Repository Analysis

MoonshotAI/kimi-code

Kimi Code CLI — The Starting Point for Next-Gen Agents

2.5 Likely human-written View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of MoonshotAI/kimi-code, a TypeScript project with 3,097 GitHub stars. SynthScan v2.0 examined 729,260 lines of code across 3400 source files, recording 1248 pattern matches distributed across 11 syntactic categories. The overall adjusted score of 2.5 places this repository in the Likely human-written band.

The scanner applied 160+ deterministic lexical heuristics, multi-line block detectors, abstract syntax tree depth profilers, and a cross-file Jaccard similarity matrix to construct a statistically normalised synthetic code estimate. All matches are individually weighted by severity coefficient and contextual multiplier before summation, and the resulting headline score is temporally discounted to account for the repository's development history relative to the commercial emergence of large language model coding tooling (November 2022 onward).

2.5
Adjusted Score
2.5
Raw Score
100%
Time Factor
2026-07-14
Last Push
3.1K
Stars
TypeScript
Language
729.3K
Lines of Code
3.4K
Files
1.2K
Pattern Hits
2026-07-14
Scan Date
0.00
HC Hit Rate

What These Metrics Mean

Adjusted Score
Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score
The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor
The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits
Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate
High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files
Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 3HIGH 9MEDIUM 220LOW 1016

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 1248 distinct pattern matches across 11 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. 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 diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Hyper-Verbose Identifiers830 hits · 859 pts
SeverityFileLineSnippetContext
LOWpackages/acp-adapter/test/approval-cancel.test.ts80function makeCancellableApprovalSession(sessionId: string): {CODE
LOWpackages/acp-adapter/test/session-resume.test.ts70function makeSessionWithMainConfig(CODE
LOW…/acp-adapter/test/session-config-option-funnel.test.ts113function extractSingleConfigOptionUpdate(CODE
LOWpackages/acp-adapter/src/config-options.ts186export async function buildSessionConfigOptions(CODE
LOWpackages/acp-adapter/src/events-map.ts34export function assistantDeltaToSessionUpdate(CODE
LOWpackages/acp-adapter/src/events-map.ts67export function turnEndReasonToStopReason(CODE
LOWpackages/acp-adapter/src/events-map.ts158export function toolCallStartToSessionUpdate(CODE
LOWpackages/acp-adapter/src/events-map.ts203export function toolCallDeltaToSessionUpdate(CODE
LOWpackages/acp-adapter/src/events-map.ts251export function toolCallLazyCreateToSessionUpdate(CODE
LOWpackages/acp-adapter/src/events-map.ts291export function toolCallStartedUpgradeToSessionUpdate(CODE
LOWpackages/acp-adapter/src/events-map.ts331export function toolProgressToSessionUpdate(CODE
LOWpackages/acp-adapter/src/events-map.ts354export function thinkingDeltaToSessionUpdate(CODE
LOWpackages/acp-adapter/src/events-map.ts379export function toolResultToSessionUpdate(CODE
LOWpackages/acp-adapter/src/events-map.ts485export function availableCommandsUpdateNotification(CODE
LOWpackages/acp-adapter/src/events-map.ts516export function configOptionUpdateNotification(CODE
LOWpackages/acp-adapter/src/approval.ts94export function approvalRequestToPermissionOptions(CODE
LOWpackages/acp-adapter/src/approval.ts147export function permissionResponseToApprovalResponse(CODE
LOWpackages/acp-adapter/src/approval.ts256export function buildPermissionToolCallUpdate(CODE
LOWpackages/acp-adapter/src/model-catalog.ts84export function deriveDefaultThinkingEffort(alias: ModelAlias): string {CODE
LOWpackages/acp-adapter/src/session.ts1478function formatCompactionCompleted(result: CompactionCompletedResult): string {CODE
LOWpackages/acp-adapter/src/session.ts1636function toolMessageContentToAcpToolCallContent(CODE
LOWpackages/acp-adapter/src/question.ts50export function questionItemToPermissionOptions(CODE
LOWpackages/acp-adapter/src/server.ts1083function sessionSummaryToSessionInfo(summary: SessionSummary): SessionInfo {CODE
LOWpackages/oauth/test/managed-kimi-code.test.ts844 function makeThinkingTypeModelsResponse(): Response {CODE
LOWpackages/oauth/src/oauth.ts101export async function requestDeviceAuthorization(CODE
LOWpackages/oauth/src/identity.ts124export function parseKimiCodeCustomHeaders(CODE
LOWpackages/oauth/src/managed-kimi-code.ts348export function resolveKimiCodeRuntimeAuth(options: {CODE
LOWpackages/oauth/src/managed-kimi-code.ts445export function parseSupportsThinkingType(value: unknown): SupportsThinkingType | undefined {CODE
LOWpackages/oauth/src/managed-kimi-code.ts477export async function fetchManagedKimiCodeModels(CODE
LOWpackages/oauth/src/managed-kimi-code.ts513export function applyManagedKimiCodeConfig(CODE
LOWpackages/oauth/src/managed-kimi-code.ts617export function applyManagedKimiCodeLogoutConfig(config: ManagedKimiConfigShape): void {CODE
LOWpackages/oauth/src/managed-kimi-code.ts707export function clearManagedKimiCodeConfig(CODE
LOWpackages/oauth/src/managed-kimi-code.ts751function assertPositiveContextLength(model: ManagedKimiCodeModelInfo): void {CODE
LOWpackages/oauth/src/managed-kimi-code.ts757export async function provisionManagedKimiCodeConfigAfterLogin(CODE
LOWpackages/oauth/src/managed-feedback-upload.ts51export function kimiCodeFeedbackUploadUrl(baseUrl?: string): string {CODE
LOWpackages/oauth/src/managed-feedback-upload.ts55export function kimiCodeFeedbackUploadCompleteUrl(baseUrl?: string): string {CODE
LOWpackages/oauth/src/managed-feedback-upload.ts59export async function fetchCreateFeedbackUploadUrl(CODE
LOWpackages/oauth/src/managed-feedback-upload.ts73export async function fetchCompleteFeedbackUpload(CODE
LOWpackages/oauth/src/toolkit.ts440export function resolveKimiTokenStorageName(input: {CODE
LOWpackages/oauth/src/refreshProviderModels.ts114function customRegistrySourceCredentialKey(source: CustomRegistrySource): string {CODE
LOWpackages/oauth/src/refreshProviderModels.ts118async function fetchCustomRegistryFromSources(CODE
LOWpackages/oauth/src/refreshProviderModels.ts141function collectModelIdsForAliases(CODE
LOWpackages/oauth/src/refreshProviderModels.ts163function generatedProviderAliasKeys(CODE
LOWpackages/oauth/src/refreshProviderModels.ts256function preserveUserProviderAliases(CODE
LOWpackages/oauth/src/refreshProviderModels.ts308function clearDefaultThinkingWhenDefaultRemoved(CODE
LOWpackages/oauth/src/custom-registry.ts261export function capabilitiesFromCustomEntry(model: CustomRegistryModelEntry): string[] {CODE
LOWpackages/oauth/src/custom-registry.ts312export function applyCustomRegistryProvider(CODE
LOWpackages/oauth/src/custom-registry.ts372export function removeCustomRegistryProvider(CODE
LOWpackages/oauth/src/custom-registry.ts416export function applyCustomRegistryEntries(CODE
LOWpackages/agent-core-v2/test/app/bootstrap/stubs.ts54export function registerBootstrapServices(reg: ServiceRegistration): void {CODE
LOW…re-v2/test/app/skillCatalog/skill-tool-manager.test.ts29function recordContainsSkillLoaded(record: unknown, skillName: string): boolean {CODE
LOW…-v2/test/app/skillCatalog/plugin-session-start.test.ts100function pluginSessionStartMessages(ctx: ReturnType<typeof testAgent>) {CODE
LOW…gent-core-v2/test/app/llmProtocol/select-tools.test.ts46function makeChatCompletionResponse() {CODE
LOW…t-core-v2/test/app/sessionExport/sessionExport.test.ts783function registerSessionExportServices(CODE
LOWpackages/agent-core-v2/test/app/telemetry/stubs.ts58export function registerTelemetryServices(reg: ServiceRegistration): void {CODE
LOW…-v2/test/app/sessionLifecycle/sessionLifecycle.test.ts191function persistentWorkspaceRegistryStub(): IWorkspaceRegistry {CODE
LOW…-v2/test/app/sessionLifecycle/sessionLifecycle.test.ts298function agentLifecycleWithMainStub(): IAgentLifecycleService {CODE
LOW…-v2/test/app/sessionLifecycle/sessionLifecycle.test.ts324function agentLifecycleCapturingPlanSpy(opts: { mainPreexists?: boolean } = {}): {CODE
LOWpackages/agent-core-v2/test/wire/persistence.test.ts77async function createFileAppendLogHarness(): Promise<{CODE
LOWpackages/agent-core-v2/test/wire/resume.test.ts945function resumeDeferredSystemReminderHistory(): WireRecord[] {CODE
770 more matches not shown…
Decorative Section Separators204 hits · 612 pts
SeverityFileLineSnippetContext
MEDIUMpackages/acp-adapter/src/kaos-acp.ts49 // ── identity ────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/acp-adapter/src/kaos-acp.ts60 // ── path operations: delegate to inner ─────────────────────────────COMMENT
MEDIUMpackages/acp-adapter/src/kaos-acp.ts116 // ── reads: route through ACP `fs/readTextFile` ─────────────────────COMMENT
MEDIUMpackages/acp-adapter/src/kaos-acp.ts182 // ── writes: route through ACP `fs/writeTextFile` ───────────────────COMMENT
MEDIUMpackages/acp-adapter/src/kaos-acp.ts242 // ── process execution: delegate to inner ───────────────────────────COMMENT
MEDIUMpackages/oauth/test/oauth-manager.test.ts73// ── ensureFresh ───────────────────────────────────────────────────────COMMENT
MEDIUMpackages/oauth/test/oauth-manager.test.ts392 // ── force=true propagates errors (no silent swallow) ──────────────────COMMENT
MEDIUMpackages/oauth/test/oauth-manager.test.ts586// ── login ─────────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/oauth/test/oauth-manager.test.ts748// ── logout & hasToken ─────────────────────────────────────────────────COMMENT
MEDIUMpackages/oauth/test/oauth-manager.test.ts779// ── slow_down RFC 8628 §3.5 ────────────────────────────────────────────COMMENT
MEDIUMpackages/oauth/test/oauth-manager.test.ts818// ── FileTokenStorage integration ───────────────────────────────────────COMMENT
MEDIUMpackages/oauth/test/oauth.test.ts116// ── Fixtures ──────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/oauth/test/oauth.test.ts176// ── requestDeviceAuthorization ────────────────────────────────────────COMMENT
MEDIUMpackages/oauth/test/oauth.test.ts313// ── pollDeviceToken ───────────────────────────────────────────────────COMMENT
MEDIUMpackages/oauth/test/oauth.test.ts457// ── refreshAccessToken ────────────────────────────────────────────────COMMENT
MEDIUMpackages/oauth/test/oauth.test.ts611 // ── network error retry / 400 fail-fast ───────────────────────────────COMMENT
MEDIUMpackages/oauth/test/storage.test.ts168 // ── atomic save leaves no .tmp sibling ────────────────────────────────COMMENT
MEDIUMpackages/oauth/test/oauth-manager-multi-process.test.ts37// ─────────────────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/oauth/test/oauth-manager-multi-process.test.ts39// ─────────────────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/oauth/src/oauth.ts99// ── requestDeviceAuthorization ────────────────────────────────────────COMMENT
MEDIUMpackages/oauth/src/oauth.ts142// ── pollDeviceToken ───────────────────────────────────────────────────COMMENT
MEDIUMpackages/oauth/src/oauth.ts195// ── refreshAccessToken ────────────────────────────────────────────────COMMENT
MEDIUMpackages/oauth/src/managed-usage.ts255// ── HTTP fetch ────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/kap-server/test/snapshotReader.unit.test.ts33// ─── tiny stubs ───────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/kap-server/test/snapshotReader.unit.test.ts138// ─── SnapshotReader.read ──────────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/test/session-resume.test.ts64 // ── Gap 1: cold-session /messages ──────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/test/session-resume.test.ts121 // ── Gap 2: live status field ───────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/scenarios/03-refresh-replay.ts154 // ── Phase 0 ─────────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/scenarios/03-refresh-replay.ts204 // ── Phase 0 again — simulate a browser refresh (cheap re-probe) ──────COMMENT
MEDIUMpackages/server-e2e/scenarios/03-refresh-replay.ts263 // ── Phase 2: persisted REST snapshot reflects the first prompt ───────COMMENT
MEDIUMpackages/server-e2e/src/http.ts176 // ── Probes + model catalog ─────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/http.ts201 // ── Sessions ────────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/http.ts271 // ── Terminals ──────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/http.ts307 // ── Workspaces ──────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/http.ts329 // ── Folder picker (fs:browse + fs:home) ─────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/http.ts337 // ── Uploads ─────────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/http.ts356 // ── Messages ────────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/http.ts364 // ── Prompts ─────────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/http.ts396 // ── Approvals / Questions (reverse-RPC resolves) ────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/client.ts193 // ── Probes + model catalog ─────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/client.ts210 // ── HTTP convenience surface ────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/client.ts253 // ── Terminals ──────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/client.ts273 // ── Workspaces + folder picker ──────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/client.ts367 // ── WS lifecycle ────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/client.ts458 // ── WS observation ──────────────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/client.ts484 // ── Terminal WS controls ───────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/client.ts552 // ── Reverse RPC (approval + question) ───────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/client.ts602 // ── High-level convenience ──────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/client.ts658 // ── internals ───────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/index.ts71// ── server-v2 SDK (additive) ──────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/v2/transport/ws.ts243// ── Wire frame shapes (client view; not validated) ─────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/v2/resources/types.ts14// ── Shared wire shapes ─────────────────────────────────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/v2/resources/types.ts79// ── Precise override maps (keyed by action name) ───────────────────────────COMMENT
MEDIUMpackages/server-e2e/src/v2/resources/session.ts64 // ── Flattened `session` resource ─────────────────────────────────────────COMMENT
MEDIUMpackages/klient/examples/media-recovery.ts105// ── fixtures ─────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/klient/examples/media-recovery.ts199// ── main ─────────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/kaos/test/ssh.test.ts531 // ── stat(): the one method that already wraps errors. ────────────────COMMENT
MEDIUMpackages/kaos/test/ssh.test.ts625 // in ssh.ts so every method gets the same wrapping for free. ─────────COMMENT
MEDIUMpackages/kaos/test/ssh.test.ts848 // ── path helpers ────────────────────────────────────────────────────COMMENT
MEDIUMpackages/kaos/test/ssh.test.ts857 // ── stat + buildStMode variants ─────────────────────────────────────COMMENT
144 more matches not shown…
Over-Commented Block122 hits · 122 pts
SeverityFileLineSnippetContext
LOWpackages/acp-adapter/src/session.ts921 sessionId: string,COMMENT
LOWpackages/acp-adapter/src/session.ts941 // delta → tool_call_update" mapping puts updates on the wireCOMMENT
LOWpackages/acp-adapter/src/auth-methods.ts1// Advertise the `terminal-auth` method to ACP clients. Two paths coexist:COMMENT
LOWpackages/acp-adapter/src/slash.ts1// Slash-command detection for ACP `session/prompt`.COMMENT
LOWpackages/acp-adapter/src/server.ts261 // transparent passthrough for unknown fields (seeCOMMENT
LOWpackages/acp-adapter/src/server.ts301 session,COMMENT
LOWpackages/oauth/src/oauth-manager.ts301 const token = initial.token;COMMENT
LOWpackages/kap-server/src/start.ts221 passwordConfigured = passwordHash !== undefined;COMMENT
LOW…-server/src/transport/ws/v1/sessionEventBroadcaster.ts521 ) {COMMENT
LOWpackages/kap-server/src/routes/tasks.ts281COMMENT
LOWpackages/kaos/test/local.test.ts541 //COMMENT
LOWpackages/kaos/test/e2e/ssh-resolve-path.test.ts1import type { Client, SFTPWrapper, Stats as SFTPStats } from 'ssh2';COMMENT
LOWpackages/kaos/test/e2e/exec-edge-cases.test.ts1import { mkdtemp, realpath, rm } from 'node:fs/promises';COMMENT
LOWpackages/kaos/src/ssh.ts641 const [currentPattern, ...remainingParts] = patternParts;COMMENT
LOWpackages/kaos/src/local.ts321 yield* this._globWalk(resolved, patternParts, caseSensitive, initVisited);COMMENT
LOWpackages/kaos/src/local.ts361 // remaining pattern parts (or yield basePath itself when `**`COMMENT
LOWpackages/pi-tui/test/editor.test.ts4201 });COMMENT
LOWpackages/kosong/src/errors.ts141 // upstream gateway that forwards the original error only as text, with noCOMMENT
LOWpackages/kosong/src/errors.ts161COMMENT
LOWpackages/kosong/src/errors.ts381 return REQUEST_TOO_LARGE_MESSAGE_PATTERNS.some((pattern) => pattern.test(lowerMessage));COMMENT
LOWpackages/kosong/src/errors.ts401 // `tool_call_id` with no matching `tool_calls` entry in the precedingCOMMENT
LOWpackages/kosong/src/providers/anthropic.ts581 // Signed: emit the block with its signature. api.anthropic.com requires aCOMMENT
LOWpackages/kosong/src/providers/anthropic.ts1021 // Convert messages, then merge consecutive user messages into one. StrictCOMMENT
LOWpackages/node-sdk/src/index.ts61COMMENT
LOWpackages/agent-core/test/tools/image-compress.test.ts1561 // misrepresented. This proves the two tests above can fail (the probeCOMMENT
LOWpackages/agent-core/test/tools/rg-locator.test.ts341COMMENT
LOWpackages/agent-core/test/tools/cron/cron-list.test.ts281 it('one-shot nextFireAt is anchored at createdAt, not nowMs (pending today’s slot)', async () => {COMMENT
LOW…ent-core/test/agent/bg-idle-notification-repro.test.ts241 it('RESUME: terminal bg tasks discovered on reconcile are SILENTLY injected (no auto-turn)', async () => {COMMENT
LOW…agent-core/test/agent/background/agent-timeout.test.ts61 });COMMENT
LOW…agent-core/test/agent/background/agent-timeout.test.ts81 vi.useFakeTimers({ toFake: ['setTimeout', 'clearTimeout'] });COMMENT
LOW…ore/test/agent/compaction/anthropic-compliance.test.ts1// Anthropic-compliance smoke tests for compaction.COMMENT
LOW…ore/test/agent/compaction/compaction-scenarios.test.ts1// Compaction scenario + probe tests.COMMENT
LOWpackages/agent-core/src/errors.ts1// Barrel re-export so #/errors resolves to a single .ts file (the firstCOMMENT
LOWpackages/agent-core/src/index.ts161// that need the emitter `Event<T>` type import it from the explicit sub-pathCOMMENT
LOWpackages/agent-core/src/tools/cron/scheduler.ts381 } else {COMMENT
LOWpackages/agent-core/src/tools/cron/cron-create.ts201 }COMMENT
LOWpackages/agent-core/src/agent/records/types.ts21COMMENT
LOWpackages/agent-core/src/agent/context/projector.ts121// by a matching `tool_result` in the immediately following message(s). ACOMMENT
LOWpackages/agent-core/src/agent/context/projector.ts141// trailing-open-exchange trim plus replay's interrupted-result synthesis own thatCOMMENT
LOWpackages/agent-core/src/agent/context/index.ts241 }COMMENT
LOWpackages/agent-core/src/agent/context/index.ts321 role: 'user',COMMENT
LOWpackages/agent-core/src/agent/compaction/full.ts321 try {COMMENT
LOWpackages/agent-core/src/agent/compaction/full.ts421 let summary: string | undefined;COMMENT
LOWpackages/agent-core/src/agent/compaction/full.ts581 // Loaded dynamic tool schemas are deliberately NOT rebuilt: compactionCOMMENT
LOWpackages/agent-core/src/agent/compaction/micro.ts61 // const cacheMissed = cacheAgeMs !== null && cacheAgeMs >= config.cacheMissedThresholdMs;COMMENT
LOWpackages/agent-core/src/agent/compaction/micro.ts81 // // two compaction paths can be compared on the same axis.COMMENT
LOWpackages/agent-core/src/agent/compaction/micro.ts101 // previous_cutoff: previousCutoff,COMMENT
LOWpackages/agent-core/src/agent/compaction/micro.ts121 // for (const msg of messages) {COMMENT
LOWpackages/agent-core/src/agent/turn/index.ts601 this.closeAbandonedToolExchange(ended);COMMENT
LOWpackages/agent-core/src/agent/turn/index.ts801 // the turn so the goal driver blocks the goal at the boundary.COMMENT
LOW…ages/agent-core/src/agent/permission/policies/index.ts41 new AutoModeApprovePermissionPolicy(agent),COMMENT
LOW…nt-core/src/services/coreProcess/coreProcessService.ts81 // undefined` and synthesizes a closure that ALWAYS throwsCOMMENT
LOW…nt-core/src/services/coreProcess/coreProcessService.ts241COMMENT
LOWpackages/agent-core/src/services/message/transcript.ts261 // ContextMemory.applyCompaction. Re-deriving it from the fullCOMMENT
LOW…nt-core/src/services/authSummary/authSummaryService.ts141COMMENT
LOWpackages/agent-core/src/session/git-context.ts61 // empty block (the subagent works without git context, same as before):COMMENT
LOWpackages/minidb/bench/measure-session-memory.ts1// bench/measure-session-memory.tsCOMMENT
LOWpackages/minidb/bench/message-composed.ts1// bench/message-composed.tsCOMMENT
LOWpackages/minidb/bench/session-children.ts1// bench/session-children.tsCOMMENT
LOWpackages/minidb/bench/session-children.ts21// -> O(N log N)COMMENT
62 more matches not shown…
Fake / Example Data41 hits · 56 pts
SeverityFileLineSnippetContext
LOWpackages/pi-tui/test/markdown.test.ts165 `1. Lorem ipsum dolor sit amet.CODE
LOWpackages/pi-tui/test/markdown.test.ts165 `1. Lorem ipsum dolor sit amet.CODE
LOWpackages/pi-tui/test/markdown.test.ts182 "1. Lorem ipsum dolor sit amet.",CODE
LOWpackages/pi-tui/test/markdown.test.ts182 "1. Lorem ipsum dolor sit amet.",CODE
LOWpackages/pi-tui/test/markdown.test.ts1271 assert.ok(joinedPlain.includes("user@example.com"), "Should contain email");CODE
LOWpackages/pi-tui/test/editor.test.ts1246 const chunks = wordWrapLine("Lorem ipsum dolor sit amet, consectetur", 30);CODE
LOWpackages/pi-tui/test/editor.test.ts1246 const chunks = wordWrapLine("Lorem ipsum dolor sit amet, consectetur", 30);CODE
LOWpackages/pi-tui/test/editor.test.ts1249 assert.strictEqual(chunks[0]!.text, "Lorem ipsum dolor sit ");CODE
LOWpackages/pi-tui/test/editor.test.ts1254 const chunks = wordWrapLine("Lorem ipsum dolor sit amet, consectetur", 30);CODE
LOWpackages/pi-tui/test/editor.test.ts1254 const chunks = wordWrapLine("Lorem ipsum dolor sit amet, consectetur", 30);CODE
LOWpackages/pi-tui/test/editor.test.ts1257 assert.strictEqual(chunks[0]!.text, "Lorem ipsum dolor sit ");CODE
LOWpackages/pi-tui/test/editor.test.ts1262 const chunks = wordWrapLine("Lorem ipsum dolor sit amet, consectetur", 30);CODE
LOWpackages/pi-tui/test/editor.test.ts1262 const chunks = wordWrapLine("Lorem ipsum dolor sit amet, consectetur", 30);CODE
LOWpackages/pi-tui/test/editor.test.ts1265 assert.strictEqual(chunks[0]!.text, "Lorem ipsum dolor sit ");CODE
LOWpackages/pi-tui/test/editor.test.ts1271 const chunks = wordWrapLine("Lorem ipsum dolor sit amet, consectetur", 30);CODE
LOWpackages/pi-tui/test/editor.test.ts1271 const chunks = wordWrapLine("Lorem ipsum dolor sit amet, consectetur", 30);CODE
LOWpackages/pi-tui/test/editor.test.ts1274 assert.strictEqual(chunks[0]!.text, "Lorem ipsum dolor sit ");CODE
LOWpackages/pi-tui/test/editor.test.ts1280 const chunks = wordWrapLine("Lorem ipsum dolor sit amet, consectetur", 30);CODE
LOWpackages/pi-tui/test/editor.test.ts1280 const chunks = wordWrapLine("Lorem ipsum dolor sit amet, consectetur", 30);CODE
LOWpackages/pi-tui/test/editor.test.ts1283 assert.strictEqual(chunks[0]!.text, "Lorem ipsum dolor sit ");CODE
LOWpackages/pi-tui/test/editor.test.ts1289 const chunks = wordWrapLine("Lorem ipsum dolor sit amet, consectetur", 30);CODE
LOWpackages/pi-tui/test/editor.test.ts1289 const chunks = wordWrapLine("Lorem ipsum dolor sit amet, consectetur", 30);CODE
LOWpackages/pi-tui/test/editor.test.ts1292 assert.strictEqual(chunks[0]!.text, "Lorem ipsum dolor sit ");CODE
LOWpackages/pi-tui/src/components/markdown.ts547 // For mailto: links strip the prefix (autolinked emails use text="foo@bar.com"COMMENT
LOW…ckages/migration-legacy/test/sessions/classify.test.ts27 expect(await classifySessionDir(p)).toBe('placeholder');CODE
LOWpackages/migration-legacy/src/sessions/classify.ts6export type SessionClass = 'placeholder' | 'empty' | 'malformed' | 'real';CODE
LOWpackages/migration-legacy/src/sessions/classify.ts16 if (entries.length === 1 && entries[0] === 'test') return 'placeholder';CODE
LOWpackages/migration-legacy/src/sessions/index.ts83 if (cls === 'placeholder') {CODE
LOW…est/tui/components/editor/wrapping-select-list.test.ts55 'lorem ipsum dolor sit amet consectetur adipiscing elit sed do eiusmod tempor incididunt',CODE
LOW…est/tui/components/editor/wrapping-select-list.test.ts55 'lorem ipsum dolor sit amet consectetur adipiscing elit sed do eiusmod tempor incididunt',CODE
LOW…est/tui/components/editor/wrapping-select-list.test.ts61 ' init[D] lorem ipsum dolor sit amet consectetur adipiscing elit sed do',CODE
LOW…est/tui/components/editor/wrapping-select-list.test.ts61 ' init[D] lorem ipsum dolor sit amet consectetur adipiscing elit sed do',CODE
LOW…est/tui/components/editor/wrapping-select-list.test.ts67 const description = 'lorem ipsum dolor sit amet consectetur adipiscing elit '.repeat(4).trim();CODE
LOW…est/tui/components/editor/wrapping-select-list.test.ts67 const description = 'lorem ipsum dolor sit amet consectetur adipiscing elit '.repeat(4).trim();CODE
LOW…est/tui/components/editor/wrapping-select-list.test.ts74 expect(lines[1]).toMatch(/^ {2}init\[D\] {8}lorem ipsum/);CODE
LOW…est/tui/components/editor/wrapping-select-list.test.ts80 const description = 'lorem ipsum dolor sit amet consectetur adipiscing elit '.repeat(4).trim();CODE
LOW…est/tui/components/editor/wrapping-select-list.test.ts80 const description = 'lorem ipsum dolor sit amet consectetur adipiscing elit '.repeat(4).trim();CODE
LOW…est/tui/components/editor/wrapping-select-list.test.ts86 expect(lines[0]).toMatch(/^\[S\]→ goal {8}lorem ipsum/);CODE
LOWapps/kimi-web/src/components/ui/Textarea.vue32 :placeholder="placeholder"CODE
LOWapps/kimi-web/src/components/ui/Input.vue49 :placeholder="placeholder"CODE
LOWapps/kimi-web/src/components/chat/Composer.vue906 :placeholder="placeholder"CODE
Magic Placeholder Names9 hits · 45 pts
SeverityFileLineSnippetContext
HIGHAGENTS.md73- In public text and test data, replace real internal identifiers with neutral placeholders such as `example.com`, `examCODE
HIGHCLAUDE.md73- In public text and test data, replace real internal identifiers with neutral placeholders such as `example.com`, `examCODE
HIGH.agents/skills/gen-docs/SKILL.md78- **Public examples**: Never write real internal endpoints, key names, account names, or service names into docs. Use neCODE
HIGH.agents/skills/gen-changesets/SKILL.md73- Do not include real internal endpoints, key names, account names, or service names. If an example is needed, use neutrCODE
HIGH.agents/skills/sync-changelog/SKILL.md132Public-text rule: do not copy real internal endpoints, key names, account names, or service names into docs changelogs. CODE
HIGH.agents/skills/translate-docs/SKILL.md58- **Public examples**: Do not introduce real internal endpoints, key names, account names, or service names while translCODE
HIGHdocs/zh/configuration/env-vars.md92export KIMI_MODEL_API_KEY="YOUR_API_KEY"CODE
HIGHdocs/en/configuration/env-vars.md92export KIMI_MODEL_API_KEY="YOUR_API_KEY"CODE
HIGHapps/kimi-code/test/cli/doctor.test.ts59api_key = "YOUR_API_KEY"CODE
Hallucination Indicators3 hits · 30 pts
SeverityFileLineSnippetContext
CRITICAL…es/agent-core/test/agent/background/rpc-events.test.ts179 const trackCall = agent.telemetry.track.mock.calls.find(CODE
CRITICAL…i/controllers/session-event-handler-goal-queue.test.ts172 const component = host.state.transcriptContainer.addChild.mock.calls.at(-1)?.[0];CODE
CRITICALapps/kimi-code/src/tui/controllers/btw-panel.ts142 if (!this.host.state.btwPanelContainer.children.includes(panel)) return;CODE
Verbosity Indicators11 hits · 23 pts
SeverityFileLineSnippetContext
LOWpackages/node-sdk/examples/t8-race-direct.ts37 // Step 1: check indexCOMMENT
LOWpackages/node-sdk/examples/t8-race-direct.ts45 // Step 2: simulate "isDirectory" check + mkdir gapCOMMENT
LOWpackages/node-sdk/examples/t8-race-direct.ts54 // Step 3: append indexCOMMENT
LOW…gent-core/test/loop/tool-exchange-fallback.e2e.test.ts465 // Step 1: normal projection rejected, degraded resend recovers.COMMENT
LOW…gent-core/test/loop/tool-exchange-fallback.e2e.test.ts468 // Step 2: built straight from the degraded projection, not the normal one.COMMENT
LOWpackages/agent-core/src/session/git-context.ts52 // Step 1: is this a git repo? `rev-parse` is the authoritative probe — itCOMMENT
LOWpackages/agent-core/src/session/git-context.ts69 // Step 2: collect context in parallel. Every probe is optional — gitCOMMENT
LOWapps/vis/server/test/lib/context-projector.test.ts458 // Step 1: append u1, u2 then undo(1) → removes u2, leaves [u1, <undo marker>].COMMENT
LOWapps/vis/server/test/lib/context-projector.test.ts459 // Step 2: append u3, u4 → array is [u1, <undo marker>, u3, u4].COMMENT
LOWapps/vis/server/test/lib/context-projector.test.ts493 // Step 1: append tool c0, user u1 then undo(1) → removes u1, leavesCOMMENT
LOWapps/vis/server/test/lib/context-projector.test.ts495 // Step 2: append tool c1 → array is [c0, <undo marker>, c1].COMMENT
Structural Annotation Overuse11 hits · 23 pts
SeverityFileLineSnippetContext
LOWpackages/node-sdk/examples/t8-race-direct.ts37 // Step 1: check indexCOMMENT
LOWpackages/node-sdk/examples/t8-race-direct.ts45 // Step 2: simulate "isDirectory" check + mkdir gapCOMMENT
LOWpackages/node-sdk/examples/t8-race-direct.ts54 // Step 3: append indexCOMMENT
LOW…gent-core/test/loop/tool-exchange-fallback.e2e.test.ts465 // Step 1: normal projection rejected, degraded resend recovers.COMMENT
LOW…gent-core/test/loop/tool-exchange-fallback.e2e.test.ts468 // Step 2: built straight from the degraded projection, not the normal one.COMMENT
LOWpackages/agent-core/src/session/git-context.ts52 // Step 1: is this a git repo? `rev-parse` is the authoritative probe — itCOMMENT
LOWpackages/agent-core/src/session/git-context.ts69 // Step 2: collect context in parallel. Every probe is optional — gitCOMMENT
LOWapps/vis/server/test/lib/context-projector.test.ts458 // Step 1: append u1, u2 then undo(1) → removes u2, leaves [u1, <undo marker>].COMMENT
LOWapps/vis/server/test/lib/context-projector.test.ts459 // Step 2: append u3, u4 → array is [u1, <undo marker>, u3, u4].COMMENT
LOWapps/vis/server/test/lib/context-projector.test.ts493 // Step 1: append tool c0, user u1 then undo(1) → removes u1, leavesCOMMENT
LOWapps/vis/server/test/lib/context-projector.test.ts495 // Step 2: append tool c1 → array is [c0, <undo marker>, c1].COMMENT
AI Slop Vocabulary8 hits · 21 pts
SeverityFileLineSnippetContext
MEDIUMpackages/kap-server/src/services/auth/tokenStore.ts45 // robust even on filesystems with coarse (1s) mtime resolution.COMMENT
MEDIUMpackages/node-sdk/src/sdk-rpc-client.ts20import { KimiHarness } from '#/kimi-harness';CODE
MEDIUMpackages/node-sdk/src/index.ts1export { KimiHarness } from '#/kimi-harness';CODE
MEDIUMpackages/node-sdk/src/index.ts2export type { KimiHarnessRuntimeOptions } from '#/kimi-harness';CODE
MEDIUM…s/agent-core/test/agent/cron/agent-integration.test.ts59 // precise unit being asserted, and it stays robust if the loop /COMMENT
MEDIUMpackages/agent-core/src/tools/support/rg-locator.ts298 // Match on basename (not full path) — keeps the matcher robustCOMMENT
MEDIUMpackages/minidb/test/e2e/crash-recovery.test.ts28 // the kill clock, so the test is robust even under heavy CPU contention.COMMENT
MEDIUMpackages/minidb/test/e2e/compaction-race.test.ts79 // measuring absolute timing, so the assertion stays robust under CPU/IO loadCOMMENT
Modern AI Meta-Vocabulary8 hits · 17 pts
SeverityFileLineSnippetContext
MEDIUMplugins/official/kimi-datasource/SKILL.md61### 例 2:用户问"找几篇 retrieval augmented generation 的综述"COMMENT
MEDIUMpackages/kosong/CHANGELOG.md35- [#1131](https://github.com/MoonshotAI/kimi-code/pull/1131) [`76c643b`](https://github.com/MoonshotAI/kimi-code/commit/CODE
MEDIUMpackages/agent-core/CHANGELOG.md74- [#1131](https://github.com/MoonshotAI/kimi-code/pull/1131) [`76c643b`](https://github.com/MoonshotAI/kimi-code/commit/CODE
MEDIUMpackages/agent-core/CHANGELOG.md378- [#211](https://github.com/MoonshotAI/kimi-code/pull/211) [`54590d3`](https://github.com/MoonshotAI/kimi-code/commit/54CODE
MEDIUMpackages/agent-core/CHANGELOG.md484- [#17](https://github.com/MoonshotAI/kimi-code/pull/17) [`bfbd522`](https://github.com/MoonshotAI/kimi-code/commit/bfbdCODE
MEDIUMapps/kimi-code/CHANGELOG.md620- [#1131](https://github.com/MoonshotAI/kimi-code/pull/1131) [`76c643b`](https://github.com/MoonshotAI/kimi-code/commit/CODE
MEDIUMapps/kimi-code/CHANGELOG.md1350- [#211](https://github.com/MoonshotAI/kimi-code/pull/211) [`54590d3`](https://github.com/MoonshotAI/kimi-code/commit/54CODE
MEDIUMapps/kimi-code/CHANGELOG.md1538- [#17](https://github.com/MoonshotAI/kimi-code/pull/17) [`bfbd522`](https://github.com/MoonshotAI/kimi-code/commit/bfbdCODE
Slop Phrases1 hit · 2 pts
SeverityFileLineSnippetContext
LOWapps/kimi-code/src/tui/utils/printable-key.ts18 * The module's existence is itself the "don't forget to decode" constraint:COMMENT