import { createHash } from "node:crypto"; import { readFileSync, statSync, writeFileSync } from "node:fs"; import { resolve } from "node:path"; const root = resolve(import.meta.dirname, ".."); const mainPath = resolve( root, "src/data/deepseek-v2-lite-routing-role-marker-head-control.json", ); const reproPath = resolve( root, "src/data/deepseek-v2-lite-routing-role-marker-head-control-repro.json", ); const boundaryPath = resolve( root, "src/data/deepseek-v2-lite-routing-history-boundary-token-control.json", ); const outputPath = resolve( root, "src/data/deepseek-v2-lite-routing-role-marker-head-control-compact.json", ); const sha256 = (path) => createHash("sha256") .update(readFileSync(path)) .digest("hex"); const mainSha256 = sha256(mainPath); const reproSha256 = sha256(reproPath); const mainBytes = statSync(mainPath).size; const reproBytes = statSync(reproPath).size; const exact = mainSha256 === reproSha256 && mainBytes === reproBytes; if (!exact) { throw new Error("role-marker formal run and rerun are not byte-exact"); } const role = JSON.parse(readFileSync(mainPath, "utf8")); const boundary = JSON.parse(readFileSync(boundaryPath, "utf8")); const roleEdges = [ "system_official", "system_target_assistant", "system_target_x", "system_suffix_user", "target_assistant_at_s0", "target_assistant_at_s1", "target_x_at_s0", "target_x_at_s1", "suffix_user_at_s0", "suffix_user_at_s1", ]; const aggregateAlignment = (layer, domain, edge) => { const rows = layer.prompts .filter((prompt) => prompt.domain === domain) .map((prompt) => prompt.alignments[edge]); const aligned = rows.reduce( (sum, row) => sum + row.aligned_tokens, 0, ); const setExact = rows.reduce( (sum, row) => sum + row.set_topk_exact, 0, ); const orderedExact = rows.reduce( (sum, row) => sum + row.ordered_topk_exact, 0, ); const weightedJaccard = rows.reduce( (sum, row) => sum + row.mean_jaccard * row.aligned_tokens, 0, ); return { aligned, setExactRate: setExact / aligned, orderedExactRate: orderedExact / aligned, meanJaccard: weightedJaccard / aligned, }; }; const sourceById = new Map( boundary.corpus_contract.selected.map((source) => [source.id, source]), ); const tokenContract = { compared: 0, messageHashExact: 0, renderedHashExact: 0, tokenIdHashExact: 0, targetContractExact: 0, }; for (const source of role.corpus_contract.selected) { const priorSource = sourceById.get(source.id); if (!priorSource) throw new Error(`boundary source missing: ${source.id}`); for (const system of [0, 1]) { const current = source.conditions[`s${system}_official`]; const previous = priorSource.conditions[`s${system}_eos`]; tokenContract.compared += 1; tokenContract.messageHashExact += ( current.messages_sha256 === previous.messages_sha256 ); tokenContract.renderedHashExact += ( current.rendered_sha256 === previous.rendered_sha256 ); tokenContract.tokenIdHashExact += ( current.token_ids_sha256 === previous.token_ids_sha256 ); tokenContract.targetContractExact += ( current.tokens === previous.tokens && current.content_tokens === previous.content_tokens && current.aligned_content_tokens === previous.aligned_content_tokens ); } } const crossBatch = role.layers.slice(1).map((layer) => { const previousLayer = boundary.layers.find( (candidate) => candidate.layer === layer.layer, ); const previousById = new Map( previousLayer.prompts.map((prompt) => [prompt.id, prompt]), ); const counts = { compared: 0, fullRouteHashExact: 0, targetRouteHashExact: 0, fullLoadExact: 0, targetLoadExact: 0, }; for (const prompt of layer.prompts) { const previousPrompt = previousById.get(prompt.id); if (!previousPrompt) { throw new Error(`boundary prompt missing: ${prompt.id}`); } for (const system of [0, 1]) { const current = prompt.conditions[`s${system}_official`]; const previous = previousPrompt.conditions[`s${system}_eos`]; counts.compared += 1; counts.fullRouteHashExact += ( current.topk_sha256 === previous.topk_sha256 ); counts.targetRouteHashExact += ( current.content_topk_sha256 === previous.content_topk_sha256 ); counts.fullLoadExact += ( JSON.stringify(current.full_load) === JSON.stringify(previous.full_load) ); counts.targetLoadExact += ( JSON.stringify(current.content_load) === JSON.stringify(previous.content_load) ); } } return { layer: layer.layer, ...counts }; }); const compact = { schemaVersion: 1, source: { mainSha256, reproSha256, mainBytes, reproBytes, exact, }, domains: role.corpus_contract.domains, labels: role.corpus_contract.domain_labels, inference: role.inference_contract, contract: { tokenIds: role.role_marker_head_contract.role_token_ids, validation: role.role_marker_head_contract.render_validation, official: role.boundary.official_serialization_by_role_head, tokenContractAgainstBoundaryRun: tokenContract, }, crossBatch, layers: role.layers.slice(1).map((layer) => ({ layer: layer.layer, alignment: Object.fromEntries( role.corpus_contract.domains.map((domain) => [ domain, Object.fromEntries( roleEdges.map((edge) => [ edge, aggregateAlignment(layer, domain, edge), ]), ), ]), ), scopes: Object.fromEntries( ["target_content", "full_input"].map((scope) => [ scope, { modes: Object.fromEntries( ["prompt_balanced", "token_weighted"].map((mode) => { const control = ( layer.statistics[scope].modes[mode].role_marker_control ); return [ mode, Object.fromEntries( role.corpus_contract.domains.map((domain) => [ domain, { distances: control[domain].system_edge_distances, contrasts: ( control[domain].system_edge_distance_contrasts ), cvEdges: control[domain].metric_system_edges.cv, cvContrasts: ( control[domain].metric_system_edge_contrasts.cv ), direct: control[domain].direct_substitutions, }, ]), ), ]; }), ), }, ]), ), })), }; writeFileSync( outputPath, `${JSON.stringify(compact, null, 2)}\n`, "utf8", ); process.stdout.write( `${outputPath}\n${mainSha256}\n${mainBytes} bytes source → ` + `${statSync(outputPath).size} bytes compact\n`, );