AI Slop Code RIsk Monitor

jev-chat/jev-chat-jarvis

The chat decision assistant: before you reply, Jev reads the chat, judges intent and risk, and drafts replies you fill in with one tap. You press send. Android · Windows · macOS · iOS | 聊天辅助决策工具:先看懂对方再回复,发不发由你。

13.8 Moderate pattern signal View on GitHub

Maintenance and Governance Review

This report summarizes scanner evidence for jev-chat/jev-chat-jarvis, a Kotlin project with 7,606 GitHub stars. SynthScan examined 27,379 lines of code across 172 source files, recording 44 pattern matches distributed across 6 syntactic categories. The legacy adjusted pattern signal is 13.8 (Moderate pattern signal); it is not an authorship estimate.

Use the findings to ask whether maintainers can explain intent, verify dependencies, simplify unnecessary scaffolding, and focus review effort. Risk Payload v1 adds ownership, supply-chain, over-engineering, and review-effort vectors when available. These are prompts for human verification, not probabilities, security findings, or measured maintenance costs.

13.8
Adjusted Signal
13.8
Raw Pattern Score
100%
Time Factor
2026-10-08
Last Push
7.6K
Stars
Kotlin
Language
27.4K
Lines of Code
172
Files
44
Pattern Hits
2026-10-12
Scan Date
0.17
HC Hit Rate

Risk Review · v3

Use each vector to guide manual verification of the underlying findings.

Cognitive Ownership Risk 0.6/100 · LOW

Can maintainers explain intent, assumptions, and trade-offs? 3 finding(s).

Hallucinated Dependency & Supply Chain Risk 48.8/100 · MEDIUM

Are imports declared and package/API names verified? 35 finding(s).

Agent Over-Engineering Ratio 1.8/100 · LOW

Are wrappers, guards, and repeated structures necessary? 6 finding(s).

PR Review Velocity Impact 43.2/100 · MEDIUM

Which changes need focused human review? 44 finding(s).

What These Metrics Mean

Adjusted Signal
Legacy pattern score normalized per 1,000 scanned lines and multiplied by the repository-level time factor. It is not an estimate of AI authorship.
Raw Pattern Score
Sum of severity- and context-weighted pattern findings before applying the time factor.
Time Factor
A coarse multiplier based on repository last-push metadata. It does not identify when individual code was written.
Pattern Hits
Count of configured pattern findings. Review each location and surrounding code before acting.
HC Hit Rate
High- and critical-severity findings per scanned file. Severity is a configured detector weight, not proof of a vulnerability or authorship.
Lines / Files
Scan coverage denominators used by the legacy normalized score.

Pattern-Signal History

Run additional scans to build a history of the legacy pattern signal. Score changes are not a measure of AI adoption or code quality.

No multi-scan history yet — run the scanner again to build trend data.

Severity Breakdown

Groups findings by configured severity weight. Severity is not a confidence estimate, security rating, or proof that a package is missing. Verify imports against the project's manifests and inspect each finding in its local design context.

CRITICAL 29HIGH 1MEDIUM 0LOW 14

Directory Score Breakdown

This horizontal bar chart shows where configured pattern scores accumulate across directories. Treat the bars as locations to inspect, not as evidence of authorship or code quality. Use the file-level findings to decide whether a directory needs a focused ownership, dependency, complexity, or review check.

Pattern Findings

The scanner identified 44 distinct pattern matches across 6 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.

Hallucination Indicators29 hits · 360 pts
SeverityFileLineSnippetContext
CRITICAL…st/kotlin/com/jev/overseas/core/CandidateChecksTest.kt188 val own = com.jev.overseas.core.engine.GoalBuilder.fromEditedSummary(null, "Tell her I can't do Friday")CODE
CRITICAL…st/kotlin/com/jev/overseas/core/CandidateChecksTest.kt201 com.jev.overseas.core.engine.ScorePart(total, "", split, List(6) { 1.0 / 6 }), null, total, emptyList())CODE
CRITICAL…st/kotlin/com/jev/overseas/core/CandidateChecksTest.kt229 val g = com.jev.overseas.core.engine.GoalBuilder.fromStance(late, "Thursday")CODE
CRITICAL…st/kotlin/com/jev/overseas/core/CandidateChecksTest.kt254 val g = com.jev.overseas.core.engine.GoalBuilder.fromStance(ack)CODE
CRITICAL…c/test/kotlin/com/jev/overseas/core/GoalBuilderTest.kt59 private val work = com.jev.overseas.core.scene.Selection(com.jev.overseas.core.scene.Scene.WORK, com.jev.overseas.coCODE
CRITICAL…c/test/kotlin/com/jev/overseas/core/GoalBuilderTest.kt61 com.jev.overseas.core.scene.WorkScene.stances(behavior, work, emptySet())!!.options.first { it.id == id }CODE
CRITICAL…c/test/kotlin/com/jev/overseas/core/GoalBuilderTest.kt92 val admit = com.jev.overseas.core.scene.Shared.complaintStances().first { it.id == "admit_apologise" }CODE
CRITICAL…/src/test/kotlin/com/jev/overseas/core/DraftingTest.kt54 assertTrue(com.jev.overseas.core.engine.Drafting.nearDuplicate("ok", "OK"))CODE
CRITICAL⚡…/src/test/kotlin/com/jev/overseas/core/DraftingTest.kt118 val sel = com.jev.overseas.core.scene.Selection(com.jev.overseas.core.scene.Scene.WORK, com.jev.overseas.core.scCODE
CRITICAL⚡…/src/test/kotlin/com/jev/overseas/core/DraftingTest.kt119 val late = com.jev.overseas.core.scene.WorkScene.stances("W02", sel, emptySet())!!.options.first { it.id == "latCODE
CRITICAL⚡…/src/test/kotlin/com/jev/overseas/core/DraftingTest.kt120 val goal = com.jev.overseas.core.engine.GoalBuilder.fromStance(late, relationshipId = "senior")CODE
CRITICAL⚡…/src/test/kotlin/com/jev/overseas/core/DraftingTest.kt121 val conv = com.jev.overseas.core.testing.chat(com.jev.overseas.core.testing.me("hi"), com.jev.overseas.core.testCODE
CRITICAL⚡…/src/test/kotlin/com/jev/overseas/core/DraftingTest.kt122 val user = com.jev.overseas.core.json.MiniJson.parseObject(CODE
CRITICAL⚡…/src/test/kotlin/com/jev/overseas/core/DraftingTest.kt131 assertFalse(com.jev.overseas.core.json.MiniJson.parseObject(Drafting.userPrompt(conv, sel, goal, "UK")).containsCODE
CRITICAL…est/kotlin/com/jev/overseas/core/AnalysisEngineTest.kt265 val pdf = com.jev.overseas.core.engine.ChatMessage(com.jev.overseas.core.engine.Sender.OTHER, "[document]", readCODE
CRITICAL⚡…est/kotlin/com/jev/overseas/core/AnalysisEngineTest.kt279 val pdf = com.jev.overseas.core.engine.ChatMessage(com.jev.overseas.core.engine.Sender.OTHER, "[document]", readCODE
CRITICAL⚡…est/kotlin/com/jev/overseas/core/AnalysisEngineTest.kt280 val g = com.jev.overseas.core.testing.FakeGateway()CODE
CRITICAL⚡…est/kotlin/com/jev/overseas/core/AnalysisEngineTest.kt281 val out = com.jev.overseas.core.engine.Assistant(g).analyze(chat(me("can you send the invoice?"), pdf), work, coCODE
CRITICAL…est/kotlin/com/jev/overseas/core/WhatsAppReplayTest.kt184 val c = com.jev.overseas.core.engine.Conversation.fromRows(read.rows)CODE
CRITICAL⚡…/test/kotlin/com/jev/overseas/core/ConversationTest.kt168 com.jev.overseas.core.testing.me("can you do friday?"),CODE
CRITICAL⚡…/test/kotlin/com/jev/overseas/core/ConversationTest.kt169 com.jev.overseas.core.testing.them("hmm"),CODE
CRITICAL⚡…/test/kotlin/com/jev/overseas/core/ConversationTest.kt171 com.jev.overseas.core.testing.them("actually no, sorry"),CODE
CRITICAL⚡…/test/kotlin/com/jev/overseas/core/ConversationTest.kt177 com.jev.overseas.core.testing.me("ok"),CODE
CRITICAL⚡…/test/kotlin/com/jev/overseas/core/ConversationTest.kt179 com.jev.overseas.core.testing.them("see you then"),CODE
CRITICAL…t/kotlin/com/jev/overseas/core/AssistantSessionTest.kt288 val prompt = com.jev.overseas.core.json.MiniJson.parseObject(gateway.chats.last().user!!)CODE
CRITICAL…t/kotlin/com/jev/overseas/core/AssistantSessionTest.kt442 val lastDraft = com.jev.overseas.core.json.MiniJson.parseObject(gateway.chats.last().user!!)CODE
CRITICAL…t/kotlin/com/jev/overseas/core/AssistantSessionTest.kt583 val dump = com.jev.overseas.core.json.MiniJson.encode(events)CODE
CRITICAL…src/test/kotlin/com/jev/overseas/core/live/LiveEval.kt450 val set = assistant.draftAndCheck(conv, sel, com.jev.overseas.core.engine.GoalBuilder.fromStance(option), boundaCODE
CRITICAL…test/kotlin/com/jev/overseas/core/live/RevisionEval.kt113 val r = gateway.decisions(com.jev.overseas.core.engine.CandidateChecks.state(l.conv, l.sel, l.goal, textCODE
Unused Imports6 hits · 6 pts
SeverityFileLineSnippetContext
LOWcn/tools/jev/questions.py3CODE
LOWcn/tools/jev/demo_meme.py3CODE
LOWcn/tools/jev/jev_client.py3CODE
LOWcn/tools/jev/calibrate.py3CODE
LOWcn/tools/jev/probe_background_field.py17CODE
LOWglobal/tools/or_client.py10CODE
Excessive Try-Catch Wrapping5 hits · 5 pts
SeverityFileLineSnippetContext
LOWcn/tools/jev/jev_client.py46 except Exception:CODE
LOWcn/tools/jev/probe_background_field.py96 except Exception as e: # network-levelCODE
LOWglobal/tools/or_client.py54 except Exception:CODE
LOWglobal/tools/or_client.py90 except Exception:CODE
LOWglobal/tools/or_client.py101 except Exception:CODE
Empty Error Handlers1 hit · 5 pts
SeverityFileLineSnippetContext
HIGHcn/tools/jev/calibrate.py73except (TypeError, ValueError):CODE
Deep Nesting2 hits · 2 pts
SeverityFileLineSnippetContext
LOWcn/tools/jev/demo_meme.py34CODE
LOWglobal/tools/probe/read_dump.py41CODE
Over-Commented Block1 hit · 1 pts
SeverityFileLineSnippetContext
LOW…/main/java/com/jev/probe/capture/ChatCaptureService.kt281 override fun onAccessibilityEvent(event: AccessibilityEvent?) {COMMENT