|
| 1 | +import path from "node:path" |
| 2 | +import { writeLiveArtifact } from "../../../llm/script/live-llm/config" |
| 3 | +import { finishLiveScript } from "./lifecycle" |
| 4 | +import { runLegacyLiveCases } from "./runtime" |
| 5 | + |
| 6 | +const directMarker = `direct-intent-${crypto.randomUUID()}` |
| 7 | +const rewriteMarker = `rewrite-intent-${crypto.randomUUID()}` |
| 8 | +const directIntentID = `intent-direct-${crypto.randomUUID()}` |
| 9 | +const rewriteIntentID = `intent-rewrite-${crypto.randomUUID()}` |
| 10 | +// Keep classifier input natural; response markers belong to the agent prompt, not the user request. |
| 11 | +const directPrompt = "你好" |
| 12 | +const conflictingPrompt = "你好!" |
| 13 | +const rewritePrompt = "谢谢" |
| 14 | + |
| 15 | +const artifact = await runLegacyLiveCases({ |
| 16 | + suite: "prompt-intent-fencing-legacy", |
| 17 | + permission: { "*": "deny" }, |
| 18 | + cases: [ |
| 19 | + { |
| 20 | + name: "intelligence-direct", |
| 21 | + prompt: directPrompt, |
| 22 | + intelligence: { outputLanguage: "english", expectedRoute: "general" }, |
| 23 | + admission: { |
| 24 | + intentID: directIntentID, |
| 25 | + source: "intelligence", |
| 26 | + variant: "original", |
| 27 | + exactRetry: true, |
| 28 | + conflictingRetry: { prompt: conflictingPrompt, variant: "rewritten" }, |
| 29 | + }, |
| 30 | + }, |
| 31 | + { |
| 32 | + name: "revert-rewrite", |
| 33 | + prompt: rewritePrompt, |
| 34 | + admission: { |
| 35 | + intentID: rewriteIntentID, |
| 36 | + source: "rewrite", |
| 37 | + variant: "rewritten", |
| 38 | + exactRetry: true, |
| 39 | + }, |
| 40 | + revertBefore: { targetCase: "intelligence-direct", retryTargetIntent: true }, |
| 41 | + }, |
| 42 | + ], |
| 43 | + sharedSession: true, |
| 44 | + primaryPrompt: |
| 45 | + `When the user says "${directPrompt}", reply with exactly ${directMarker}. ` + |
| 46 | + `When the user says "${rewritePrompt}", reply with exactly ${rewriteMarker}. ` + |
| 47 | + "Do not call tools or add any other text.", |
| 48 | + modelMaxTokens: 128, |
| 49 | + maxProviderTurns: 2, |
| 50 | +}) |
| 51 | + |
| 52 | +const direct = requireCase("intelligence-direct") |
| 53 | +const rewrite = requireCase("revert-rewrite") |
| 54 | + |
| 55 | +if (direct.sessionID !== rewrite.sessionID) throw new Error("Prompt intent fencing did not use one durable Session") |
| 56 | +if (direct.intelligenceDraft?.route !== "general" || direct.intelligenceDraft.preview !== directPrompt) { |
| 57 | + throw new Error("Intelligence preparation did not select the direct route with the original prompt") |
| 58 | +} |
| 59 | +if ( |
| 60 | + direct.admission?.state !== "admitted" || |
| 61 | + direct.admission.source !== "intelligence" || |
| 62 | + direct.admission.variant !== "original" || |
| 63 | + direct.admission.delivery !== "turn" |
| 64 | +) { |
| 65 | + throw new Error(`Direct intent receipt was invalid: ${JSON.stringify(direct.admission)}`) |
| 66 | +} |
| 67 | +const directRetry = direct.admission.retry |
| 68 | +if ( |
| 69 | + directRetry?.exact?.accepted !== true || |
| 70 | + !directRetry.activeBeforeRetry || |
| 71 | + directRetry.exact.userCountBefore !== directRetry.exact.userCountAfter |
| 72 | +) { |
| 73 | + throw new Error("Exact direct-intent retry was not an active-turn admission no-op") |
| 74 | +} |
| 75 | +if ( |
| 76 | + directRetry.conflict?.accepted !== false || |
| 77 | + directRetry.conflict.error !== "SessionPromptIntent.Conflict" |
| 78 | +) { |
| 79 | + throw new Error(`Late rewritten draft was not rejected: ${JSON.stringify(directRetry.conflict)}`) |
| 80 | +} |
| 81 | +if (direct.users.length !== 1 || direct.users[0]?.text !== directPrompt) { |
| 82 | + throw new Error(`Direct route materialized ${direct.users.length} user messages instead of the original input once`) |
| 83 | +} |
| 84 | +if (direct.users[0].metadata?.deepagent?.prompt_pipeline?.mode !== "direct_override") { |
| 85 | + throw new Error("Direct-route user message did not preserve direct_override metadata") |
| 86 | +} |
| 87 | +if ( |
| 88 | + direct.assistantTurns !== 1 || |
| 89 | + direct.newTools.length !== 0 || |
| 90 | + direct.providerErrors.length !== 0 || |
| 91 | + !direct.finalText.includes(directMarker) |
| 92 | +) { |
| 93 | + throw new Error("Direct-route execution did not complete exactly once through the real provider") |
| 94 | +} |
| 95 | + |
| 96 | +if ( |
| 97 | + rewrite.revert?.targetCase !== "intelligence-direct" || |
| 98 | + rewrite.revert.epochAfter !== rewrite.revert.epochBefore + 1 || |
| 99 | + rewrite.revert.retry?.accepted !== false || |
| 100 | + rewrite.revert.retry.error !== "SessionMutationEpoch.Stale" |
| 101 | +) { |
| 102 | + throw new Error(`Revert did not fence the old prompt intent: ${JSON.stringify(rewrite.revert)}`) |
| 103 | +} |
| 104 | +if ( |
| 105 | + rewrite.admission?.state !== "admitted" || |
| 106 | + rewrite.admission.source !== "rewrite" || |
| 107 | + rewrite.admission.variant !== "rewritten" || |
| 108 | + rewrite.admission.mutationEpoch !== rewrite.revert.epochAfter |
| 109 | +) { |
| 110 | + throw new Error(`Rewrite intent receipt was invalid: ${JSON.stringify(rewrite.admission)}`) |
| 111 | +} |
| 112 | +const rewriteRetry = rewrite.admission.retry |
| 113 | +if ( |
| 114 | + rewriteRetry?.exact?.accepted !== true || |
| 115 | + !rewriteRetry.activeBeforeRetry || |
| 116 | + rewriteRetry.exact.userCountBefore !== rewriteRetry.exact.userCountAfter |
| 117 | +) { |
| 118 | + throw new Error("Exact rewrite retry was not an active-turn admission no-op") |
| 119 | +} |
| 120 | +if (rewrite.users.length !== 1 || rewrite.users[0]?.text !== rewritePrompt) { |
| 121 | + throw new Error(`Revert/rewrite materialized ${rewrite.users.length} current user messages instead of one`) |
| 122 | +} |
| 123 | +if ( |
| 124 | + rewrite.assistantTurns !== 1 || |
| 125 | + rewrite.newTools.length !== 0 || |
| 126 | + rewrite.providerErrors.length !== 0 || |
| 127 | + !rewrite.finalText.includes(rewriteMarker) |
| 128 | +) { |
| 129 | + throw new Error("Rewritten prompt did not execute exactly once through the real provider") |
| 130 | +} |
| 131 | +if (rewrite.allText.includes(directMarker) || artifact.workspace.status.trim()) { |
| 132 | + throw new Error("Revert left stale output in the active transcript or mutated the workspace") |
| 133 | +} |
| 134 | +if ( |
| 135 | + artifact.cases.some( |
| 136 | + (testCase) => testCase.permissionRequests.length !== 0 || testCase.questionRequests.length !== 0, |
| 137 | + ) |
| 138 | +) { |
| 139 | + throw new Error("Prompt intent fencing requested undeclared permission or question input") |
| 140 | +} |
| 141 | + |
| 142 | +const result = { |
| 143 | + ...artifact, |
| 144 | + mode: "ext" as const, |
| 145 | + evidence: { |
| 146 | + directIntentHash: Bun.hash(directIntentID).toString(16), |
| 147 | + rewriteIntentHash: Bun.hash(rewriteIntentID).toString(16), |
| 148 | + directMarkerHash: Bun.hash(directMarker).toString(16), |
| 149 | + rewriteMarkerHash: Bun.hash(rewriteMarker).toString(16), |
| 150 | + exactRetries: 2, |
| 151 | + conflictingDraftRejected: true, |
| 152 | + staleEpochRetryRejected: true, |
| 153 | + mutationEpochAdvance: rewrite.revert.epochAfter - rewrite.revert.epochBefore, |
| 154 | + userMessagesAfterRewrite: rewrite.users.length, |
| 155 | + providerTurns: direct.assistantTurns + rewrite.assistantTurns, |
| 156 | + }, |
| 157 | +} |
| 158 | + |
| 159 | +await writeLiveArtifact( |
| 160 | + { artifactDirectory: path.resolve(import.meta.dir, "../../.artifacts/live-llm") }, |
| 161 | + result.suite, |
| 162 | + result, |
| 163 | + { |
| 164 | + redactions: [ |
| 165 | + { value: directMarker, replacement: `<direct-marker hash=${result.evidence.directMarkerHash}>` }, |
| 166 | + { value: rewriteMarker, replacement: `<rewrite-marker hash=${result.evidence.rewriteMarkerHash}>` }, |
| 167 | + { value: directIntentID, replacement: `<direct-intent hash=${result.evidence.directIntentHash}>` }, |
| 168 | + { value: rewriteIntentID, replacement: `<rewrite-intent hash=${result.evidence.rewriteIntentHash}>` }, |
| 169 | + ], |
| 170 | + }, |
| 171 | +) |
| 172 | +console.log( |
| 173 | + `${result.suite}: passed (${result.fingerprint.providerID}/${result.fingerprint.modelID}, ` + |
| 174 | + `${result.evidence.providerTurns} provider turns, epoch +${result.evidence.mutationEpochAdvance})`, |
| 175 | +) |
| 176 | + |
| 177 | +finishLiveScript() |
| 178 | + |
| 179 | +function requireCase(name: string) { |
| 180 | + const testCase = artifact.cases.find((item) => item.name === name) |
| 181 | + if (!testCase) throw new Error(`Missing prompt-intent case ${name}`) |
| 182 | + return testCase |
| 183 | +} |
0 commit comments