ADR lifecycle management — create, index, reconcile, supersede, check compliance, and link Architecture Decision Records to code via AgentDB hierarchical store…

ADR lifecycle management -- create, index, reconcile, supersede, and link Architecture Decision Records to code.
Manages Architecture Decision Records through their full lifecycle (proposed, accepted, deprecated, superseded). ADRs are stored as markdown files in docs/adr/ and indexed in AgentDB with causal edges tracking supersedes/amends/depends-on relationships. Includes compliance checking that scans git diffs for ADR violations, and reconciliation (adr-reindex) for ADRs deleted from disk (#2666).
claude --plugin-dir plugins/ruflo-adr
| Agent | Model | Role |
|---|---|---|
adr-architect | sonnet | ADR lifecycle management, code-ADR linking via grep/blame, AgentDB graph storage |
| Skill | Usage | Description |
|---|---|---|
adr-create | /adr-create <title> | Create a new ADR with sequential numbering and AgentDB registration |
adr-index | /adr-index | Build or rebuild the ADR index and dependency graph in AgentDB (add/update only — never removes) |
adr-review | /adr-review [--branch BRANCH] | Review code changes against accepted ADRs for compliance violations |
adr-verify | /adr-verify | Read back adr-patterns + adr-edges namespaces, surface dangling refs / supersede cycles / status mismatches; exits 1 on cycles |
adr-reindex | /adr-reindex | Reconcile a deleted ADR file: drop-and-rebuild adr-patterns + adr-edges from what's on disk right now |
# Lifecycle
adr create <title>
adr list
adr status <adr-id> <new-status>
adr supersede <old-id> <new-id>
# Compliance
adr check # Scan recent git changes for ADR violations
adr graph # Show ADR dependency graph
adr search <query> # Semantic search across ADRs
proposed --> accepted --> deprecated
\--> superseded by ADR-XXX
Relationships tracked as causal edges: supersedes, amends, depends-on, related.
Body relationship fields accept qualifiers such as Amends by scope: or Depends-on / confirms:, and Relates is an alias for Related. Wrapped lists may continue on lines containing only ADR references (including Markdown links) and separators. Narrative continuation is not scanned for relationships; declare additional relationships in another bold field.
@claude-flow/cli v3.6 major+minor.bash plugins/ruflo-adr/scripts/smoke.sh is the contract.This plugin owns the adr-patterns AgentDB namespace. It defers to ruflo-agentdb ADR-0001 §"Namespace convention" for naming rules. Reserved namespaces (pattern, claude-memories, default) MUST NOT be shadowed.
adr-patterns follows kebab-case <plugin-stem>-<intent> per the convention. The plugin uses it for semantic ADR search and for cross-project pattern transfer (via hooks_transfer in ruflo-intelligence).
bash plugins/ruflo-adr/scripts/smoke.sh
# Expected: "22 passed, 0 failed"
ADR-0001 — ruflo-adr plugin contract (pinning, namespace coordination, smoke as contract)ADR-0002 — Reconcile deleted ADRs (hard-delete primitive + drop-and-rebuild reindex)ruflo-agentdb — namespace convention owner; backing store for the ADR graphruflo-ddd — document domain decisions as ADRsruflo-sparc — Architecture phase (Phase 3) produces ADRsruflo-migrations — schema change decisions recorded as ADRsruflo-jujutsu — ADR-aware diff analysis on PRsruflo-intelligence — hooks_transfer ships ADR patterns across projectsMIT
ADR also ships as a function-hook mod (ADR-445 pattern; hooks in hooks/, loaded with the plugin). No network, no process, no model call.
agentdb_hierarchical-store, agentdb_causal-edge or memory_store into an adr* namespace) that holds a key, token or password. It only tightens: it never allows anything the session would deny, and the refusal never repeats the secret. Turn it off with the guard option./adr-mod: answered locally. /adr-mod status, /adr-mod scan <text>, /adr-mod format..claude-flow/adr-mod/status.json (version, updatedMs, counters), written at session start and whenever a call is refused; the console reads it.userConfig): guard (on by default).Test: claude plugin validate plugins/ruflo-adr, claude plugin test plugins/ruflo-adr, and bash plugins/ruflo-adr/scripts/smoke.sh.
The separate .codex-plugin/plugin.json selects hooks/codex-hooks.json, replacing the Claude-only module entry for Codex. Claude's manifest and register.ts remain unchanged. The synchronous native PreToolUse adapter bundles the existing pure guard and shared secret screen; it preserves their tool/namespace scope and emits the native permission-denial envelope before a guarded write. SessionStart and guarded calls maintain private per-session counters in PLUGIN_DATA; the existing version-1 project status file remains a best-effort courtesy view. Status failure does not permit a denied write. Guarding is enabled for the native adapter.
Existing skills and command files remain available. Claude's dynamic $.command.register / command.run mod interception has no native command-hook equivalent: Codex does not get that interception. The same deterministic local command helpers are available explicitly via node <plugin-root>/hooks/codex-hook.cjs --command status (and the helper's existing subcommands). This is guard/status compatibility, not full SDK-mod parity.
Maintainers rebuild the committed standalone bundles with ESBUILD=<esbuild executable> node scripts/build-codex-mod-hooks.mjs, then run node --test tests/plugins/codex-mod-hooks.test.mjs. Set ESBUILD in that test run to check byte reproducibility using the same installed builder. Run scripts/sync-mod-screen.mjs --check before bundling when the shared screen changes. The adapters need Node.js and contain no runtime SDK dependency.
This source change requires a released upstream package or an explicitly owned source projection to reach installations. It does not patch foreign cache entries, pin upstream updates, disable plugins, or claim an already published repair.
Release both host manifests with the same patch version. Codex 0.160's published remote-bundle sync skips downloading a release whose version equals the installed version; merging same-version source does not establish automatic cache refresh. Its explicit native plugin install replaces the cached root atomically even at the same version. An owned projection must therefore refresh its upstream source generation and explicitly reinstall it; refreshing a marketplace catalog alone is not installation proof. No foreign cache entry should be edited in place.
hooks/register.ts 58 lines1import type { Hook, Register } from 'claude-code'
2
3import { answer } from './command'
4import { owns, verdict } from './guard'
5import { readOptions } from './options'
6import { newStats, STATUS_PATH, statusText, type Stats } from './status'
7import type { ModOptions } from './options'
8
9type Dollar = Parameters<Hook<'session.start'>>[0]
10
11/** Everything one session of the mod keeps: its settings, counters and the project root. */
12type Session = { readonly opts: ModOptions; readonly stats: Stats; root?: string }
13
14async function flush($: Dollar, s: Session): Promise<void> {
15 if (s.root === undefined) return
16 try {
17 await $.fs.write(`${s.root}/${STATUS_PATH}`, statusText(s.stats, s.opts, await $.clock.now()))
18 } catch {
19 /* the status file is a courtesy */
20 }
21}
22
23/**
24 * ADR as a mod (ADR-445 pattern): a tighten-only guard on ADR writes (`agentdb_hierarchical-store`, `agentdb_causal-edge`, `memory_store` into an `adr*` namespace), `/adr-mod`, and a status file the console reads.
25 * No network, no process: only the hooks API.
26 */
27export const register: Register = (on, options) => {
28 const s: Session = { opts: readOptions(options), stats: newStats() }
29
30 on('session.start', async ($, e, next) => {
31 const result = await next(e)
32 s.root = (await $.session.root()) as string | undefined
33 s.stats.startedMs = await $.clock.now()
34 try {
35 await $.command.register({ name: 'adr-mod', description: 'ADR mod: status, scan <text>, format' })
36 } catch {
37 /* a name taken by another plugin must not stop the mod */
38 }
39 await flush($, s)
40 return result
41 })
42
43 if (s.opts.guard) {
44 on('tool.call', async ($, e, next) => {
45 if (!owns(e.tool, e)) return next(e)
46 s.stats.calls++
47 const reason = verdict(e.tool, e)
48 if (reason === undefined) return next(e)
49 s.stats.blocked++
50 await flush($, s)
51 return { deny: reason }
52 })
53 }
54
55 /** `/adr-mod` (a markdown command of the plugin cannot be answered by a hook, so the mod owns this name). */
56 on('command.run', { command: 'adr-mod' }, async (_$, e) => ({ text: answer(typeof e.args === 'string' ? e.args : '', { opts: s.opts, stats: s.stats }) }))
57}
58hooks/command.ts 32 lines1import { scan } from './screen'
2import type { ModOptions } from './options'
3import type { Stats } from './status'
4
5/** `/adr-mod` is answered locally and takes no model turn. */
6export type CommandDeps = { readonly opts: ModOptions; readonly stats: Stats }
7
8const HELP = ['/adr-mod status', '/adr-mod scan <text>', '/adr-mod format'].join('\n')
9
10export function answer(args: string, deps: CommandDeps): string {
11 const [verb = '', ...rest] = args.trim().split(/\s+/)
12 const arg = rest.join(' ')
13 const { opts, stats } = deps
14
15 if (verb === '' || verb === 'help') return HELP
16
17 if (verb === 'status') {
18 return `guard ${opts.guard ? 'on' : 'off'} · calls guarded ${stats.calls} · blocked ${stats.blocked}`
19 }
20
21 if (verb === 'scan') {
22 if (arg === '') return 'usage: /adr-mod scan <text>'
23 const found = scan(arg)
24 const parts = [found.secrets.length ? `secrets: ${found.secrets.join(', ')}` : '', found.injection.length ? `injection phrasing: ${found.injection.join(', ')}` : ''].filter(Boolean)
25 return parts.length ? `The guard would refuse a write of that (${parts.join('; ')}).` : 'Nothing found: the guard would let that through.'
26 }
27
28 if (verb === 'format') return 'An ADR carries: Status (proposed, accepted, deprecated, superseded), Context, Decision, Consequences. Relations: supersedes, amends, depends-on, related. Create with /adr-create, index with /adr-index.'
29
30 return `Unknown: ${verb}\n${HELP}`
31}
32hooks/guard.ts 44 lines1import { hasSecret } from './screen'
2import { textsOf } from './screen'
3export { textsOf }
4
5/** `mcp__<server>__<tool>` into its two halves; tool names never hold a double underscore. */
6export function splitName(name: string): { server: string; tool: string } | undefined {
7 if (!name.startsWith('mcp__')) return undefined
8 const at = name.lastIndexOf('__')
9 return at > 5 ? { server: name.slice(5, at), tool: name.slice(at + 2) } : undefined
10}
11
12const namespaceOf = (input: unknown): string => {
13 const ns = (input as { namespace?: unknown } | null)?.namespace
14 return typeof ns === 'string' ? ns : ''
15}
16
17/** An ADR entry id as the plugin's skills write it: `mem:ADR-0007`, `ADR-0007`. */
18const ADR_ID = /^(?:mem:)?ADR-/i
19
20const field = (input: unknown, key: string): string => {
21 const v = (input as Record<string, unknown> | null)?.[key]
22 return typeof v === 'string' ? v : ''
23}
24
25/**
26 * True for the tool calls this plugin guards: ADR writes. `memory_store` into an `adr*` namespace; `agentdb_hierarchical-store` (which has no namespace
27 * field, so the entry is told apart by its `mem:ADR-NNN` key) and `agentdb_causal-edge` (by its `mem:ADR-NNN` ends), as the adr-create skill calls them.
28 */
29export function owns(tool: string, input: unknown): boolean {
30 const parts = splitName(tool)
31 const name = parts?.tool ?? tool
32 const adrNamespace = /adr/i.test(namespaceOf(input))
33 if (name === 'memory_store') return adrNamespace
34 if (name === 'agentdb_hierarchical-store') return adrNamespace || ADR_ID.test(field(input, 'key'))
35 if (name === 'agentdb_causal-edge') return adrNamespace || ADR_ID.test(field(input, 'sourceId')) || ADR_ID.test(field(input, 'targetId'))
36 return false
37}
38
39/** The reason a call is refused, or undefined when it may go. Never names or echoes the secret. */
40export function verdict(tool: string, input: unknown): string | undefined {
41 if (!owns(tool, input)) return undefined
42 return textsOf(input).some(hasSecret) ? "ruflo-adr: this ADR write holds what looks like a secret (a key, token or password). An ADR records a decision; name where the secret lives, not its value." : undefined
43}
44hooks/options.ts 19 lines1import type { PluginOptions } from 'claude-code'
2
3/** The plugin's `userConfig`, validated: a bad value is the default (guard on). */
4export type ModOptions = {
5 readonly guard: boolean
6}
7
8// BEGIN SHARED FLAG (generated by scripts/sync-mod-screen.mjs; edit plugins/ruflo-agentdb/hooks/options.ts)
9export const flag = (value: unknown, fallback: boolean) =>
10 value === true || value === 'true' || value === 'on' ? true : value === false || value === 'false' || value === 'off' ? false : fallback
11// END SHARED FLAG
12
13export function readOptions(options: PluginOptions | undefined): ModOptions {
14 const o = options ?? {}
15 return {
16 guard: flag(o.guard, true),
17 }
18}
19hooks/status.ts 12 lines1/** Counters the mod keeps for the session and writes to `.claude-flow/adr-mod/status.json` for the console. */
2export type Stats = { calls: number; blocked: number; startedMs: number }
3
4export const newStats = (): Stats => ({ calls: 0, blocked: 0, startedMs: 0 })
5
6export const STATUS_PATH = '.claude-flow/adr-mod/status.json'
7
8/** The file's text; `version` lets the console refuse a shape it does not know. */
9export function statusText(stats: Stats, mode: { guard: boolean }, nowMs: number): string {
10 return `${JSON.stringify({ version: 1, updatedMs: nowMs, mod: 'adr', guard: mode.guard, ...stats }, null, 2)}\n`
11}
12hooks/screen.ts 261 lines1/**
2 * Pure text screening for the AgentDB mod (ADR-445). Two jobs: find secrets (so none is stored) and find prompt-injection phrasing (so
3 * retrieved memory cannot instruct the model). Findings are NAMES only: the matched text is never returned, logged or counted by value.
4 */
5
6// BEGIN SHARED SCREEN (generated from plugins/ruflo-agentdb/hooks/screen.ts by scripts/sync-mod-screen.mjs; do not edit in a copy)
7export type Rules = readonly (readonly [string, RegExp])[]
8
9/** The secret shapes every mod screens for. A plugin adds its own after these, outside the markers. */
10export const COMMON_SECRETS: Rules = [
11 ['private key', /-----BEGIN [A-Z ]*PRIVATE KEY-----/],
12 ['aws access key', /\b(?:AKIA|ASIA)[0-9A-Z]{16}\b/],
13 ['github token', /\b(?:gh[pousr]_[A-Za-z0-9]{30,}|github_pat_[A-Za-z0-9_]{40,})\b/],
14 ['slack token', /\bxox[abprs]-[A-Za-z0-9-]{10,}/],
15 ['slack webhook', /\bhooks\.slack\.com\/services\/T[A-Z0-9]{6,}\/B[A-Z0-9]{6,}\/[A-Za-z0-9]{16,}/],
16 ['google api key', /\bAIza[0-9A-Za-z_-]{35}\b/],
17 ['anthropic or openai key', /\bsk-(?:(?:ant|proj|svcacct|admin)-[A-Za-z0-9_-]{20,}|(?=[A-Za-z]{0,40}\d)[A-Za-z0-9]{32,})/],
18 ['stripe key', /\b[rs]k_live_[A-Za-z0-9]{16,}/],
19 ['npm token', /\bnpm_[A-Za-z0-9]{36}\b/],
20 ['huggingface token', /\bhf_[A-Za-z0-9]{30,}\b/],
21 ['sendgrid key', /\bSG\.[A-Za-z0-9_-]{16,}\.[A-Za-z0-9_-]{16,}/],
22 ['twilio key', /\bSK[0-9a-f]{32}\b/],
23 ['jwt', /\beyJ[A-Za-z0-9_-]{8,}\.eyJ[A-Za-z0-9_-]{8,}\.[A-Za-z0-9_-]{8,}/],
24 ['bearer token', /\bBearer\s+([A-Za-z0-9._~+/=-]{24,})/],
25 ['database url with credentials', /\b[a-z][a-z0-9+.-]{1,20}:\/\/[^\s:@/]+:[^\s@/]{3,}@[^\s/]+/i],
26]
27
28export const INJECTION: Rules = [
29 ['override instructions', /\b(?:ignore|disregard|forget|override)\b[^.\n]{0,40}\b(?:previous|prior|above|earlier|all|any|system)\b[^.\n]{0,30}\b(?:instructions?|rules?|prompts?|guidelines?)\b/i],
30 ['role reassignment', /\byou are (?:now|no longer)\b|\bact as (?:an? )?(?:unrestricted|jailbroken)\b/i],
31 ['new instructions', /\b(?:new|updated|real) (?:system )?instructions?\s*:/i],
32 ['fake role tags', /<\/?\s*(?:system|assistant|developer|instructions?)\s*>|^\s*(?:system|assistant)\s*:/im],
33 ['concealment', /\bdo not (?:tell|inform|mention|reveal)[^.\n]{0,30}\b(?:user|human|operator)\b/i],
34 ['exfiltration', /\b(?:exfiltrate|send|post|upload)\b[^.\n]{0,50}\b(?:secrets?|credentials?|tokens?|api keys?|\.env)\b/i],
35 ['shell pipe', /\b(?:curl|wget)\b[^|\n]{0,200}\|\s*(?:sudo\s+)?(?:ba|z)?sh\b/i],
36]
37
38// C0/C1 controls (keeping tab and newline), DEL, soft hyphen, combining grapheme joiner, Arabic letter mark, Hangul and Mongolian fillers/separators,
39// zero-width, bidi (overrides and isolates) and invisible-format characters, variation selectors; built with escapes, never raw.
40const INVISIBLE = new RegExp(
41 '[\\u0000-\\u0008\\u000b-\\u001f\\u007f-\\u009f\\u00ad\\u034f\\u061c\\u115f\\u1160\\u17b4\\u17b5\\u180b-\\u180e\\u200b-\\u200f\\u2028-\\u202e\\u2060-\\u206f\\u3164\\ufe00-\\ufe0f\\ufeff\\uffa0\\ufff9-\\ufffb]',
42 'g',
43)
44
45/** Longest input scanned in one pass; a longer one keeps its head and tail halves. One regex pass per rule, so cost stays linear. */
46const MAX_SCAN = 200_000
47
48/** Input bounded to MAX_SCAN characters with invisible characters removed, so none can hide a secret or a phrase. */
49export const bare = (text: string) =>
50 (text.length > MAX_SCAN ? text.slice(0, MAX_SCAN / 2) + '\n' + text.slice(-MAX_SCAN / 2) : text).replace(INVISIBLE, '')
51
52// A value is a secret CANDIDATE only when it is not a reference (env var, call, identifier path, placeholder, secret-manager path) and its
53// shape is random enough: at least two character classes, one of them a digit or symbol, and Shannon entropy of at least 2.5 bits per character.
54const PLACEHOLDER = /placeholder|your[-_ ]|example|changeme|change[-_]?me|redacted|dummy|replace[-_]?me|insert[-_]|\*{3,}|x{5,}|\.{3}|^(?:none|null|undefined|true|false)$/i
55const REFERENCE =
56 /^(?:\$(?:\{[^}]*\}|\(|[A-Za-z_]\w*$)|%[^%]*%$|<[^>]*>$|\{\{|process\.env|os\.environ|env[.[]|import\.meta|System\.getenv|secrets?\.|vault:|op:\/\/|ref\+|arn:|projects\/[^/]+\/secrets\/|gcp:|kms:|aws:|file:)/i
57const CALL = /^[A-Za-z_$][\w$]*(?:\.[A-Za-z_$][\w$]*)*\(|^[A-Za-z_$][\w$]*\[/
58const IDENT_PATH = /^[A-Za-z_$][\w$]*(?:\.[A-Za-z_$][\w$]*)+$/
59const UUID = /^[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12}$/i
60const NAME_LIKE = /^[a-z][a-z0-9]*(?:[-_./][a-z0-9]+){2,}$/
61
62function entropy(v: string): number {
63 const counts = new Map<string, number>()
64 for (const ch of v) counts.set(ch, (counts.get(ch) ?? 0) + 1)
65 let h = 0
66 for (const n of counts.values()) h -= (n / v.length) * Math.log2(n / v.length)
67 return h
68}
69
70/** True when `v` is a name, call, path or placeholder rather than a literal credential. */
71function isReference(v: string): boolean {
72 if (PLACEHOLDER.test(v) || REFERENCE.test(v) || CALL.test(v) || IDENT_PATH.test(v) || URL_NO_CREDS.test(v)) return true
73 return NAME_LIKE.test(v) && v.replace(/\D/g, '').length / v.length < 0.15
74}
75
76export function plausibleSecret(v: string): boolean {
77 if (v.length < 8 || v.length > 256 || /\s/.test(v) || UUID.test(v) || isReference(v)) return false
78 const symbol = /[^A-Za-z0-9]/.test(v)
79 const digit = /\d/.test(v)
80 const classes = [/[a-z]/.test(v), /[A-Z]/.test(v), digit, symbol].filter(Boolean).length
81 return classes >= 2 && (digit || symbol) && entropy(v) >= 2.5
82}
83
84/** Under a secret-named key a literal this long is a secret even with one character class or a UUID shape, unless it is a clear reference. */
85const KEYED_MIN = 20
86const PLACEHOLDER_WORD = /(?:^|[^a-z])(?:your|placeholder|changeme|change[-_]?me|example|redacted|dummy|replace[-_]?me|insert)(?:[^a-z]|$)|\*{3,}|x{5,}|\.{3}|^(?:none|null|undefined|true|false)$/i
87const URL_NO_CREDS = /^[a-z][a-z0-9+.-]{1,20}:\/\/[^\s@]*$/i
88
89/** Three or more lowercase hyphen-separated words (no hex or digit-only run of 8+, few digits), such as my-k8s-secret-name-for-database. */
90function hyphenName(v: string): boolean {
91 const parts = v.split('-')
92 return parts.length >= 3 && parts.every(p => /^[a-z0-9]{2,}$/.test(p) && !/^[0-9a-f]{8,}$/.test(p)) && v.replace(/\D/g, '').length / v.length < 0.15
93}
94
95function keyedSecret(v: string): boolean {
96 if (v.length < KEYED_MIN || v.length > 256 || /\s/.test(v)) return false
97 return !(PLACEHOLDER_WORD.test(v) || REFERENCE.test(v) || CALL.test(v) || IDENT_PATH.test(v) || URL_NO_CREDS.test(v) || (!UUID.test(v) && hyphenName(v)))
98}
99
100const KEY_NAME = /(?:api[_-]?key|secret|token|passw(?:or)?d|passwd|pwd|credential|private[_-]?key|auth(?!or))s?[A-Za-z0-9_-]{0,40}["']?\s*[:=]\s*/gi
101const QUOTED = /(["'\x60])((?:(?!\1)[^\n]){1,256})\1/y
102const BARE_VALUE = /[^\s"'\x60,;]{1,256}/y
103const QUERY_VALUE = /[^\s"'\x60,;&]{1,256}/y
104
105/** A secret-named key assigned a literal value: env style, JSON, YAML, code. Values that are calls, references or placeholders do not count. */
106function assignmentSecret(text: string): boolean {
107 let valueEnd = 0
108 for (const m of text.matchAll(KEY_NAME)) {
109 if (m.index < valueEnd) continue // a key-looking word inside the previous value, such as secretsmanager in an ARN
110 const at = m.index + m[0].length
111 let back = m.index
112 while (back > 0 && m.index - back < 64 && /[A-Za-z0-9_.-]/.test(text.charAt(back - 1))) back--
113 const re = /["'\x60]/.test(text.charAt(at)) ? QUOTED : /[?&]/.test(text.charAt(back - 1)) ? QUERY_VALUE : BARE_VALUE
114 re.lastIndex = at
115 const hit = re.exec(text)
116 const v = hit && (hit[2] ?? hit[0])
117 valueEnd = hit ? at + hit[0].length : at
118 if (v && (plausibleSecret(v) || keyedSecret(v))) return true
119 }
120 return false
121}
122
123/** A password in a URL's userinfo that is not a placeholder such as user:password or ${DB_PASSWORD}. */
124function urlCredential(url: string): boolean {
125 const pass = /^[^:]+:\/\/[^\s:@/]+:([^\s@/]+)@/.exec(url)?.[1]
126 if (!pass || /\$\{|\{\{|%\(|%s/.test(pass)) return false
127 return !/^(?:password|passwd|pass|pwd|secret|changeme|dbpassword|db_password|\$\w*|<.*>|\{.*\}|\*+|x+)$/i.test(pass) && !PLACEHOLDER.test(pass)
128}
129
130const CHECKS: Readonly<Record<string, (m: RegExpMatchArray) => boolean>> = {
131 'bearer token': m => !isReference(m[1] ?? ''),
132 'database url with credentials': m => urlCredential(m[0]),
133 'database url with password': m => urlCredential(m[0]),
134}
135const globals = new WeakMap<RegExp, RegExp>()
136
137function matches(name: string, re: RegExp, text: string): boolean {
138 if (name === 'key assignment') return assignmentSecret(text)
139 const check = CHECKS[name]
140 if (!check) return re.test(text)
141 let g = globals.get(re)
142 if (!g) globals.set(re, (g = new RegExp(re.source, re.flags.includes('g') ? re.flags : re.flags + 'g')))
143 for (const m of text.matchAll(g)) if (check(m)) return true
144 return false
145}
146
147/**
148 * The text textsOf appends when it had to drop input (a node, character or per-string budget ran out). It is never matched against a rule:
149 * `names` reports it as a finding of its own, so every guard that asks "is there a secret in these texts" refuses what it could not read in full.
150 */
151export const TRUNCATED = 'ruflo-screen: input exceeded the screening budget'
152export const TRUNCATED_NAME = 'input too large to screen'
153
154/** Names of the rules that match `text` (already bare'd). A rule named 'key assignment' is judged by assignmentSecret, whatever its regex. */
155export const names = (rules: Rules, text: string) => text === TRUNCATED ? [TRUNCATED_NAME] : rules.filter(([name, re]) => matches(name, re, text)).map(([name]) => name)
156
157export type Findings = { readonly secrets: readonly string[]; readonly injection: readonly string[] }
158
159/** Names of every secret shape in `secrets` and every injection phrase found in `text`. Cost is linear in the capped input. */
160export function screenWith(secrets: Rules, text: string): Findings {
161 const bounded = bare(text)
162 return { secrets: names(secrets, bounded), injection: names(INJECTION, bounded) }
163}
164
165export const hasSecretIn = (secrets: Rules, text: string) => names(secrets, bare(text)).length > 0
166
167/** Makes stored text safe to show: no control or bidi characters, whitespace collapsed, at most `max` characters. */
168export function tidy(text: string, max: number): string {
169 const flat = text.replace(INVISIBLE, '').replace(/\s+/g, ' ').trim()
170 return flat.length > max ? `${flat.slice(0, Math.max(0, max - 1))}…` : flat
171}
172/** Bounds for textsOf: nodes visited, characters returned, the longest string read in full, the size of one returned chunk, chunk overlap. */
173export type TextLimits = { readonly nodes?: number; readonly chars?: number; readonly perString?: number }
174const NODES = 20_000
175const CHARS = 2_000_000
176const PER_STRING = 1_500_000
177const OVERLAP = 2_048
178const BARE_KEY_MIN = 8
179
180/** A string as texts the screen can read whole: one text up to MAX_SCAN, else overlapping MAX_SCAN windows so a secret anywhere is inside one. */
181function windows(text: string, out: string[]): void {
182 if (text.length <= MAX_SCAN) {
183 out.push(text)
184 return
185 }
186 for (let at = 0; ; at += MAX_SCAN - OVERLAP) {
187 out.push(text.slice(at, at + MAX_SCAN))
188 if (at + MAX_SCAN >= text.length) return
189 }
190}
191
192/**
193 * Every string in a tool input, for the screen to read: iterative (no recursion, so nesting 5000 deep cannot overflow the stack) and
194 * breadth-first (siblings before depth, so a long list cannot hide a nested value). A string under an object key comes back as `key=value`,
195 * so a secret-named key is judged with its value; a key whose value is not a string is returned bare. Strings longer than the screen window
196 * come back as overlapping windows; one over `perString` keeps its head and tail. Work is bounded by `nodes` slots and `chars` characters.
197 * Anything dropped (slots or characters ran out, or a string lost its middle) is reported by a final TRUNCATED text, which `names` and
198 * `hasSecretIn` count as a finding, so the screen fails closed instead of passing what it did not read.
199 */
200export function textsOf(input: unknown, limits: TextLimits = {}): string[] {
201 const out: string[] = []
202 let slots = limits.nodes ?? NODES
203 let chars = limits.chars ?? CHARS
204 const perString = limits.perString ?? PER_STRING
205 let truncated = false
206 const take = (text: string): void => {
207 if (chars <= 0) {
208 truncated = true
209 return
210 }
211 if (text.length <= Math.min(perString, chars)) {
212 chars -= text.length
213 windows(text, out)
214 return
215 }
216 truncated = true
217 const half = Math.floor(Math.min(perString, chars) / 2)
218 chars -= 2 * half
219 windows(text.slice(0, half), out)
220 windows(text.slice(-half), out)
221 }
222 const queue: unknown[] = [input]
223 let head = 0
224 for (; head < queue.length && chars > 0; head++) {
225 const node = queue[head]
226 if (typeof node === 'string') take(node)
227 else if (Array.isArray(node)) {
228 let i = 0
229 for (; i < node.length && slots > 0; i++, slots--) if (i in node) queue.push(node[i])
230 if (i < node.length) truncated = true
231 } else if (typeof node === 'object' && node !== null) {
232 for (const k in node) {
233 if (slots-- <= 0) {
234 truncated = true
235 break
236 }
237 if (!Object.prototype.hasOwnProperty.call(node, k)) continue
238 const v = (node as Record<string, unknown>)[k]
239 if (typeof v === 'string') queue.push(k + '=' + v)
240 else {
241 if (k.length >= BARE_KEY_MIN) take(k)
242 queue.push(v)
243 }
244 }
245 }
246 }
247 if (queue.length > head) truncated = true
248 if (truncated) out.push(TRUNCATED)
249 return out
250}
251// END SHARED SCREEN
252
253const SECRETS: Rules = [
254 ...COMMON_SECRETS,
255 ['key assignment', /\b(?:api[_-]?key|secret|token|passw(?:or)?d|credential)s?["']?\s*[:=]\s*["']?[A-Za-z0-9/+=_.-]{16,}/i],
256]
257
258export const scan = (text: string): Findings => screenWith(SECRETS, text)
259
260export const hasSecret = (text: string) => hasSecretIn(SECRETS, text)
261