql", "repo": "asg017/sqlite-vec", "span_codepoints": 32, "start": 1106, "suffix": " sqlite3_stmt *stmt;\n int rc = sqlite3_prepare_v2(db, zSql, -1, &stmt, 0);\n sqlite3_free(zSql);\n if ((rc != SQLITE_OK) || (sqlite3_step(stmt) != SQLITE_DONE)) {\n *pzErr = sqlite3_mprintf(\n \"Could not create '_rescore_chunks%02d' shad", "target": ")\n return SQLITE_NOMEM;\n "}
{"bin": "8_token_ish", "content_sha256": "3641a863ac524478d70063e4487c16e17230c167d21d6ebdd2a738539d836a63", "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/archive.rs", "end": 7417, "example_id": "000336198cfac164ebafc3bf71372c619475d39b1b0ecc6d596e915c01bec2b8", "language": "rust", "prefix": " prior to proceeding, as per:\n // https://docs.rs/async_zip/0.0.16/async_zip/base/read/stream/\n (.., zip) = entry.skip().await?;\n\n // Store the current offset.\n offset = zip.offset();\n\n continue;\n ", "repo": "j178/prek", "span_codepoints": 32, "start": 7385, "suffix": ".join(path);\n let is_dir = entry.reader().entry().dir()?;\n\n // Either create the directory or write the file to disk.\n if is_dir {\n if directories.insert(path.clone()) {\n fs_err::tokio::create_dir_all(path).aw", "target": " };\n\n let path = target"}
{"bin": "64_token_ish", "content_sha256": "bc0af3ba327657630e5f6c60be619e6b5394bf03edc29b1384a15f09a1b348bf", "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:src/hooks/caveman-activate.js", "end": 3486, "example_id": "00033d9ab62e5672a7a8c2eb2ee44ab96559533530e77753c3f5fa1aa57ad69d", "language": "javascript", "prefix": "th hooks at\n// $CLAUDE_CONFIG_DIR/hooks/ and the skill at $CLAUDE_CONFIG_DIR/skills/caveman/.\n// All misses fall through to the hardcoded fallback ruleset below.\nconst skillCandidates = [];\nif (process.env.CLAUDE_PLUGIN_ROOT) {\n skillCandidates.push(", "repo": "JuliusBrussee/caveman", "span_codepoints": 256, "start": 3230, "suffix": "';\nfor (const candidate of skillCandidates) {\n try {\n skillContent = fs.readFileSync(candidate, 'utf8');\n break;\n } catch (e) { /* try next candidate */ }\n}\n\nlet output;\n\nif (skillContent) {\n // Strip YAML frontmatter\n const body = skillContent.r", "target": "path.join(process.env.CLAUDE_PLUGIN_ROOT, 'skills', 'caveman', 'SKILL.md'));\n}\nskillCandidates.push(\n path.join(__dirname, '..', '..', 'skills', 'caveman', 'SKILL.md'),\n path.join(__dirname, '..', 'skills', 'caveman', 'SKILL.md')\n);\n\nlet skillContent = '"}
{"bin": "8_token_ish", "content_sha256": "6f8e0258269e160c83ea20b5b6568220afad26b3a325e65bb3c1e7dd27297781", "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:type-driven-correctness-book/src/ch13-reference-card.md", "end": 4955, "example_id": "00033de5e0a3aa7fdee17ed0f83206cbe3f59edd81d1ce71b500dba53f2d5600", "language": "markdown", "prefix": "e | Don't derive Clone |\n| `let vendor_id: u16 = 0xFFFF` | Sentinel carried internally | `let vendor_id: Option = None` |\n| `fn route(level: &str)` with fallback | Typos silently default | `let level: DiagLevel = s.parse()?` |\n| `Builder::new().finish", "repo": "microsoft/RustTraining", "span_codepoints": 32, "start": 4923, "suffix": "object constructed | Typestate builder: `finish()` gated on `Set` |\n| `let buf: Vec` for fixed-size HW buffer | Size only checked at runtime | `RegisterBank<4096>` (const generic) |\n| Raw `unsafe { ptr::read(...) }` scattered | UB risk, unauditable | `", "target": "()` without fields | Incomplete "}
{"bin": "16_token_ish", "content_sha256": "bfb61792348d0e569cedf1c2b3307d237c6c2ecebbf76db01f09e4a0c8922f38", "document_id": "TecharoHQ/anubis@34badc646c39af3d9f1f70757474b141316f23ad:cmd/robots2policy/main.go", "end": 1713, "example_id": "000344d27c4d98c2d71d6b719fb9f0079435e62c3ec383c16695e5a0b7c550c6", "language": "go", "prefix": "ig.Weight `yaml:\"weight,omitempty\" json:\"weight,omitempty\"`\n\tName string `yaml:\"name\" json:\"name\"`\n\tAction string `yaml:\"action\" json:\"action\"`\n}\n\nfunc init() {\n\tflag.Usage = func() {\n\t\tfmt.Fprintf(os", "repo": "TecharoHQ/anubis", "span_codepoints": 64, "start": 1649, "suffix": "\"%s [options] -input \\n\\n\", os.Args[0])\n\t\tflag.PrintDefaults()\n\t\tfmt.Fprintln(os.Stderr, \"\\nExamples:\")\n\t\tfmt.Fprintln(os.Stderr, \" # Convert local robots.txt file\")\n\t\tfmt.Fprintln(os.Stderr, \" robots2policy -input robots.txt -output policy.y", "target": ".Stderr, \"Usage of %s:\\n\", os.Args[0])\n\t\tfmt.Fprintf(os.Stderr, "}
{"bin": "8_token_ish", "content_sha256": "5a9976de581707f0f816221505b968d3d2da6a9415279166c491882a217f5ad7", "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/linker/lnk_symbol_table.c", "end": 16564, "example_id": "000352c2a7f43acd1d1587cd2ae88d621b2e36ea28c5f37fe093a99f0c7cfef7", "language": "c", "prefix": "x1000);\n new_trie->name = &symbol->name;\n new_trie->symbol = symbol;\n MemoryZeroArray(new_trie->child);\n\n // try to insert new node\n LNK_SymbolHashTrie *cmp = ins_atomic_ptr_eval_cond_assign(curr_trie_ptr,", "repo": "EpicGames/raddebugger", "span_codepoints": 32, "start": 16532, "suffix": " was symbol inserted?\n if (cmp == curr_trie) {\n break;\n }\n\n // rollback chunk list push\n --chunks->last->count;\n\n // retry insert with trie node from another thread\n curr_trie = cmp;\n }\n\n // load current symbol\n ", "target": " new_trie, curr_trie);\n\n //"}
{"bin": "32_token_ish", "content_sha256": "bd73903a16a7ef88221cde582f85e861f568f4d9fd018c94d82ebbde37357b6e", "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/lichess/lichess.test.js", "end": 3007, "example_id": "00035e73549bd9e6738e0bb311d8593ad9b3080ef91f8b3bc1c6e24ab8e749f2", "language": "javascript", "prefix": "ching', async () => {\n const fetchMock = vi.fn();\n vi.stubGlobal('fetch', fetchMock);\n await expect(cmd.func({ perf: '' })).rejects.toThrow(ArgumentError);\n await expect(cmd.func({ perf: 'turbo' })).rejects.toThrow(ArgumentError", "repo": "jackwener/OpenCLI", "span_codepoints": 128, "start": 2879, "suffix": "toHaveBeenCalled();\n });\n\n it('throws EmptyResultError on empty leaderboard', async () => {\n vi.stubGlobal('fetch', vi.fn().mockResolvedValue(new Response(JSON.stringify({ users: [] }), { status: 200 })));\n await expect(cmd.func({ perf:", "target": ");\n await expect(cmd.func({ perf: 'blitz', limit: 9999 })).rejects.toThrow(ArgumentError);\n expect(fetchMock).not."}
{"bin": "64_token_ish", "content_sha256": "052d859eda206385b608aba621784a7ef7dce0e689a5dcc6b9f45f7aed596e76", "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:adk/interrupt_test.go", "end": 63701, "example_id": "00036ddcecad4a66bd25f5ff05517cb2a9b456233b74470d21653153e4246200", "language": "go", "prefix": "eckpointErr error\n\tfor {\n\t\tevent, ok := iter.Next()\n\t\tif !ok {\n\t\t\tbreak\n\t\t}\n\t\tevents = append(events, event)\n\t\tif event.Err != nil {\n\t\t\tcheckpointErr = event.Err\n\t\t\tt.Logf(\"event error: %v\", event.Err)\n\t\t}\n\t}\n\n\t// The bug: checkpoint save fails because the", "repo": "cloudwego/eino", "span_codepoints": 256, "start": 63445, "suffix": "failed stream's error in session\")\n\n\tvar hasInterrupt bool\n\tfor _, event := range events {\n\t\tif event.Action != nil && event.Action.Interrupted != nil {\n\t\t\thasInterrupt = true\n\t\t}\n\t}\n\tassert.True(t, hasInterrupt, \"should receive an interrupt event from the", "target": " failed stream's error chunk\n\t// is encountered during gob encoding of the session events.\n\t// If the bug is fixed, checkpointErr should be nil and we should see an interrupt event.\n\tassert.NoError(t, checkpointErr, \"checkpoint save should not fail due to "}
{"bin": "8_token_ish", "content_sha256": "35d3bac200ce605ab32a55e6d873c36bd652ca3ec57136de120b0870f450cb79", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/validation.test.ts", "end": 7003, "example_id": "00037b69df6a742b12c729fa88f43cc113c75a21f5ceb27d2ee46cb47af03afa", "language": "typescript", "prefix": "\n#### Scenario: Invalid credentials\nGiven a user with invalid credentials\nWhen they submit the login form\nThen they see an error message`;\n\n const specPath = path.join(testDir, 'spec.md');\n await fs.writeFile(specPath, specContent);\n \n ", "repo": "Fission-AI/OpenSpec", "span_codepoints": 32, "start": 6971, "suffix": ");\n const report = await validator.validateSpec(specPath);\n \n expect(report.valid).toBe(true);\n expect(report.summary.errors).toBe(0);\n });\n\n it('should detect missing overview section', async () => {\n const specContent = `# ", "target": "const validator = new Validator("}
{"bin": "64_token_ish", "content_sha256": "d84cd6b8a42ef21acf064a431e36ca1db3f3c27035b11f04a96b2abfa87b7933", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/references.test.ts", "end": 7929, "example_id": "000381cd3201cf314a8f24bdbb2b0cdde433334ca16bb7dec0a39f500f1a7f72", "language": "typescript", "prefix": "ce_root_unhealthy',\n fix: expect.stringContaining('openspec store doctor'),\n })\n );\n }\n });\n\n it('degrades every reference when the registry is unreadable', async () => {\n const registryDir = path.join(globalDataDir, 'stores');", "repo": "Fission-AI/OpenSpec", "span_codepoints": 256, "start": 7673, "suffix": "entry of entries) {\n expect(entry.status[0].code).toBe('reference_registry_unreadable');\n }\n });\n\n it('skips spec content, fetch recipes, and the budget in health mode (3.6)', async () => {\n const storeRoot = await registerStore('team-context'", "target": "\n fs.mkdirSync(registryDir, { recursive: true });\n fs.writeFileSync(path.join(registryDir, 'registry.yaml'), ':[ not yaml');\n\n const entries = await assemble(['team-context', 'other-context']);\n\n expect(entries).toHaveLength(2);\n for (const "}
{"bin": "8_token_ish", "content_sha256": "41f333c036d3e7c5d742f81da42534ef63ce6c1c25b2237145029d55248000f3", "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/image.sh", "end": 3919, "example_id": "0003859ef3a8760e7dd1e8007b867a4d840d70fe32523507f6124672a01f71e3", "language": "shell", "prefix": "_name=\"$5\"\n local -n versions_ref=\"$versions_name\"\n local -n bases_ref=\"$bases_name\"\n local -n groups_ref=\"$groups_name\"\n local -n indexes_ref=\"$indexes_name\"\n\n local count image image_index\n local display product platform\n local edition_id install_", "repo": "dockur/windows", "span_codepoints": 32, "start": 3887, "suffix": " versions_ref=()\n bases_ref=()\n groups_ref=()\n indexes_ref=()\n\n platform=$(getPlatform \"$xml\")\n count=$(xmllint --nonet --xpath 'count(/WIM/IMAGE)' - 2>/dev/null <<< \"$xml\") || return 0\n\n for ((i=1; i<=count; i++)); do\n\n image_index=$(xmllint --n", "target": "type\n local candidate flags i\n\n"}
{"bin": "8_token_ish", "content_sha256": "0ade33ba18b5de7898b0031c737185a5bc944d529b58ba3661e833f930a77ade", "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:adk/filesystem/backend_inmemory_test.go", "end": 15931, "example_id": "000385bf0813d628b475dad13d0c705e7aa26575ed21198c05ea9cd6564a2afa", "language": "go", "prefix": "] = true\n\t\t\t} else {\n\t\t\t\tt.Errorf(\"Unexpected path: %s\", info.Path)\n\t\t\t}\n\t\t}\n\n\t\tfor path, found := range expected {\n\t\t\tif !found {\n\t\t\t\tt.Errorf(\"Expected absolute path not found: %s\", path)\n\t\t\t}\n\t\t}\n\t})\n}\n\nfunc TestInMemoryBackend_Concurrent(t *testing.T) ", "repo": "cloudwego/eino", "span_codepoints": 32, "start": 15899, "suffix": "()\n\tctx := context.Background()\n\n\t// Test concurrent writes and reads\n\tdone := make(chan bool)\n\tfor i := 0; i < 10; i++ {\n\t\tgo func(n int) {\n\t\t\tbackend.Write(ctx, &WriteRequest{\n\t\t\t\tFilePath: \"/concurrent.txt\",\n\t\t\t\tContent: \"content\",\n\t\t\t})\n\t\t\tbackend.Rea", "target": "{\n\tbackend := NewInMemoryBackend"}
{"bin": "64_token_ish", "content_sha256": "fafc7dce4309aac0cdf33c8d5eb4f90a536fca6595a6ec33ae75df4e9e72f247", "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:browser_use/llm/litellm/chat.py", "end": 2513, "example_id": "0003865e59e050d90a40cec47b6954f03f72f6f62fd2570fba9077c30c1de992", "language": "python", "prefix": "one:\n\t\t\"\"\"Extract token usage from a litellm response.\"\"\"\n\t\tusage = getattr(response, 'usage', None)\n\t\tif usage is None:\n\t\t\treturn None\n\n\t\tprompt_tokens = getattr(usage, 'prompt_tokens', 0) or 0\n\t\tcompletion_tokens = getattr(usage, 'completion_tokens', 0) ", "repo": "browser-use/browser-use", "span_codepoints": 256, "start": 2257, "suffix": "_cached = getattr(details, 'cached_tokens', None)\n\n\t\treturn ChatInvokeUsage(\n\t\t\tprompt_tokens=prompt_tokens,\n\t\t\tprompt_cached_tokens=int(prompt_cached) if prompt_cached is not None else None,\n\t\t\tprompt_cache_creation_tokens=int(cache_creation) if cache_cre", "target": "or 0\n\n\t\tprompt_cached = getattr(usage, 'cache_read_input_tokens', None)\n\t\tcache_creation = getattr(usage, 'cache_creation_input_tokens', None)\n\n\t\tif prompt_cached is None:\n\t\t\tdetails = getattr(usage, 'prompt_tokens_details', None)\n\t\t\tif details:\n\t\t\t\tprompt"}
{"bin": "64_token_ish", "content_sha256": "37dea31db4757ee41e18bf6e82526d2c4e421cd01cf03ba56b2f4a0f64b26cc7", "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/pdb/pdb_parse.c", "end": 29287, "example_id": "0003887410964c8256357ef47d3797fe42fbe72bdb07c44919f6061320965254", "language": "c", "prefix": "+ 1);\n CV_NumericParsed size = cv_numeric_from_data_range(numeric_ptr, first + cap);\n \n // name\n U8 *name_ptr = numeric_ptr + size.encoded_size;\n String8 name = ", "repo": "EpicGames/raddebugger", "span_codepoints": 256, "start": 29031, "suffix": " U8 *unique_name_ptr = name_ptr + name.size + 1;\n String8 unique_name = str8_cstring_capped((char*)unique_name_ptr, (char *)(first + cap));\n extracted_name = unique_name;\n }\n ", "target": "str8_cstring_capped((char*)name_ptr, (char *)(first + cap));\n \n // unique name\n if (compare_unique_name){\n if (lf_struct->props & CV_TypeProp_HasUniqueName) {\n "}
{"bin": "64_token_ish", "content_sha256": "a618f96d7f0b1e9c887a3ca44e23f411f471845cd521c72fb41df8fef6b335fb", "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/paperreview/submit.js", "end": 2303, "example_id": "00038ffac561a70700a979f78d20760d4e1ac26acd79818b2551b91eef0243ab", "language": "javascript", "prefix": " throw new CliError('ARGUMENT', 'An email address is required.', 'Pass --email ');\n }\n if (dryRun) {\n return summarizeSubmission({\n pdfFile,\n email,\n venue,\n ", "repo": "jackwener/OpenCLI", "span_codepoints": 256, "start": 2047, "suffix": " method: 'POST',\n headers: { 'Content-Type': 'application/json' },\n body: JSON.stringify({\n filename: pdfFile.fileName,\n venue,\n }),\n });\n ensureSuccess(uploadUrlResponse, upload", "target": " message: 'Input validation passed. No remote request was sent.',\n dryRun: true,\n });\n }\n const { response: uploadUrlResponse, payload: uploadUrlPayload } = await requestJson('/api/get-upload-url', {\n "}
{"bin": "64_token_ish", "content_sha256": "484e503fcb815524b23c61ae6a3c74d86ade5f21fae906a41317ec2f8925fb88", "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/__tests__/remove.test.ts", "end": 2060, "example_id": "000396a62e33ab70da382c6e852bf5f047639eb847df0eb8f6d2afefe03ee27f", "language": "typescript", "prefix": "n(tmpdir(), `ctx7-uninstall-${Date.now()}`);\n await mkdir(tempDir, { recursive: true });\n process.chdir(tempDir);\n});\n\nafterEach(async () => {\n process.chdir(originalCwd);\n await rm(tempDir, { recursive: true, force: true });\n vi.restoreAllMocks();\n})", "repo": "upstash/context7", "span_codepoints": 256, "start": 1804, "suffix": "\", \"SKILL.md\");\n const mcpSkillPath = join(tempDir, \".cursor\", \"skills\", \"context7-mcp\", \"SKILL.md\");\n\n await mkdir(join(tempDir, \".cursor\", \"rules\"), { recursive: true });\n await mkdir(join(tempDir, \".cursor\", \"skills\", \"find-docs\"), { recursive:", "target": ";\n\ndescribe(\"remove command\", () => {\n test(\"removes only CLI artifacts for cursor project setup\", async () => {\n const rulePath = join(tempDir, \".cursor\", \"rules\", \"context7.mdc\");\n const cliSkillPath = join(tempDir, \".cursor\", \"skills\", \"find-docs"}
{"bin": "64_token_ish", "content_sha256": "f9195f442170c1d21467e69398def04e748f5bbbc5ab619c289aec8d5a9d422f", "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/yahoo/search.test.js", "end": 707, "example_id": "00039c3cfc064e44118889a3daeaad021d2be207a84547434ac8d0d2876731bf", "language": "javascript", "prefix": " goto: vi.fn().mockResolvedValue(undefined),\n wait: vi.fn().mockResolvedValue(undefined),\n evaluate: vi.fn().mockResolvedValue(evaluateResult),\n };\n}\n\ndescribe('yahoo search', () => {\n it('should register as a valid command', () => {\n expect(", "repo": "jackwener/OpenCLI", "span_codepoints": 256, "start": 451, "suffix": ").toBe('search.yahoo.com');\n });\n\n it('should define keyword positional arg', () => {\n const kwArg = command.args.find(a => a.name === 'keyword');\n expect(kwArg).toBeDefined();\n expect(kwArg.positional).toBe(true);\n expect(kwArg.required).toB", "target": "command).toBeDefined();\n expect(command.site).toBe('yahoo');\n expect(command.name).toBe('search');\n expect(command.access).toBe('read');\n expect(command.browser).toBe(true);\n expect(command.strategy).toBe('public');\n expect(command.domain"}
{"bin": "32_token_ish", "content_sha256": "9ea1b94f6304d1aed4b677b35338f932f9e29b4d712b138062c3227746209b38", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converters/_wikipedia_converter.py", "end": 1745, "example_id": "00039f8cc508b709accd7b0e3770b04b6b271c0d45c0d95ab47b3b6ebd259986", "language": "python", "prefix": "o: StreamInfo,\n **kwargs: Any, # Options to pass to the converter\n ) -> DocumentConverterResult:\n # Parse the stream\n encoding = \"utf-8\" if stream_info.charset is None else stream_info.charset\n soup = bs4.BeautifulSoup(file_", "repo": "microsoft/markitdown", "span_codepoints": 128, "start": 1617, "suffix": "\", \"style\"]):\n script.extract()\n\n # Print only the main content\n body_elm = soup.find(\"div\", {\"id\": \"mw-content-text\"})\n title_elm = soup.find(\"span\", {\"class\": \"mw-page-title-main\"})\n\n webpage_text = \"\"\n main_", "target": "stream, \"html.parser\", from_encoding=encoding)\n\n # Remove javascript and style blocks\n for script in soup([\"script"}
{"bin": "16_token_ish", "content_sha256": "20d0c254b23a5b09ef7d3c07ac1d45e381cfd1c069fdfe8a85db113539d02f3c", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/commands/store-root-selection.test.ts", "end": 3362, "example_id": "0003a8583c50fd5e78cb1c47310d91fd3df923934a8b0d7a0414dfafad693827", "language": "typescript", "prefix": "FileSync(\n path.join(changeDir, 'proposal.md'),\n '## Why\\nBilling needs work.\\n\\n## What Changes\\n- **billing:** Add billing\\n'\n );\n fs.writeFileSync(\n path.join(changeDir, 'tasks.md'),\n options.tasksDone === false ? '- [ ] Task 1", "repo": "Fission-AI/OpenSpec", "span_codepoints": 64, "start": 3298, "suffix": ") {\n const specDir = path.join(changeDir, 'specs', 'billing');\n fs.mkdirSync(specDir, { recursive: true });\n fs.writeFileSync(path.join(specDir, 'spec.md'), options.deltaSpec ?? VALID_DELTA_SPEC);\n }\n return changeDir;\n }\n\n function ", "target": "\\n' : '- [x] Task 1\\n'\n );\n if (options.deltaSpec !== null"}
{"bin": "16_token_ish", "content_sha256": "8ae91557828e8597f00437dbbb71227e676e152c94bbd03804aee6a1bcaa4987", "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/hooks/pre_commit_hooks/check_merge_conflict.rs", "end": 4387, "example_id": "0003ad4fb159b227285c08aed1f4afe4ab0691fc50394ef043edb60afc515f25", "language": "rust", "prefix": ", \"clean.txt\", content).await?;\n let (code, output) = check_file(Path::new(\"\"), &file_path).await?;\n assert_eq!(code, 0);\n assert!(output.is_empty());\n Ok(())\n }\n\n #[tokio::test]\n async fn test_conflict_marker_start() -", "repo": "j178/prek", "span_codepoints": 64, "start": 4323, "suffix": " = b\"Some content\\n<<<<<<< HEAD\\nConflicting line\\n\";\n let file_path = create_test_file(&dir, \"conflict.txt\", content).await?;\n let (code, output) = check_file(Path::new(\"\"), &file_path).await?;\n assert_eq!(code, 1);\n assert!(!o", "target": "> Result<()> {\n let dir = tempdir()?;\n let content"}
{"bin": "64_token_ish", "content_sha256": "ab7d0b795cc4c53fbc05178f67b73f0d6f93fb57cd448017f2d32470a77c9546", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/core/update.ts", "end": 9208, "example_id": "0003b0ac172bc27f840b12da3c6b27d46694b2e8987c1605fd19eb3b06c24cf3", "language": "typescript", "prefix": "t failedTools: Array<{ name: string; error: string }> = [];\n const skillsInvocableCommandSkips: string[] = [];\n let removedCommandCount = 0;\n let removedSkillCount = 0;\n let removedDeselectedCommandCount = 0;\n let removedDeselectedSkillCount", "repo": "Fission-AI/OpenSpec", "span_codepoints": 256, "start": 8952, "suffix": "join(resolvedProjectPath, tool.skillsDir, 'skills');\n const shouldGenerateSkills = shouldGenerateSkillsForTool(tool.value, delivery);\n const shouldGenerateCommands = shouldGenerateCommandsForTool(tool.value, delivery);\n const toolWorkf", "target": " = 0;\n\n for (const toolId of toolsToUpdate) {\n const tool = AI_TOOLS.find((t) => t.value === toolId);\n if (!tool?.skillsDir) continue;\n\n const spinner = ora(`Updating ${tool.name}...`).start();\n\n try {\n const skillsDir = path."}
{"bin": "64_token_ish", "content_sha256": "ab5c97cd2d97c4a83a2b8ece386dbdbb1508dd350a483fd12612262ed89cca04", "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/tools-ai-sdk/src/index.test.ts", "end": 5385, "example_id": "0003b85d9cd57f26f28dd294bfe85d55044979de06a1e397195d9e983493658c", "language": "typescript", "prefix": " instructions: \"Custom instructions for testing\",\n });\n\n expect(agent).toBeDefined();\n });\n\n test(\"should accept Context7 config options\", () => {\n const agent = new Context7Agent({\n model: bedrock(\"anthropic.claude-3-haiku", "repo": "upstash/context7", "span_codepoints": 256, "start": 5129, "suffix": "\",\n inputSchema: z.object({\n input: z.string().describe(\"Test input\"),\n }),\n execute: async ({ input }) => ({ result: `processed: ${input}` }),\n });\n\n const agent = new Context7Agent({\n model: bedrock(\"anthrop", "target": "-20240307-v1:0\"),\n apiKey: \"ctx7sk-test-key\",\n });\n\n expect(agent).toBeDefined();\n });\n\n test(\"should accept additional tools alongside Context7 tools\", () => {\n const customTool = tool({\n description: \"A custom test tool"}
{"bin": "64_token_ish", "content_sha256": "d7c5a42bb1923a79a37836f579ca57d36098a3cfe30440271ec73597e1c3d3a4", "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:examples/cloud/README.md", "end": 1647, "example_id": "0003bdaf0c8c324b263682d19d6e8a58bf4591f717bb975de2aabe58aab4e5de", "language": "markdown", "prefix": "task.py)** - Your first cloud task (start here!)\n- **[02_fast_mode_gemini.py](./02_fast_mode_gemini.py)** - ⚡ Ultra-fast mode with Gemini Flash & Fireship humor\n- **[03_structured_output.py](./03_structured_output.py)** - Get structured JSON responses\n- **", "repo": "browser-use/browser-use", "span_codepoints": 256, "start": 1391, "suffix": " execution ($0.01/step)\n2. **Disable proxy** when not needed for captcha solving\n3. **Disable element highlighting** for better performance\n4. **Set max_agent_steps** to prevent runaway costs\n5. **Use structured output** to reduce parsing overhead\n6. **Add", "target": "[04_proxy_usage.py](./04_proxy_usage.py)** - 🌍 Proxy for geo-restrictions & captcha solving\n- **[05_search_api.py](./05_search_api.py)** - 🔍 Search API for content extraction (BETA)\n\n## 💰 Cost Optimization Tips\n\n1. **Use Gemini Flash** for fastest/cheapest"}
{"bin": "16_token_ish", "content_sha256": "b898fa7d192aa35a985cd95e242dc3dbd71dd2a2b5bdf6abf0b3e17cf44a79fa", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converter_utils/docx/math/latex_dict.py", "end": 4161, "example_id": "0003c4be755d4312725250a6e0548333c10ecd724051dc11fd07cd50fedc9c07", "language": "python", "prefix": "\\gg \",\n \"\\u2208\": \"\\\\in \",\n \"\\u2209\": \"\\\\notin \",\n \"\\u220b\": \"\\\\ni \",\n \"\\u220c\": \"\\\\nni \",\n # Ordinary symbols\n \"\\u221e\": \"\\\\infty \",\n # Binary relations\n \"\\u00b1\": \"\\\\pm \",\n \"\\u2213\": \"\\\\mp \",\n # Italic, Latin, uppercase\n ", "repo": "microsoft/markitdown", "span_codepoints": 64, "start": 4097, "suffix": "\n \"\\U0001d437\": \"D\",\n \"\\U0001d438\": \"E\",\n \"\\U0001d439\": \"F\",\n \"\\U0001d43a\": \"G\",\n \"\\U0001d43b\": \"H\",\n \"\\U0001d43c\": \"I\",\n \"\\U0001d43d\": \"J\",\n \"\\U0001d43e\": \"K\",\n \"\\U0001d43f\": \"L\",\n \"\\U0001d440\": \"M\",\n \"\\U0001d441\": \"N\",\n ", "target": "\"\\U0001d434\": \"A\",\n \"\\U0001d435\": \"B\",\n \"\\U0001d436\": \"C\","}
{"bin": "8_token_ish", "content_sha256": "90368b23c0d0ca8bb0d2fc007c86100de630857bd2934d5a9254402095b039c6", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converters/_cu_converter.py", "end": 1715, "example_id": "0003cb73121da8af102315abaf505040553d18543b1974e992e017d27af48dc9", "language": "python", "prefix": "ultAzureCredential: # type: ignore[no-redef]\n pass\n\n def to_llm_input(*args, **kwargs): # type: ignore[no-redef]\n pass\n\n\n# ---------------------------------------------------------------------------\n# File type enum and routing tables\n# ", "repo": "microsoft/markitdown", "span_codepoints": 32, "start": 1683, "suffix": "-------------------------------------------\n\n\nclass ContentUnderstandingFileType(str, Enum):\n \"\"\"Supported file types for Content Understanding conversion.\"\"\"\n\n # Documents\n PDF = \"pdf\"\n DOCX = \"docx\"\n PPTX = \"pptx\"\n XLSX = \"xlsx\"\n HTM", "target": "--------------------------------"}
{"bin": "32_token_ish", "content_sha256": "b3a0c69c32b557a7b1dd00b93eb466752d5ffbc6da40065dfebc1d6d27b25795", "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/1688/download.js", "end": 994, "example_id": "0003cbf0d0916bf682380eccd07875d217c289c073072763f4610878f18cbb49", "language": "javascript", "prefix": "ssets) {\n const items = [];\n const pushImages = (urls, prefix) => {\n urls.forEach((url, index) => {\n items.push({\n type: 'image',\n url,\n filename: `${offerId}_${prefix}_${String(index + 1", "repo": "jackwener/OpenCLI", "span_codepoints": 128, "start": 866, "suffix": " pushImages(assets.sku_images, 'sku');\n pushImages(assets.detail_images, 'detail');\n pushImages(assets.other_images, 'other');\n assets.videos.forEach((url, index) => {\n items.push({\n type: 'video',\n url,\n ", "target": ").padStart(2, '0')}${extFromUrl(url, '.jpg')}`,\n });\n });\n };\n pushImages(assets.main_images, 'main');\n "}
{"bin": "64_token_ish", "content_sha256": "c7b8119f0c956a69abf4cf48d23de9667d47f54b68c51ba9fb9e3762758a81f8", "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/migrations/0_collections_snapshot_0_19_0_dev_1.go", "end": 27003, "example_id": "0003d203c75d37aea1f53d43678c181369fa01afe92f7000f46672afd6a6a695", "language": "go", "prefix": "idden\": false,\n\t\t\t\t\"id\": \"date2675529103\",\n\t\t\t\t\"max\": \"\",\n\t\t\t\t\"min\": \"\",\n\t\t\t\t\"name\": \"start\",\n\t\t\t\t\"presentable\": false,\n\t\t\t\t\"required\": true,\n\t\t\t\t\"system\": false,\n\t\t\t\t\"type\": \"date\"\n\t\t\t},\n\t\t\t{\n\t\t\t\t\"hidden\": false,\n\t\t\t\t\"id\": \"date16528305\",\n\t\t\t\t\"max\": \"\",\n\t", "repo": "henrygd/beszel", "span_codepoints": 256, "start": 26747, "suffix": "\" + ` (\\n ` + \"`\" + `user` + \"`\" + `,\\n ` + \"`\" + `system` + \"`\" + `\\n)\",\n\t\t\t\"CREATE INDEX ` + \"`\" + `idx_6T7ljT7FJd` + \"`\" + ` ON ` + \"`\" + `quiet_hours` + \"`\" + ` (\\n ` + \"`\" + `type` + \"`\" + `,\\n ` + \"`\" + `end` + \"`\" + `\\n)\"\n\t\t],\n\t\t\"listRule\": \"@re", "target": "\t\t\t\"min\": \"\",\n\t\t\t\t\"name\": \"end\",\n\t\t\t\t\"presentable\": false,\n\t\t\t\t\"required\": true,\n\t\t\t\t\"system\": false,\n\t\t\t\t\"type\": \"date\"\n\t\t\t}\n\t\t],\n\t\t\"id\": \"pbc_451525641\",\n\t\t\"indexes\": [\n\t\t\t\"CREATE INDEX ` + \"`\" + `idx_q0iKnRP9v8` + \"`\" + ` ON ` + \"`\" + `quiet_hours` + \"`"}
{"bin": "16_token_ish", "content_sha256": "a9cbe88ad1942abf948ad9f3ca3dc064f9d63ed3a0fe95cbecc794f45e2662c9", "document_id": "unitycatalog/unitycatalog@ed504deea31b30c3e7d27e360372077cce04a509:server/src/test/java/io/unitycatalog/server/utils/PopulateTestDatabase.java", "end": 13140, "example_id": "0003eb8c5c3d76ce0019103c51ad0c5aa153356c973cc23f529b9ca597e36560", "language": "java", "prefix": " .schemaId(UUID.fromString(schemaId))\n .comment(\"Partitioned table\")\n .columns(List.of(firstName, age, country))\n .dataSourceFormat(DataSourceFormat.DELTA.getValue())\n .type(TableType.EXTERNAL.getValue(", "repo": "unitycatalog/unitycatalog", "span_codepoints": 64, "start": 13076, "suffix": " Date())\n .url(partitionedTablePath)\n .build();\n\n partitionedTableInfoDAO\n .getColumns()\n .forEach(columnInfoDAO -> columnInfoDAO.setTable(partitionedTableInfoDAO));\n\n try (Session session = factory.openSession()) ", "target": "))\n .createdAt(new Date())\n .updatedAt(new"}
{"bin": "64_token_ish", "content_sha256": "8e6e4cc0362274dfdffebfe2c34dfc352377feab8251ac7c81eb3a7437fde08c", "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:examples/models/langchain/serializer.py", "end": 1093, "example_id": "0003ec88c709cd9de4a7b50a30ab28dd48bc2db4ee3185e9c20bfbc2db22da37", "language": "python", "prefix": "ge,\n)\n\n\nclass LangChainMessageSerializer:\n\t\"\"\"Serializer for converting between browser-use message types and LangChain message types.\"\"\"\n\n\t@staticmethod\n\tdef _serialize_user_content(\n\t\tcontent: str | list[ContentPartTextParam | ContentPartImageParam],\n\t) ", "repo": "browser-use/browser-use", "span_codepoints": 256, "start": 837, "suffix": "\t\t\t'type': 'text',\n\t\t\t\t\t\t'text': part.text,\n\t\t\t\t\t}\n\t\t\t\t)\n\t\t\telif part.type == 'image_url':\n\t\t\t\t# LangChain format for images\n\t\t\t\tserialized_parts.append(\n\t\t\t\t\t{'type': 'image_url', 'image_url': {'url': part.image_url.url, 'detail': part.image_url.detail}}\n", "target": "-> str | list[str | dict]:\n\t\t\"\"\"Convert user message content for LangChain compatibility.\"\"\"\n\t\tif isinstance(content, str):\n\t\t\treturn content\n\n\t\tserialized_parts = []\n\t\tfor part in content:\n\t\t\tif part.type == 'text':\n\t\t\t\tserialized_parts.append(\n\t\t\t\t\t{\n\t\t\t"}
{"bin": "32_token_ish", "content_sha256": "25bf224c95efef7f424e6fcbbe72ac1b10ff5f030c244260a0a5723be8210325", "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:tests/installer/e2e.freshinstall.test.mjs", "end": 663, "example_id": "0003f1b634b48387051e262a198b0b87ababaa049fa30e4579775aa8b7955039", "language": "javascript", "prefix": " pipeline that a dry-run can't\n// see — missing hook files, malformed settings entries, broken statusline\n// wiring, idempotency bugs, JSONC-tolerance regressions (#249-class).\n//\n// Limitations:\n// - The Claude Code provider only triggers when `claude` ", "repo": "JuliusBrussee/caveman", "span_codepoints": 128, "start": 535, "suffix": " that don't need `claude` (idempotence,\n// JSONC tolerance) always run.\n// - The installer's uninstall path also calls `claude plugin uninstall` and\n// `gemini extensions uninstall` against whatever binary is on PATH. We\n// strip those out of", "target": "is on PATH. Tests\n// that depend on it skip cleanly when missing (most CI runners and dev\n// boxes won't have it). Tests"}
{"bin": "8_token_ish", "content_sha256": "007a2f56e0b9d64cf28e4aeeb7329fb3bd818400bb88444dc92ef5537d7255b4", "document_id": "nicbarker/clay@e6cc36941ab2af5d81107617039d6f527a1c660b:renderers/cairo/clay_renderer_cairo.c", "end": 6936, "example_id": "0003fc3ab232c22c49f816eea1b46336c145a8563197dce1c06e0213cbb18e5d", "language": "c", "prefix": "nerRadius.topRight,\n\t\t\t\t\t 3 * M_PI / 2, 2 * M_PI); // 270° to 360°\n\t\t\tcairo_arc(cr, bb.x + bb.width - config->cornerRadius.bottomRight,\n\t\t\t\t\t bb.y + bb.height - config->cornerRadius.bottomRight,\n\t\t\t\t\t config->cornerRadius.bottomRight,\n\t\t\t\t\t 0, M_PI / 2", "repo": "nicbarker/clay", "span_codepoints": 32, "start": 6904, "suffix": " bb.x + config->cornerRadius.bottomLeft,\n\t\t\t\t\t bb.y + bb.height - config->cornerRadius.bottomLeft,\n\t\t\t\t\t config->cornerRadius.bottomLeft,\n\t\t\t\t\t M_PI / 2, M_PI); // 90° to 180°\n\t\t\tcairo_close_path(cr);\n\n\t\t\tcairo_fill(cr);\n\t\t\tbreak;\n\t\t}\n\t\tcase CLAY_RENDER", "target": "); // 0° to 90°\n\t\t\tcairo_arc(cr,"}
{"bin": "16_token_ish", "content_sha256": "549bf14217ca8076437fa391ef117efe215ebcad0268561dc85bc6ec4f7d19cd", "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:tests/providers/deepseek/request_hook.rs", "end": 3165, "example_id": "0003feee366c0429f53467104a1385bed4e8dfdff8aa7cbc7950b4f4dba559dd", "language": "rust", "prefix": " response_calls: Arc::new(AtomicUsize::new(0)),\n seen_prompt: Arc::new(Mutex::new(None)),\n seen_response: Arc::new(Mutex::new(None)),\n };\n\n let response = agent.prompt(\"Entertain me!\").add_", "repo": "0xPlaygrounds/rig", "span_codepoints": 64, "start": 3101, "suffix": "(&response);\n anyhow::ensure!(\n hook.prompt_calls.load(Ordering::SeqCst) == 1,\n \"expected one prompt hook call\"\n );\n anyhow::ensure!(\n hook.response_calls.load(Ordering::SeqCst) ", "target": "hook(hook.clone()).await?;\n\n assert_nonempty_response"}
{"bin": "8_token_ish", "content_sha256": "a5ea4191118ce5a1c0609ea738431ae64550706fa92f4f28b6eb86124a16c5bb", "document_id": "modelcontextprotocol/java-sdk@fd004989b9484c9b81be6b03463396797b354804:mcp-core/src/main/java/io/modelcontextprotocol/client/transport/ServerParameters.java", "end": 2814, "example_id": "00040195831689dcdf90fbdb32b5b21af646d1f3c8fcec161ce16746198e8d4e", "language": "java", "prefix": "env.putAll(env);\n\t\t\t}\n\t\t\treturn this;\n\t\t}\n\n\t\tpublic Builder addEnvVar(String key, String value) {\n\t\t\tAssert.notNull(key, \"The key can not be null\");\n\t\t\tAssert.notNull(value, \"The value can not be null\");\n\t\t\tthis.env.put(key, value);\n\t\t\treturn this;\n\t\t}\n\n\t\t", "repo": "modelcontextprotocol/java-sdk", "span_codepoints": 32, "start": 2782, "suffix": "{\n\t\t\treturn new ServerParameters(command, args, env);\n\t\t}\n\n\t}\n\n\t/**\n\t * Returns a default environment object including only environment variables deemed\n\t * safe to inherit.\n\t */\n\tprivate static Map getDefaultEnvironment() {\n\t\treturn System", "target": "public ServerParameters build() "}
{"bin": "64_token_ish", "content_sha256": "351fad53d9e0661c25cd3b4e6d9b3a6f281b9bad45046ce3e7c67d425c4421d3", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_module_misc.py", "end": 9133, "example_id": "0004138d4eb28a06b336c1be17747043a50e6f446a53a1018e759530bbfb4ccd", "language": "python", "prefix": "?param=value\"\n netloc, path = file_uri_to_path(file_uri)\n assert netloc is None\n assert path == \"/path/to/file.txt\"\n\n # Test file URI with fragment\n file_uri = \"file:///path/to/file.txt#fragment\"\n netloc, path = file_uri_to_path(file_uri)", "repo": "microsoft/markitdown", "span_codepoints": 256, "start": 8877, "suffix": "result = markitdown_with_style_map.convert(\n os.path.join(TEST_FILES_DIR, \"test_with_comment.docx\")\n )\n validate_strings(result, DOCX_COMMENT_TEST_STRINGS)\n\n\ndef test_docx_equations() -> None:\n markitdown = MarkItDown()\n docx_file = os.p", "target": "\n assert netloc is None\n assert path == \"/path/to/file.txt\"\n\n\ndef test_docx_comments() -> None:\n # Test DOCX processing, with comments and setting style_map on init\n markitdown_with_style_map = MarkItDown(style_map=\"comment-reference => \")\n "}
{"bin": "32_token_ish", "content_sha256": "f27ac893dc3f6befb569083a96dc3001948855d41eaed82b8cdb1c5ec633c10c", "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/dwarf/dwarf_expr.c", "end": 15642, "example_id": "0004193e2fe742326627624c5debae436d1bd17c84b9ddd14bb68ae2c9d52b3a", "language": "c", "prefix": "1);\n }\n n->v = push_vals[push_idx];\n SLLStackPush(state->top_val, n);\n }\n }\n \n //- rjf: do not need a break? advance state.\n //\n // (if we *do* need a break, this means we need to ask the caller for\n // more info", "repo": "EpicGames/raddebugger", "span_codepoints": 128, "start": 15514, "suffix": "\n state->op_idx += 1;\n state->off = off;\n }\n \n //- rjf: at the end of the expression? -> set success, fill result\n if(off == expr.size)\n {\n result.status = DW_EvalStatus_Good;\n if(state->top_val != 0)\n {\n resu", "target": ", like memory reads, and so we want to resume from the\n // offset just before this opcode)\n //\n if(!need_a_break)\n {"}
{"bin": "16_token_ish", "content_sha256": "e6ff121105322d4915f1e730b2fabdd4e83031022c24eb8c82da405412e47089", "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:tests/test_repo_local_config.js", "end": 1655, "example_id": "000421d7b349169e2023f906ddf9aa98a9d964a1d5ba71961d01ecc55aeae4d3", "language": "javascript", "prefix": "defined) delete process.env.CAVEMAN_DEFAULT_MODE;\n else process.env.CAVEMAN_DEFAULT_MODE = origEnv;\n fs.rmSync(tmpBase, { recursive: true, force: true });\n }\n}\n\nconsole.log('repo-local config resolution tests\\n');\n\ntest('returns \"full\" when no env, ", "repo": "JuliusBrussee/caveman", "span_codepoints": 64, "start": 1591, "suffix": ";\n assert.strictEqual(getDefaultMode(), 'full');\n});\n\ntest('reads .caveman/config.json in cwd', (tmp) => {\n fs.mkdirSync(path.join(tmp, '.caveman'));\n fs.writeFileSync(path.join(tmp, '.caveman', 'config.json'),\n JSON.stringify({ defaultMode: 'lite' }", "target": "no repo config, no user config', (tmp) => {\n process.chdir(tmp)"}
{"bin": "16_token_ish", "content_sha256": "9efd8c49e5b4bf7132f59fb450ea26db8ef4b27ada37df95ae1e1761fd8231d0", "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/core/shell.py", "end": 26617, "example_id": "000422773d5249ae58449ff6db5e6b4b06405fc979e10be626388f417046b5ad", "language": "python", "prefix": " if not page or not isinstance(page, Selector): # pragma: no cover\n raise TypeError(\"Input must be of type `Selector`\")\n elif not filename or not isinstance(filename, str) or not filename.strip():\n raise ValueError(\"Filename ", "repo": "D4Vinci/Scrapling", "span_codepoints": 64, "start": 26553, "suffix": "html\", \".txt\")):\n raise ValueError(\"Unknown file type: filename must end with '.md', '.html', or '.txt'\")\n else:\n with open(filename, \"w\", encoding=page.encoding) as f:\n extension = filename.split(\".\")[-1]\n ", "target": "must be provided\")\n elif not filename.endswith((\".md\", \"."}
{"bin": "64_token_ish", "content_sha256": "a2aed2930510f336d4c741954ba889652e6d51fa7896e117c1928cc2f08be559", "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/languages/python/uv.rs", "end": 16274, "example_id": "00042bac61dbb73839ca4f220fc6e7dcb390154de30bc673f73a1ce38fd2ea94", "language": "rust", "prefix": " }\n })\n .collect::>();\n\n while let Some(result) = tasks.join_next().await {\n if let Ok((source, response)) = result {\n if let Ok(resp) = response\n ", "repo": "j178/prek", "span_codepoints": 256, "start": 16018, "suffix": "select! {\n Ok(true) = check_github() => InstallSource::GitHub,\n Ok(source) = select_best_pypi() => InstallSource::PyPi(source),\n else => {\n warn!(\"Failed to check uv source availability, falli", "target": " && resp.status().is_success()\n {\n best = source;\n break;\n }\n }\n }\n\n Ok(best)\n }\n\n let source = tokio::"}
{"bin": "16_token_ish", "content_sha256": "fcf067fceb8e3428fdac592012b5de635307730e203700ca40e6347925a555a9", "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:async-book/src/ch12-common-pitfalls.md", "end": 7092, "example_id": "00042e1195181a21d74f9e4089ab1c5e3daf6c41987f8920b7df8bd56aef0ab5", "language": "markdown", "prefix": " tokio::spawn(async move {\n let _ = conn.shutdown().await;\n });\n\n // ✅ Workaround 2: Use a synchronous close\n // self.connection.blocking_close();\n }\n}\n```\n\n**Best practice**: Provide an explicit `async fn close(self)", "repo": "microsoft/RustTraining", "span_codepoints": 64, "start": 7028, "suffix": " only as a safety net, not the primary cleanup path.\n\n### select! Fairness and Starvation\n\n```rust\nuse tokio::sync::mpsc;\n\n// ❌ UNFAIR: busy_stream always wins, slow_stream starves\nasync fn unfair(mut fast: mpsc::Receiver, mut slow: mpsc::Receiver Result<()> {\n let dir = tempdir()?;\n let file_path = create_test_file(&dir, \"invalid_name.xml\", b\"<1root/>\").await?;\n let (code, output) = ", "repo": "j178/prek", "span_codepoints": 32, "start": 6907, "suffix": "path).await?;\n assert_eq!(code, 1);\n assert!(!output.is_empty());\n Ok(())\n }\n\n #[tokio::test]\n async fn test_valid_xml_with_cdata() -> Result<()> {\n let dir = tempdir()?;\n let content = br#\" anyhow::Result<()> {\n let temp = TempDir::new()?;\n let dir_path = temp.path().join(\"non-existent\");\n\n let stats = remove_dir_all(&dir_path, None)?;\n assert_eq!(stats.num_files, 0);\n assert_eq!(", "target": "::NotADirectory);\n assert!(file_path.exists(), \"file must not be deleted\");\n\n Ok(())\n }\n\n #[test]\n fn rm_"}
{"bin": "64_token_ish", "content_sha256": "40d218b913bdf11f10a2906adf24bb1815076e549923d62c67b7a1dcb94e0ab6", "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:c-cpp-book/src/ch05-data-structures.md", "end": 16634, "example_id": "0004388037d55d0c4d4f0d2e75ed50ff44d80963ea8c04e37d33c278b8f2cad3", "language": "markdown", "prefix": "ve |\n| `T&&` (rvalue ref) | Just `T` | Take by value = take ownership |\n| `T&&` in template (universal ref) | `impl Trait` or `` | Generics replace forwarding |\n| `std::move(x)` | `x` (just use it) | Move is the default |\n| `std::forward(x)` |", "repo": "microsoft/RustTraining", "span_codepoints": 256, "start": 16378, "suffix": "and the source is invalidated:\n\n```rust\n// Rust move = memcpy the bytes, mark source as invalid\nlet s1 = String::from(\"hello\");\nlet s2 = s1; // Bytes of s1 are copied to s2's stack slot\n // s1 is now invalid — compiler enforces this\n// println", "target": " No equivalent needed | No universal references to forward |\n\n#### 2. Moves Are Bitwise — No Move Constructors\n\nIn C++, moving is a *user-defined operation* (move constructor / move assignment). In Rust, moving is always a **bitwise memcpy** of the value, "}
{"bin": "8_token_ish", "content_sha256": "adc07f2bdb51d6295fbb6f069a335988a232ba76ede6fb7c4480d2e9843bf878", "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:tests/providers/llamacpp/structured_output.rs", "end": 3308, "example_id": "00043f62d0ad359dc6873f252de756d17db5ac140feace875f2408bb7b024a97", "language": "rust", "prefix": "nded_details_structured_output() {\n let client = support::completions_client();\n let model = support::model_name();\n let agent = client\n .agent(model)\n .preamble(WEATHER_PREAMBLE)\n .temperature(0.0)\n .build();\n\n let ", "repo": "0xPlaygrounds/rig", "span_codepoints": 32, "start": 3276, "suffix": "_typed::(\n \"Return JSON weather data for Los Angeles with fields city, current.temperature_f, current.humidity_pct, and current.description.\",\n )\n .extended_details()\n .await\n .expect(\"extended prompt", "target": "extended = agent\n .prompt"}
{"bin": "8_token_ish", "content_sha256": "2e2ac2e045c91407dda7722c34239b8afed22ac27509acbde53b9ec4035d5a1c", "document_id": "modelcontextprotocol/java-sdk@fd004989b9484c9b81be6b03463396797b354804:mcp-test/src/test/java/io/modelcontextprotocol/server/ResourceSubscriptionTests.java", "end": 4759, "example_id": "000444932177651fc324537dfa2509feb6b3a6441860970184cecc0a96b0979b", "language": "java", "prefix": "tification());\n\t\ttransportProvider.simulateIncomingMessage(subscribeRequest(RESOURCE_URI));\n\t\ttransport.clearSentMessages();\n\n\t\tStepVerifier\n\t\t\t.create(server.notifyResourcesUpdated(new McpSchema.ResourcesUpdatedNotification(\"test://other/resource\")))\n\t\t\t.", "repo": "modelcontextprotocol/java-sdk", "span_codepoints": 32, "start": 4727, "suffix": "transport.getAllSentMessages())\n\t\t\t.as(\"notification for a different URI should not reach a session subscribed to a different URI\")\n\t\t\t.isEmpty();\n\n\t\tserver.closeGracefully().block();\n\t}\n\n\t@Test\n\tvoid notifyResourcesUpdated_afterUnsubscribe_doesNotNotifySe", "target": "verifyComplete();\n\n\t\tassertThat("}
{"bin": "64_token_ish", "content_sha256": "1e2203cf7d3137221a7ff2d1b79d5405580eea2ce4c22ba916dbeb9c689e96be", "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:tests/test-unit.c", "end": 47185, "example_id": "00044683822fc4d3fd38da672e2169989e266cf032c92d12ad739e5ae0968949", "language": "c", "prefix": "NN(NEIGHBOR_QUANTIZER=BINARY)\";\n rc = vec0_parse_vector_column(input, (int)strlen(input), &col);\n assert(rc == SQLITE_OK);\n assert(col.index_type == VEC0_INDEX_TYPE_DISKANN);\n assert(col.diskann.quantizer_type == VEC0_DISKANN_QUANTIZER_BINARY);", "repo": "asg017/sqlite-vec", "span_codepoints": 256, "start": 46929, "suffix": "_column(input, (int)strlen(input), &col);\n assert(rc == SQLITE_OK);\n assert(col.diskann.search_list_size == 128); // default (unified)\n assert(col.diskann.search_list_size_search == 256);\n assert(col.diskann.search_list_size_insert == 64);\n ", "target": "\n sqlite3_free(col.name);\n }\n\n // Split search_list_size: search and insert\n {\n const char *input = \"emb float[128] INDEXED BY diskann(neighbor_quantizer=binary, search_list_size_search=256, search_list_size_insert=64)\";\n rc = vec0_parse_vector"}
{"bin": "32_token_ish", "content_sha256": "c84154be2a7e8cb5c0b350485417005c4865b86870578e24f3b773b5a82c97d3", "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/cli/install.rs", "end": 15354, "example_id": "000452f83f92433d367746ac6806f44a784ff1d81982edb99308f98ff7153739", "language": "rust", "prefix": " printer.stderr(),\n \"`{}` is not managed by prek, skipping.\",\n hook_path.user_display().cyan()\n )?;\n }\n continue;\n }\n ", "repo": "j178/prek", "span_codepoints": 128, "start": 15226, "suffix": " printer.stderr(),\n \"`{}` does not exist, skipping.\",\n hook_path.user_display().cyan()\n )?;\n }\n continue;\n }\n Err(err) => return", "target": "Err(err) if err.kind() == std::io::ErrorKind::NotFound => {\n if !all {\n writeln!(\n "}
{"bin": "64_token_ish", "content_sha256": "90368b23c0d0ca8bb0d2fc007c86100de630857bd2934d5a9254402095b039c6", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converters/_cu_converter.py", "end": 15375, "example_id": "00045c4c7d23bc6106d0d370ab78c8615baacab02849fbd261b75862a85fd6a1", "language": "python", "prefix": "file_modality in {\"document\", \"image\"}\n return file_modality == analyzer_modality\n\n\n# ---------------------------------------------------------------------------\n# Converter\n# ---------------------------------------------------------------------------\n\n", "repo": "microsoft/markitdown", "span_codepoints": 256, "start": 15119, "suffix": " def __init__(\n self,\n *,\n endpoint: str,\n credential: AzureKeyCredential | TokenCredential | None = None,\n analyzer_id: Optional[str] = None,\n file_types: Optional[List[ContentUnderstandingFileType]] = None,\n ", "target": "\nclass ContentUnderstandingConverter(DocumentConverter):\n \"\"\"Converts files using Azure Content Understanding.\n\n Provides high-quality document, image, audio, and video conversion\n with structured field extraction via YAML front matter.\n \"\"\"\n\n "}
{"bin": "16_token_ish", "content_sha256": "007a2f56e0b9d64cf28e4aeeb7329fb3bd818400bb88444dc92ef5537d7255b4", "document_id": "nicbarker/clay@e6cc36941ab2af5d81107617039d6f527a1c660b:renderers/cairo/clay_renderer_cairo.c", "end": 7908, "example_id": "00046741971bbe0ff214831921ac80b2049111635f9d22d02c9c5dc68d71977c", "language": "c", "prefix": "e(&toTerminate);\n\t\t\tchar *font_family = fonts[config->fontId];\n\n\t\t\tClay_BoundingBox bb = command->boundingBox;\n\t\t\tClay_Color color = config->textColor;\n\n\t\t\tcairo_select_font_face(Clay__Cairo, font_family, CAIRO_FONT_SLANT_NORMAL, CAIRO_FONT_WEIGHT_NORMAL);", "repo": "nicbarker/clay", "span_codepoints": 64, "start": 7844, "suffix": "(cr, bb.x, bb.y + bb.height);\n\n\t\t\tcairo_set_source_rgba(cr, CLAY_TO_CAIRO(color));\n\t\t\tcairo_show_text(cr, text);\n\t\t\tcairo_close_path(cr);\n\n\t\t\tfree(text);\n\t\t\tbreak;\n\t\t}\n\t\tcase CLAY_RENDER_COMMAND_TYPE_BORDER: {\n Clay_BorderRenderData *config = &c", "target": "\n\t\t\tcairo_set_font_size(cr, config->fontSize);\n\n\t\t\tcairo_move_to"}
{"bin": "16_token_ish", "content_sha256": "9211ddd2687ba04a75c6c19f9896bbd1e62343d3d738e093f5241119da405645", "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/browser/test_tabs.py", "end": 16155, "example_id": "0004727d450046fd2560c922571ade543d154709864325ba613b42e3362086bf", "language": "python", "prefix": "home page\",\n\t\t\t\t\"evaluation_previous_goal\": \"Starting task\",\n\t\t\t\t\"memory\": \"Navigating to home page\",\n\t\t\t\t\"next_goal\": \"Navigate to home page\",\n\t\t\t\t\"action\": [\n\t\t\t\t\t{{\n\t\t\t\t\t\t\"navigate\": {{\n\t\t\t\t\t\t\t\"url\": \"{base_url}/home\",\n\t\t\t\t\t\t\t\"new_tab\": false\n\t\t\t\t\t\t}}\n\t", "repo": "browser-use/browser-use", "span_codepoints": 64, "start": 16091, "suffix": "\t\t\tf\"\"\"\n\t\t\t{{\n\t\t\t\t\"thinking\": \"Opening page 1 in new tab\",\n\t\t\t\t\"evaluation_previous_goal\": \"Home page loaded\",\n\t\t\t\t\"memory\": \"Opening page 1\",\n\t\t\t\t\"next_goal\": \"Open page 1\",\n\t\t\t\t\"action\": [\n\t\t\t\t\t{{\n\t\t\t\t\t\t\"navigate\": {{\n\t\t\t\t\t\t\t\"url\": \"{base_url}/page1\",\n\t\t", "target": "\t\t\t\t}}\n\t\t\t\t]\n\t\t\t}}\n\t\t\t\"\"\",\n\t\t\t# Action 2: Open page1 in new tab\n"}
{"bin": "8_token_ish", "content_sha256": "bdd3c89b8a1c3e224ddd424546129eee3c8a1e96087431cc06ff70948fbb8082", "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/cli/test_cli.py", "end": 9113, "example_id": "0004740a6d28e42a0774b78e26e4685bee5686f6dde2f51b0c6c03f4ae1d0a50", "language": "python", "prefix": "\n\n with patch(\"scrapling.fetchers.StealthyFetcher.fetch\") as mock_fetch:\n mock_fetch.return_value = configure_selector_mock()\n\n result = runner.invoke(\n stealthy_fetch, [html_url, str(output_file), \"--executable-", "repo": "D4Vinci/Scrapling", "span_codepoints": 32, "start": 9081, "suffix": " )\n assert result.exit_code == 0\n assert mock_fetch.call_args.kwargs[\"executable_path\"] == \"/opt/custom-chromium\"\n\n monkeypatch.setenv(\"SCRAPLING_EXECUTABLE_PATH\", \"/opt/env-chromium\")\n with patch(\"scrapling.fe", "target": "path\", \"/opt/custom-chromium\"]\n "}
{"bin": "16_token_ish", "content_sha256": "3f0e691dc253a9f329dc0a630983dc2ea5bc1c1f9814d71ea50a66c7451a0dd2", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/_markitdown.py", "end": 18409, "example_id": "00047c88785b69886b75b241b6db2d08098a8ea8c6face99a38991007472ff1b", "language": "python", "prefix": " a content-type header, get the mimetype and charset (if present)\n mimetype: Optional[str] = None\n charset: Optional[str] = None\n\n if \"content-type\" in response.headers:\n parts = response.headers[\"content-type\"].split(\";\")\n ", "repo": "microsoft/markitdown", "span_codepoints": 64, "start": 18345, "suffix": "in parts:\n if part.strip().startswith(\"charset=\"):\n _charset = part.split(\"=\")[1].strip()\n if len(_charset) > 0:\n charset = _charset\n\n # If there is a content-disposition he", "target": " mimetype = parts.pop(0).strip()\n for part "}
{"bin": "32_token_ish", "content_sha256": "82dc30e0c9cd672a324b6d0d1a5f44c4a823908593ee65406431f975b93d4297", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converter_utils/docx/math/omml.py", "end": 2671, "example_id": "00048027f1ae5d33124b526cb27442312178c29d26b5463092b917b8f84b0e0f", "language": "python", "prefix": "of the elm,return dict\n \"\"\"\n latex_chars = dict()\n for stag, t, e in self.process_children_list(elm, include):\n latex_chars[stag] = t\n return latex_chars\n\n def process_children(self, elm, include=None):\n \"\"\"", "repo": "microsoft/markitdown", "span_codepoints": 128, "start": 2543, "suffix": " isinstance(t, Tag2Method) else str(t)\n for stag, t, e in self.process_children_list(elm, include)\n )\n )\n\n def process_unknow(self, elm, stag):\n return None\n\n\nclass Pr(Tag2Method):\n text = \"\"\n\n __val_tags = ", "target": "\n process children of the elm,return string\n \"\"\"\n return BLANK.join(\n (\n t if not"}
{"bin": "64_token_ish", "content_sha256": "5997502d65e6d8b077a92f6efab4879ebc35c78e1ad8ba8bfd5ea52e9de5f294", "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:src/mcp-servers/caveman-shrink/compress.js", "end": 3760, "example_id": "0004874105eedf22bac23be6e0b3338a8c7fedbaad9361c91896c3639e0a1cb5", "language": "javascript", "prefix": "AX_RESTORE_PASSES; pass++) {\n sentinel.lastIndex = 0;\n if (!sentinel.test(out)) break;\n out = out.replace(/\u0000(\\d+)\u0000/g, (_, i) => segments[+i]);\n }\n return out;\n}\n\nfunction compressProse(text) {\n let s = text;\n s = s.replace(LEADERS, '');\n s = ", "repo": "JuliusBrussee/caveman", "span_codepoints": 256, "start": 3504, "suffix": "s = s.replace(/\\n{3,}/g, '\\n\\n');\n // Capitalize the first letter of each sentence we may have left lowercase.\n s = s.replace(/(^|[.!?]\\s+)([a-z])/g, (_, pre, ch) => pre + ch.toUpperCase());\n return s.trim();\n}\n\nfunction compress(text, _opts) {\n if (ty", "target": "s.replace(PLEASANTRIES, '');\n s = s.replace(HEDGES, '');\n s = s.replace(FILLERS, '');\n s = s.replace(ARTICLES, '');\n // Collapse repeated whitespace introduced by removals.\n s = s.replace(/[ \\t]{2,}/g, ' ');\n s = s.replace(/\\s+([,.;:!?])/g, '$1');\n "}
{"bin": "64_token_ish", "content_sha256": "8431c3887cbca17a42deac1ca6b992cd80dcaeac0bdccff6a9b6f1def2926638", "document_id": "TecharoHQ/anubis@34badc646c39af3d9f1f70757474b141316f23ad:lib/config/expressionorlist_test.go", "end": 2191, "example_id": "000489ec544103392c2425db15748158c27d5ce48d301c701a762dc2a10ccb0b", "language": "go", "prefix": "ame: \"all\",\n\t\t\tinput: &ExpressionOrList{\n\t\t\t\tAll: []string{\"true\", \"true\"},\n\t\t\t},\n\t\t\toutput: []byte(`all:\n - \"true\"\n - \"true\"`),\n\t\t\terr: nil,\n\t\t},\n\t\t{\n\t\t\tname: \"all one\",\n\t\t\tinput: &ExpressionOrList{\n\t\t\t\tAll: []string{\"true\"},\n\t\t\t},\n\t\t\toutput: []byte", "repo": "TecharoHQ/anubis", "span_codepoints": 256, "start": 1935, "suffix": ": []string{\"true\"},\n\t\t\t},\n\t\t\toutput: []byte(`\"true\"`),\n\t\t\terr: nil,\n\t\t},\n\t} {\n\t\tt.Run(tt.name, func(t *testing.T) {\n\t\t\tresult, err := yaml.Marshal(tt.input)\n\t\t\tif !errors.Is(err, tt.err) {\n\t\t\t\tt.Errorf(\"wanted marshal error: %v but got: %v\", tt.err, err", "target": "(`\"true\"`),\n\t\t\terr: nil,\n\t\t},\n\t\t{\n\t\t\tname: \"any\",\n\t\t\tinput: &ExpressionOrList{\n\t\t\t\tAny: []string{\"true\", \"false\"},\n\t\t\t},\n\t\t\toutput: []byte(`any:\n - \"true\"\n - \"false\"`),\n\t\t\terr: nil,\n\t\t},\n\t\t{\n\t\t\tname: \"any one\",\n\t\t\tinput: &ExpressionOrList{\n\t\t\t\tAny"}
{"bin": "32_token_ish", "content_sha256": "a497dee4dafc4abf3240125d7c0de66f8773905518ca138257a2987dd64837dd", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_cu_converter.py", "end": 25258, "example_id": "0004a5a5a4a4269e9311b57df461fcca14b585d6afbf613f1a2e42f3ebe3b9c0", "language": "python", "prefix": "es(self):\n assert _get_modality(ContentUnderstandingFileType.MP4) == \"video\"\n assert _get_modality(ContentUnderstandingFileType.MOV) == \"video\"\n\n def test_audio_types(self):\n assert _get_modality(ContentUnderstandingFileType.WAV) ==", "repo": "microsoft/markitdown", "span_codepoints": 128, "start": 25130, "suffix": "----------------------------------\n# convert() mock tests\n# ---------------------------------------------------------------------------\n\n\nclass TestConvertMock:\n \"\"\"Test convert() with mocked CU SDK.\"\"\"\n\n def _run_convert(self, extension, mimetype, e", "target": " \"audio\"\n assert _get_modality(ContentUnderstandingFileType.MP3) == \"audio\"\n\n\n# -----------------------------------------"}
{"bin": "8_token_ish", "content_sha256": "a4cb101371d1dc25246d0a71f0c6e85ec2291d0c3c9fa0a9dbaf267bc5f38914", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py", "end": 8210, "example_id": "0004bf3a05e04bd404a6d77fa8617d0b79e44385bbc73cac0ce5c649fb91994a", "language": "python", "prefix": "tle:\n md += f\": {chart.chart_title.text_frame.text}\"\n md += \"\\\\n\\\\n\"\n data = []\n category_names = [c.label for c in chart.plots[0].categories]\n series_names = [s.name for s in chart.series]\n ", "repo": "microsoft/markitdown", "span_codepoints": 32, "start": 8178, "suffix": "series_names)\n\n for idx, category in enumerate(category_names):\n row = [category]\n for series in chart.series:\n row.append(series.values[idx])\n data.append(row)\n\n markdow", "target": " data.append([\"Category\"] + "}
{"bin": "8_token_ish", "content_sha256": "b0c2e7dbc7a768fb843fb80037bde82e6746cf7c4017e1c801f828cf827a45cc", "document_id": "modelcontextprotocol/java-sdk@fd004989b9484c9b81be6b03463396797b354804:mcp-test/src/main/java/io/modelcontextprotocol/client/AbstractMcpAsyncClientTests.java", "end": 11802, "example_id": "0004c05064673125339f1f9a14e7ebe32e7584906d77499ba55a0eb06854e3d6", "language": "java", "prefix": "AGE)))\n\t\t\t\t.consumeNextWith(resources -> {\n\t\t\t\t\tassertThat(resources).isNotNull().satisfies(result -> {\n\t\t\t\t\t\tassertThat(result.resources()).isNotNull();\n\n\t\t\t\t\t\tif (!result.resources().isEmpty()) {\n\t\t\t\t\t\t\tResource firstResource = result.resources().get(0);", "repo": "modelcontextprotocol/java-sdk", "span_codepoints": 32, "start": 11770, "suffix": ".uri()).isNotNull();\n\t\t\t\t\t\t\tassertThat(firstResource.name()).isNotNull();\n\t\t\t\t\t\t}\n\t\t\t\t\t});\n\t\t\t\t})\n\t\t\t\t.verifyComplete();\n\t\t});\n\t}\n\n\t@Test\n\tvoid testListAllResources() {\n\t\twithClient(createMcpTransport(), mcpAsyncClient -> {\n\t\t\tStepVerifier.create(mcpAsyncC", "target": "\n\t\t\t\t\t\t\tassertThat(firstResource"}
{"bin": "32_token_ish", "content_sha256": "4c97ba0ad9cd26c9138e513afc2a2a9fcd0179cac1ccf754be8b9ef5c673f525", "document_id": "DietrichGebert/ponytail@16f29800fd2681bdf24f3eb4ccffe38be3baec6b:pi-extension/test/helpers.test.js", "end": 5591, "example_id": "0004c88314799aacfd5e5aaf9a76e3341febf952d33c21f23869b9d8ca21e3e7", "language": "javascript", "prefix": "sert.ok(filtered.includes(\"Other line\"));\n});\n\ntest(\"filterSkillBodyForMode does not drop a rule bullet whose label matches a mode name\", () => {\n // A rule bullet like \"- Full: ...\" has the same \"label: text\" shape as a\n // worked example, but isn't one", "repo": "DietrichGebert/ponytail", "span_codepoints": 128, "start": 5463, "suffix": " `- Full: do not confuse this rule label with the mode name.\\n- Lite: same risk, this is a real rule bullet.\\n- lite: \"real worked example\"\\n- ultra: \"real worked example\"`;\n\n const filtered = filterSkillBodyForMode(body, \"ultra\");\n\n assert.ok(filtered.i", "target": " — it must survive in every mode. Only the\n // quoted, `- lite: \"...\"`-style bullets are real per-mode examples.\n const body ="}
{"bin": "32_token_ish", "content_sha256": "8e6e4cc0362274dfdffebfe2c34dfc352377feab8251ac7c81eb3a7437fde08c", "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:examples/models/langchain/serializer.py", "end": 868, "example_id": "0004cbb6c8168326f620ca3776b60e198eff3e7dc898def0d0cda743649696c6", "language": "python", "prefix": "l,\n\tUserMessage,\n)\nfrom browser_use.llm.messages import (\n\tSystemMessage as BrowserUseSystemMessage,\n)\n\n\nclass LangChainMessageSerializer:\n\t\"\"\"Serializer for converting between browser-use message types and LangChain message types.\"\"\"\n\n\t@staticmethod\n\tdef ", "repo": "browser-use/browser-use", "span_codepoints": 128, "start": 740, "suffix": "\"Convert user message content for LangChain compatibility.\"\"\"\n\t\tif isinstance(content, str):\n\t\t\treturn content\n\n\t\tserialized_parts = []\n\t\tfor part in content:\n\t\t\tif part.type == 'text':\n\t\t\t\tserialized_parts.append(\n\t\t\t\t\t{\n\t\t\t\t\t\t'type': 'text',\n\t\t\t\t\t\t'text'", "target": "_serialize_user_content(\n\t\tcontent: str | list[ContentPartTextParam | ContentPartImageParam],\n\t) -> str | list[str | dict]:\n\t\t\"\""}
{"bin": "64_token_ish", "content_sha256": "7e4ac7074d0ac6faa1be629b5e4866a53f4ef03be33239de567338dd8dcffb53", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_pdf_tables.py", "end": 38692, "example_id": "0004cff34317bc239e9a4eff3ef343e98fa71972ebdd977f333d4de8a49a9383", "language": "python", "prefix": " def test_markdown_table_columns_have_pipes(self, markitdown):\n \"\"\"Test that form-style PDF columns are separated with pipes.\"\"\"\n pdf_path = os.path.join(\n TEST_FILES_DIR, \"SPARSE-2024-INV-1234_borderless_table.pdf\"\n )\n\n ", "repo": "microsoft/markitdown", "span_codepoints": 256, "start": 38436, "suffix": " = text_content.split(\"\\n\")\n table_rows = [\n line for line in lines if line.startswith(\"|\") and line.endswith(\"|\")\n ]\n\n assert len(table_rows) > 0, \"Should have markdown table rows\"\n\n # Check that at least some rows h", "target": " if not os.path.exists(pdf_path):\n pytest.skip(f\"Test file not found: {pdf_path}\")\n\n result = markitdown.convert(pdf_path)\n text_content = result.text_content\n\n # Find table rows and verify column structure\n lines"}
{"bin": "64_token_ish", "content_sha256": "e7540a86fc80cdd3b0f6c7a332f60b360569342270ce3dd7ec204f7370e5a784", "document_id": "DietrichGebert/ponytail@16f29800fd2681bdf24f3eb4ccffe38be3baec6b:scripts/check-rule-copies.js", "end": 2204, "example_id": "0004d06263b6a0d9f99fd616a1076fcc7fa6fb06e7c5514912dbe34d49412a01", "language": "javascript", "prefix": "ve heuristic', // ceiling-comment rule\n 'ONE runnable check', // test reflex\n 'flimsier algorithm', // robust-variant rule\n // the four \"not lazy about\" safety carve-outs: pin each so a reword ", "repo": "DietrichGebert/ponytail", "span_codepoints": 256, "start": 1948, "suffix": " 'input validation at trust boundaries',\n 'prevents data loss',\n 'security',\n 'accessibility',\n 'Lazy code without its check is unfinished', // one-check promoted to headline\n];\n\nconst skill = read('skills/ponytail/SKILL.md');\nconst sources = [['skills", "target": "in either\n // file can't silently drop one. Only validation was pinned before. These are the\n // continuous substrings present in both files (\"prevents data loss\" because the\n // full \"error handling that prevents data loss\" wraps a line in SKILL.md).\n "}
{"bin": "16_token_ish", "content_sha256": "0d2185d967bbbf3092237c9858b4a0d0fe5a03b7b6347bdbf1b15e7b1ea492f9", "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/hooks/pre_commit_hooks/requirements_txt_fixer.rs", "end": 12210, "example_id": "0004d17cf7c6799d1be0bceabc0a97664e95bc14d347f71219dd609769ac5207", "language": "rust", "prefix": "cd\\na=3.0.0 \\\\\\n --hash=sha256:a1b1c1d1\",\n b\"a=3.0.0 \\\\\\n --hash=sha256:a1b1c1d1\\nb==1.0.0\\nc=2.0.0 \\\\\\n --hash=sha256:abcd\\n\",\n ),\n (\n b\"a=2.0.0 \\\\\\n --hash=sha256:abcd\\nb==1.0.0\\n\",\n b\"", "repo": "j178/prek", "span_codepoints": 64, "start": 12146, "suffix": " (b\"foo\\r\\nbar\\r\\n\", b\"bar\\r\\nfoo\\r\\n\"),\n (b\"# header\\nfoo \\\\\\n\\nbar\\n\", b\"# header\\n\\nbar\\n\"),\n (\n b\"zeta\\n-e git+ssh://url \\\\\\n --config=#egg=Alpha\\n\",\n b\"-e git+ssh://url \\\\\\n --config=#egg=Alp", "target": "a=2.0.0 \\\\\\n --hash=sha256:abcd\\nb==1.0.0\\n\",\n ),\n "}
{"bin": "32_token_ish", "content_sha256": "5308ec899ac988a3e5b27c4735c528027023dd4b5b7d58811cdb19b16d1eb657", "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/mido.sh", "end": 16514, "example_id": "0004df1ceda534a5c4a13addb082cde1ec6d33a8f7b3ba0728a52acdb814418e", "language": "shell", "prefix": "CE=\"$version\"\n return 0\n fi ;;\n\n \"win2025-eval\" | \"win2022-eval\" | \"win2019-eval\" | \\\n \"win2019-hv\" | \"win2016-eval\" | \"win2012r2-eval\" )\n\n if downloadWindowsEval \"$version\" \"$lang\" \"$edition\"; then\n MIDO_SOURCE=\"$version\"\n ", "repo": "dockur/windows", "span_codepoints": 128, "start": 16386, "suffix": "\"Invalid VERSION specified, value \\\"$version\\\" is not recognized!\"\n return 1\n ;;\n esac\n\n MIDO_URL=$(getMido \"$version\" \"$lang\" \"\")\n [ -z \"$MIDO_URL\" ] && return 1\n\n if [[ \"${version,,}\" == \"win2008r2\"* ]]; then\n MIDO_SOURCE=\"win2008r2-eval", "target": " return 0\n fi ;;\n\n \"win2008r2\"*| \"win81${PLATFORM,,}\"* | \"win10${PLATFORM,,}-enterprise\"* ) ;;\n\n * )\n error "}
{"bin": "8_token_ish", "content_sha256": "cb149140fb847f745eb03149390c69f24858811a64f60fc98ece5b305665b934", "document_id": "DataWithBaraa/sql-data-warehouse-project@92406686380cde6eca208c8b43e6fa40ecd26344:scripts/silver/proc_load_silver.sql", "end": 7478, "example_id": "0004e22224e0a29249b03630823a69b296dd9f97acddcab69fd5f7904fc09c34", "language": "sql", "prefix": "onze.erp_loc_a101;\n\t SET @end_time = GETDATE();\n PRINT '>> Load Duration: ' + CAST(DATEDIFF(SECOND, @start_time, @end_time) AS NVARCHAR) + ' seconds';\n PRINT '>> -------------';\n\t\t\n\t\t-- Loading erp_px_cat_g1v2\n\t\tSET @start_time = GETDATE()", "repo": "DataWithBaraa/sql-data-warehouse-project", "span_codepoints": 32, "start": 7446, "suffix": "silver.erp_px_cat_g1v2';\n\t\tTRUNCATE TABLE silver.erp_px_cat_g1v2;\n\t\tPRINT '>> Inserting Data Into: silver.erp_px_cat_g1v2';\n\t\tINSERT INTO silver.erp_px_cat_g1v2 (\n\t\t\tid,\n\t\t\tcat,\n\t\t\tsubcat,\n\t\t\tmaintenance\n\t\t)\n\t\tSELECT\n\t\t\tid,\n\t\t\tcat,\n\t\t\tsubcat,\n\t\t\tmaintenanc", "target": ";\n\t\tPRINT '>> Truncating Table: "}
{"bin": "16_token_ish", "content_sha256": "15c2f6475fc8450120c113d13ffb66e41a1689602376c09acdbe67d34f8c0567", "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/engines/_browsers/_controllers.py", "end": 3536, "example_id": "0004e684789020b8c2058485f753e65807369f9a8202242a15e9d38a05c3ae55", "language": "python", "prefix": " rules. Defaults to the system default locale.\n :param timezone_id: Changes the timezone of the browser. Defaults to the system timezone.\n :param wait_selector_state: The state to wait for the selector given with `wait_selector`. The", "repo": "D4Vinci/Scrapling", "span_codepoints": 64, "start": 3472, "suffix": " have a Chrome browser installed on your device, enable this, and the Fetcher will launch an instance of your browser and use it.\n :param load_dom: Enabled by default, wait for all JavaScript on page(s) to fully load and execute.\n :param cdp_", "target": " default state is `attached`.\n :param real_chrome: If you"}
{"bin": "64_token_ish", "content_sha256": "0f5034b20cdf6c444eb5542cb84be31eb733aba3ceafcdf7de204d108ca38ea7", "document_id": "TecharoHQ/anubis@34badc646c39af3d9f1f70757474b141316f23ad:lib/config/expressionorlist.go", "end": 802, "example_id": "0004e7860b6a5acd303a9188a00588332288a046f2a1085e174e58ceffd2b2eb", "language": "go", "prefix": "ionCantHaveBoth = errors.New(\"config: expression block can't contain multiple expression types\")\n)\n\ntype ExpressionOrList struct {\n\tExpression string `json:\"-\" yaml:\"-\"`\n\tAll []string `json:\"all,omitempty\" yaml:\"all,omitempty\"`\n\tAny ", "repo": "TecharoHQ/anubis", "span_codepoints": 256, "start": 546, "suffix": "{\n\t\t\tif i != 0 {\n\t\t\t\tfmt.Fprintf(&sb, \" && \")\n\t\t\t}\n\t\t\tfmt.Fprintf(&sb, \"( %s )\", pred)\n\t\t}\n\t\treturn sb.String()\n\tcase len(eol.Any) != 0:\n\t\tvar sb strings.Builder\n\t\tfor i, pred := range eol.Any {\n\t\t\tif i != 0 {\n\t\t\t\tfmt.Fprintf(&sb, \" || \")\n\t\t\t}\n\t\t\tfmt.Fprin", "target": " []string `json:\"any,omitempty\" yaml:\"any,omitempty\"`\n}\n\nfunc (eol ExpressionOrList) String() string {\n\tswitch {\n\tcase len(eol.Expression) != 0:\n\t\treturn eol.Expression\n\tcase len(eol.All) != 0:\n\t\tvar sb strings.Builder\n\t\tfor i, pred := range eol.All "}
{"bin": "8_token_ish", "content_sha256": "85934c959e5d8525fe947cded1423dfafddc32c1300782cdac63411aed25984d", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/commands/workflow-instructions-skipped.test.ts", "end": 4371, "example_id": "0004f213122f514ac92c6ec91e70adcce7793f51c4a9220b0c1cfbe8510e1aa0", "language": "typescript", "prefix": "tempDir = fs.mkdtempSync(path.join(os.tmpdir(), 'openspec-test-'));\n });\n\n afterEach(() => {\n fs.rmSync(tempDir, { recursive: true, force: true });\n });\n\n it('does not block apply on a skipped artifact when the schema requires all artifacts', async ", "repo": "Fission-AI/OpenSpec", "span_codepoints": 32, "start": 4339, "suffix": "apply block falls back to requiring every artifact,\n // including the specs-producing one - the skip must count as present.\n const schemaDir = path.join(tempDir, 'openspec', 'schemas', 'mini');\n fs.mkdirSync(schemaDir, { recursive: true });\n fs", "target": "() => {\n // A schema with no "}
{"bin": "8_token_ish", "content_sha256": "cf55fa3d72b6844e516e27b96125d33de000bf81990bb3c58965cb22abff8fa4", "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:csharp-book/src/ch15-2-incremental-adoption-strategy.md", "end": 1187, "example_id": "0004f7a268c1762c8af6c9b650894b7beeeac21889f339246b4d83324b7ccffa", "language": "markdown", "prefix": "line in content.lines() {\n for word in line.split_whitespace() {\n let word = word.to_lowercase();\n *word_count.entry(word).or_insert(0) += 1;\n }\n }\n \n let mut sorted: Vec<_> = word_count.into_iter().collect();\n ", "repo": "microsoft/RustTraining", "span_codepoints": 32, "start": 1155, "suffix": "(&a.1));\n \n for (word, count) in sorted.into_iter().take(args.top) {\n println!(\"{}: {}\", word, count);\n }\n \n Ok(())\n}\n```\n\n### Phase 2: Replace Performance-Critical Components (Weeks 5-8)\n```rust\n// Replace CPU-intensive data processi", "target": " sorted.sort_by(|a, b| b.1.cmp"}
{"bin": "8_token_ish", "content_sha256": "3b9cfbe86bc2af4f7f23042e60eaccf5e8d9df866d8a35a77d00672eab5202e6", "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/_base_converter.py", "end": 1063, "example_id": "0004fdc5d53725ea6c9ac1a9fa402f66cfcbaba9898030a902669d3ab583dc35", "language": "python", "prefix": "for `markdown`. New code should migrate to using `markdown` or __str__.\"\"\"\n return self.markdown\n\n @text_content.setter\n def text_content(self, markdown: str):\n \"\"\"Soft-deprecated alias for `markdown`. New code should migrate to using `", "repo": "microsoft/markitdown", "span_codepoints": 32, "start": 1031, "suffix": " self.markdown = markdown\n\n def __str__(self) -> str:\n \"\"\"Return the converted Markdown text.\"\"\"\n return self.markdown\n\n\nclass DocumentConverter:\n \"\"\"Abstract superclass of all DocumentConverters.\"\"\"\n\n def accepts(\n self,\n ", "target": "markdown` or __str__.\"\"\"\n "}
{"bin": "16_token_ish", "content_sha256": "e7c8fec3d2391a4034c89d78e2e526a03aa6a919c6603ae15d4bf3a38553c16e", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/completions/completion-provider.test.ts", "end": 7095, "example_id": "00050502d55aa6bffb1c6baddfed52b319055caa347e9bfd857453228aff5495", "language": "typescript", "prefix": ") => {\n it('should return both change and spec IDs', async () => {\n const changesDir = path.join(testDir, 'openspec', 'changes');\n const specsDir = path.join(testDir, 'openspec', 'specs');\n await fs.mkdir(changesDir, { recursive: true });", "repo": "Fission-AI/OpenSpec", "span_codepoints": 64, "start": 7031, "suffix": "Create a change\n await fs.mkdir(path.join(changesDir, 'my-change'), { recursive: true });\n await fs.writeFile(path.join(changesDir, 'my-change', 'proposal.md'), '# Change');\n\n // Create a spec\n await fs.mkdir(path.join(specsDir, 'my-spe", "target": "\n await fs.mkdir(specsDir, { recursive: true });\n\n // "}
{"bin": "32_token_ish", "content_sha256": "50b7035847a157b1de8f79fcfedda8b0ef1a36a993ad2edb7c3b7d48236ecf3e", "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:tests/fuzz/diskann-prune-direct.c", "end": 2386, "example_id": "00051611b2417cfd77b240341db0954ada7b8436b7b784c90b61bfad9f5f6a76", "language": "c", "prefix": "rom interesting values */\n uint8_t alpha_idx = fuzz_byte(&data, &size, 0) % 8;\n float alpha_values[] = {0.0f, 0.5f, 1.0f, 1.2f, 1.5f, 2.0f, 10.0f, 100.0f};\n float alpha = alpha_values[alpha_idx];\n\n if (num_candidates == 0) {\n /* Test empty case */\n ", "repo": "asg017/sqlite-vec", "span_codepoints": 128, "start": 2258, "suffix": "NULL, &outCount);\n assert(rc == 0 /* SQLITE_OK */);\n assert(outCount == 0);\n return 0;\n }\n\n /* Allocate arrays */\n int n = num_candidates;\n float *inter_distances = malloc(n * n * sizeof(float));\n float *p_distances = malloc(n * sizeof(float)", "target": " int outCount = -1;\n int rc = diskann_prune_select(NULL, NULL, 0, alpha, max_neighbors,\n "}
{"bin": "16_token_ish", "content_sha256": "5baae817d107ad948db05ed348477fea168289f3f29a4eddcc7466d5575da497", "document_id": "modelcontextprotocol/java-sdk@fd004989b9484c9b81be6b03463396797b354804:mcp-test/src/main/java/io/modelcontextprotocol/server/AbstractMcpSyncServerTests.java", "end": 4040, "example_id": "00051d0e7b2a061fe325f8baebe542f122cb8a3a291f65bf2be3716361106baa", "language": "java", "prefix": "ception();\n\t}\n\n\t@Test\n\tvoid testAddDuplicateToolCall() {\n\t\tTool duplicateTool = McpSchema.Tool.builder(TEST_TOOL_NAME, EMPTY_JSON_SCHEMA).title(\"Duplicate tool\").build();\n\n\t\tvar mcpSyncServer = prepareSyncServerBuilder().serverInfo(\"test-server\", \"1.0.0\")\n", "repo": "modelcontextprotocol/java-sdk", "span_codepoints": 64, "start": 3976, "suffix": "))\n\t\t\t.toolCall(duplicateTool,\n\t\t\t\t\t(exchange, request) -> CallToolResult.builder().content(List.of()).isError(false).build())\n\t\t\t.build();\n\n\t\tassertThatCode(() -> mcpSyncServer.addTool(McpServerFeatures.SyncToolSpecification.builder()\n\t\t\t.tool(duplicateTo", "target": "\t\t\t.capabilities(ServerCapabilities.builder().tools(true).build("}
{"bin": "32_token_ish", "content_sha256": "35d3bac200ce605ab32a55e6d873c36bd652ca3ec57136de120b0870f450cb79", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/validation.test.ts", "end": 33812, "example_id": "00051e334c460ceb00cf1008aaaa1f1d29f9a4bcf689937e11741d2605a19d12", "language": "typescript", "prefix": "tent);\n const issues = shallIssues(report.issues);\n expect(issues).toHaveLength(1);\n expect(issues[0].message).not.toContain('not only in the header');\n });\n\n it('does not flag a requirement whose body line contains the keyword', async", "repo": "Fission-AI/OpenSpec", "span_codepoints": 128, "start": 33684, "suffix": "S\\n- **WHEN** x\\n- **THEN** y'\n );\n const report = await new Validator().validateSpecContent('demo', content);\n expect(shallIssues(report.issues)).toHaveLength(0);\n });\n\n it('rejects a lowercase shall/must in the body (matching the del", "target": " () => {\n const content = buildSpec(\n '### Requirement: Logging\\nThe system SHALL log all events.\\n\\n#### Scenario: "}
{"bin": "16_token_ish", "content_sha256": "5a7bb103af6db7af89215cb2d20097fe59f2ac689e5175e4960290466fd47faf", "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:browser_use/browser/watchdogs/recording_watchdog.py", "end": 5572, "example_id": "000523e5bf4587d1848ac595fe738948f0e8211cf0609f6d66416329ae635eda", "language": "python", "prefix": "reencast on the specific session\n\t\t\t\t\tawait self.browser_session.cdp_client.send.Page.stopScreencast(session_id=self._current_session_id)\n\t\t\t\texcept Exception as e:\n\t\t\t\t\t# It's possible the session is already closed\n\t\t\t\t\tself.logger.debug(f'Failed to stop ", "repo": "browser-use/browser-use", "span_codepoints": 64, "start": 5508, "suffix": "self._current_session_id = cdp_session.session_id\n\n\t\t\t# Start recording on the new session\n\t\t\tawait cdp_session.cdp_client.send.Page.startScreencast(\n\t\t\t\tparams=self._screencast_params, # type: ignore\n\t\t\t\tsession_id=cdp_session.session_id,\n\t\t\t)\n\t\t\tself.lo", "target": "screencast on old session {self._current_session_id}: {e}')\n\n\t\t\t"}
{"bin": "16_token_ish", "content_sha256": "f9195f442170c1d21467e69398def04e748f5bbbc5ab619c289aec8d5a9d422f", "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/yahoo/search.test.js", "end": 2628, "example_id": "00052497a333adc9bb24330c2510f854beae3bedf4ef621ca448252ef0cfbbf3", "language": "javascript", "prefix": "]],\n });\n\n await expect(command.func(page, { keyword: 'opencli', limit: 1, page: 2 })).resolves.toEqual([{\n rank: 8,\n title: 'OpenCLI',\n url: 'https://github.com/jackwener/OpenCLI',\n snippet: 'CLI browser tooling',\n }]);\n });\n", "repo": "jackwener/OpenCLI", "span_codepoints": 64, "start": 2564, "suffix": " URLs', async () => {\n const page = createPageMock([\n [\n 'Bad redirect',\n 'https://r.search.yahoo.com/_ylt=x/RU=javascript%3Aalert(1)/RK=2/RS=x',\n 'should not be emitted',\n ],\n ]);\n\n await expect(command.func(page, {", "target": "\n it('drops decoded Yahoo redirect targets that are not http(s)"}
{"bin": "16_token_ish", "content_sha256": "a2aed2930510f336d4c741954ba889652e6d51fa7896e117c1928cc2f08be559", "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/languages/python/uv.rs", "end": 14554, "example_id": "00052d8a931e42c181ccbc2bd72eceeb793fde384a3f4af657657b6e52396abb", "language": "rust", "prefix": "> Self {\n Self { path }\n }\n\n pub(crate) fn cmd(&self, store: &Store) -> Cmd {\n let mut cmd = Cmd::new(&self.path);\n cmd.env(EnvVars::UV_CACHE_DIR, store.cache_path(CacheBucket::Uv));\n cmd\n }\n\n async fn select_source(", "repo": "j178/prek", "span_codepoints": 64, "start": 14490, "suffix": "Result {\n let url = format!(\n \"https://github.com/astral-sh/uv/releases/download/{CUR_UV_VERSION}/uv-x86_64-unknown-linux-gnu.tar.gz\"\n );\n let response = REQWEST_CLIENT\n .head(url)\n ", "target": ") -> Result {\n async fn check_github() -> "}
{"bin": "64_token_ish", "content_sha256": "58db8045145b385dc288be7faa24820813d36d5d39171370af1ce50ecd968256", "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/spiders/test_cache.py", "end": 1163, "example_id": "00053d33b4fdf7666c071d4c1ccb92217ce865f0d408b84000ce447e54a9c91d", "language": "python", "prefix": "body,\n status=status,\n reason=\"OK\",\n encoding=\"utf-8\",\n cookies={},\n headers={\"content-type\": \"text/html\"},\n request_headers={\"user-agent\": \"test\"},\n method=\"GET\",\n )\n\n\nclass TestResponseCacheManager:\n\n ", "repo": "D4Vinci/Scrapling", "span_codepoints": 256, "start": 907, "suffix": "x12\\x13\\x14\"\n original = _make_response(body=b\"test content\")\n\n await cache.put(fp, original, \"GET\")\n restored = await cache.get(fp)\n\n assert restored is not None\n assert restored.url == o", "target": " @pytest.mark.anyio\n async def test_put_get_roundtrip(self):\n with tempfile.TemporaryDirectory() as tmpdir:\n cache = ResponseCacheManager(tmpdir)\n fp = b\"\\x01\\x02\\x03\\x04\\x05\\x06\\x07\\x08\\x09\\x0a\\x0b\\x0c\\x0d\\x0e\\x0f\\x10\\x11\\"}
{"bin": "16_token_ish", "content_sha256": "7710f0c3f8a841937588aa777aa88e7c65df3bfbca88158aa2f93fbc65ca96d9", "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/__tests__/auth-commands.test.ts", "end": 1033, "example_id": "000540110eed1e19faa1659221297ecd6986c7a4d89e778d50f4689acae789a2", "language": "typescript", "prefix": "\n DEFAULT_DEVICE_POLL_INTERVAL_SECONDS: 5,\n}));\n\nvi.mock(\"../utils/tracking.js\", () => ({\n trackEvent: vi.fn(),\n}));\n\nconst mockSpinner = {\n start: vi.fn().mockReturnThis(),\n stop: vi.fn().mockReturnThis(),\n succeed: vi.fn().mockReturnThis(),\n fail: ", "repo": "upstash/context7", "span_codepoints": 64, "start": 969, "suffix": " default: () => mockSpinner }));\n\nconst mockOpen = vi.fn().mockResolvedValue(undefined);\nvi.mock(\"open\", () => ({ default: (...args: unknown[]) => mockOpen(...args) }));\n\nvi.mock(\"../constants.js\", () => ({ CLI_CLIENT_ID: \"test-client-id\" }));\nvi.mock(\"../", "target": "vi.fn().mockReturnThis(),\n text: \"\",\n};\nvi.mock(\"ora\", () => ({"}
{"bin": "32_token_ish", "content_sha256": "e61fd206814e0fb6c5e1c09ab716e41a85f07167bb2394fdb05465ac5cf6f512", "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/core/parsers/requirement-blocks.ts", "end": 7352, "example_id": "00054382332c06bf60eaf3c13a75151e9cd53257619884648cbd8dad7a91b4a0", "language": "typescript", "prefix": " modified: modifiedLookup.found,\n removed: removedLookup.found,\n renamed: renamedLookup.found,\n },\n };\n}\n\nfunction splitTopLevelSections(lines: string[], fenceMask: boolean[]): Record {\n const result: Record = {};\n const indices: Array<{ title: string; index: number }> = [];\n for (let i = 0; i < lines.length; i++) {\n "}
{"bin": "8_token_ish", "content_sha256": "6799887379de0dcc229a02897ab44d1ad774b2cbe6ce7cad59832e42feb0129c", "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/hub/heartbeat/heartbeat_test.go", "end": 1335, "example_id": "0005530a4899f5e187ab52e9c6cf259452a1ac75ec76000505983f6ef2b510ab", "language": "go", "prefix": "= func(key string) (string, bool) {\n\t\t\tv, ok := env[key]\n\t\t\treturn v, ok\n\t\t}\n\n\t\thb := heartbeat.New(app.App, getEnv)\n\t\trequire.NotNil(t, hb)\n\t\tcfg := hb.GetConfig()\n\t\tassert.Equal(t, \"https://heartbeat.example.com/ping\", cfg.URL)\n\t\tassert.Equal(t, 90, cfg.", "repo": "henrygd/beszel", "span_codepoints": 32, "start": 1303, "suffix": ".MethodHead, cfg.Method)\n\t})\n}\n\nfunc TestSendGETDoesNotRequireAppOrDB(t *testing.T) {\n\tapp := newTestHub(t)\n\tserver := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {\n\t\tassert.Equal(t, http.MethodGet, r.Method)\n\t\tassert.E", "target": "Interval)\n\t\tassert.Equal(t, http"}
{"bin": "16_token_ish", "content_sha256": "5a9976de581707f0f816221505b968d3d2da6a9415279166c491882a217f5ad7", "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/linker/lnk_symbol_table.c", "end": 29978, "example_id": "00055dd5afb3a096fbff5382b27e18b64224d702862f615282cdb54f12d5d4c6", "language": "c", "prefix": "ol symbol_parsed = lnk_parsed_from_symbol(symbol);\n COFF_SymbolValueInterpType symbol_interp = coff_interp_from_parsed_symbol(symbol_parsed);\n if (symbol_interp == COFF_SymbolValueInterp_Weak) {\n LNK_ObjSymbolRef resolve = {0};\n", "repo": "EpicGames/raddebugger", "span_codepoints": 64, "start": 29914, "suffix": ")) {\n COFF_ParsedSymbol resolve_parsed = lnk_parsed_symbol_from_coff_symbol_idx(resolve.obj, resolve.symbol_idx);\n COFF_SymbolValueInterpType resolve_interp = coff_interp_from_parsed_symbol(resolve_parsed);\n if (resolve_", "target": " if (lnk_resolve_weak_symbol(symtab, symbol_ref, &resolve"}
{"bin": "8_token_ish", "content_sha256": "e71a96aa60c9c56253d99a5c996d6ee7c2fe912eecf990bae6f0ecaa06207b72", "document_id": "OpenCut-app/OpenCut@4d8c49ed0706c4dc145361e01c6b1f1a87cbb863:apps/web/src/components/ui/button-group.tsx", "end": 1451, "example_id": "000564eefdb8631c9b63f2aa9262cc8ce83044756420dd446cbd257ab7159647", "language": "typescript", "prefix": "ion,\n ...props\n}: React.ComponentProps<\"div\"> & VariantProps) {\n return (\n \n )\n}\n\nfunction ButtonGroupText({\n className,\n render,\n ...props\n}: useRender.ComponentProps<\"div\">) {\n return useRender({\n defaultTagName: \"div\",\n props: mergeProps<\"div\">(\n {\n className: cn(\n \"flex items-center gap-2 ", "target": ", className)}\n {...props}\n "}
{"bin": "64_token_ish", "content_sha256": "50e0577ba8368c10751fe475d2f9fbd308e703514f16866ea53ffe2ac3d766db", "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/mercury/mercury.test.js", "end": 8174, "example_id": "0005669ca12d01f559e07109ba714118e072fa9eb4b76a4d2f75b520febb81b3", "language": "javascript", "prefix": "k([\n loggedInState(),\n createSurface(),\n clickResult(true),\n ], {\n uploadFiles: vi.fn().mockResolvedValue({ uploaded: true, files: 1, file_names: ['other.png'] }),\n });\n await expect(command.", "repo": "jackwener/OpenCLI", "span_codepoints": 256, "start": 7918, "suffix": "(),\n clickResult(true),\n ], {\n uploadFiles: vi.fn().mockResolvedValue({\n uploaded: true,\n files: 1,\n file_names: ['receipt.png'],\n target: '[data-testid=\"wrong\"]',\n ", "target": "func(page, validArgs())).rejects.toBeInstanceOf(CommandExecutionError);\n });\n\n it('typed-fails upload confirmation for the wrong input target', async () => {\n const page = createPageMock([\n loggedInState(),\n createSurface"}
{"bin": "32_token_ish", "content_sha256": "052d859eda206385b608aba621784a7ef7dce0e689a5dcc6b9f45f7aed596e76", "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:adk/interrupt_test.go", "end": 42658, "example_id": "000570da950ae1e723108fe778644958dba39066f44a9dbe06e4685e68980e15", "language": "go", "prefix": " up the hierarchy: A is parent of B and C.\n\tagentA, err := SetSubAgents(ctx, agentA, []Agent{agentB, agentC})\n\tassert.NoError(t, err)\n\n\t// Run the test\n\trunner := NewRunner(ctx, RunnerConfig{\n\t\tAgent: agentA,\n\t\tCheckPointStore: newMyStore(),\n\t})\n", "repo": "cloudwego/eino", "span_codepoints": 128, "start": 42530, "suffix": "\n\t\tif !ok {\n\t\t\tbreak\n\t\t}\n\t\tevents = append(events, event)\n\t}\n\n\t// We expect 3 transfer events (A->B, B->A, A->C) and 1 interrupt event from C.\n\tassert.Equal(t, 4, len(events))\n\n\tinterruptEvent := events[3]\n\tassert.NotNil(t, interruptEvent.Action.Interrupte", "target": "\titer := runner.Query(ctx, \"start\", WithCheckPointID(\"cyclical-1\"))\n\n\tvar events []*AgentEvent\n\tfor {\n\t\tevent, ok := iter.Next()"}
{"bin": "8_token_ish", "content_sha256": "9211ddd2687ba04a75c6c19f9896bbd1e62343d3d738e093f5241119da405645", "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/browser/test_tabs.py", "end": 14727, "example_id": "000576b8bdf0bf27e1afd5e7894b3e9d45095681b09d62a2127c4acf8345683e", "language": "python", "prefix": "\t\"next_goal\": \"Complete task\",\n\t\t\t\t\"action\": [\n\t\t\t\t\t{\n\t\t\t\t\t\t\"done\": {\n\t\t\t\t\t\t\t\"text\": \"Successfully opened 4 tabs rapidly without timeout\",\n\t\t\t\t\t\t\t\"success\": true\n\t\t\t\t\t\t}\n\t\t\t\t\t}\n\t\t\t\t]\n\t\t\t}\n\t\t\t\"\"\",\n\t\t]\n\n\t\tmock_llm = create_mock_llm(actions=actions)\n\n\t\tagent ", "repo": "browser-use/browser-use", "span_codepoints": 32, "start": 14695, "suffix": "tabs rapidly and verify browser state remains accessible',\n\t\t\tllm=mock_llm,\n\t\t\tbrowser_session=browser_session,\n\t\t)\n\n\t\t# Run with timeout - should complete within 2 minutes\n\t\ttry:\n\t\t\thistory = await asyncio.wait_for(agent.run(max_steps=5), timeout=120)\n\t\t\t", "target": "= Agent(\n\t\t\ttask='Open multiple "}
{"bin": "64_token_ish", "content_sha256": "6cd965a7b847a88e0e87d6a0813870ec7a0b83da46c623863a841c7d4375c139", "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/spiders/test_links.py", "end": 4826, "example_id": "000591d6930441fc91b26e51bff20ccf516163b2a443b1956c5fb8b464577ae7", "language": "python", "prefix": "body>\n \n m\n