feat: add native Node.js RTK output filtering (FAR-66)

Replace the init-container RTK binary approach with a self-contained
Node.js implementation. When `enableRtk: true` is set in adapter config,
the job's main container startup:

1. Writes a Node.js filter script to /tmp/.rtk-filter.js (base64-encoded
   inline — no curl, no wget, no external binary download required).
2. Merges a PostToolUse hook into ~/.claude/settings.json so Claude Code
   runs the filter after every tool call.
3. The filter truncates tool_response/tool_result content that exceeds
   `rtkMaxOutputBytes` (default: 50 000 B), handling both string and
   array (text-block) content formats.

New config fields:
  enableRtk            toggle  — off by default
  rtkMaxOutputBytes    number  — truncation threshold (default 50 000)

9 new tests cover: command shape, ordering, no-external-binary guarantee,
threshold injection, PostToolUse hook presence, and filter-script logic.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
This commit is contained in:
Test User
2026-04-22 02:08:24 +00:00
parent 5926b302e5
commit 99c97c1fb2
3 changed files with 192 additions and 2 deletions
+89 -1
View File
@@ -11,6 +11,86 @@ import {
} from "@paperclipai/adapter-utils/server-utils";
import { createHash } from "node:crypto";
/**
* Build the shell command prefix that installs a native Node.js PostToolUse
* hook into Claude Code's settings. The hook truncates oversized tool outputs
* before they reach the model — replacing the RTK binary init-container
* approach with a self-contained Node.js implementation.
*
* Both scripts are base64-encoded so they can be embedded in a sh -c command
* string without any quoting or escaping issues.
*
* @param maxOutputBytes Byte threshold above which tool output is truncated.
* @returns A shell command string (suitable for "&&"-chaining
* before the claude invocation).
*/
export function buildRtkSetupCommands(maxOutputBytes: number): string {
// --- Filter script ----------------------------------------------------------
// This script runs as the PostToolUse hook inside every K8s Job pod.
// Claude Code writes the hook event as JSON to the script's stdin; the script
// truncates the tool_response/tool_result content when it exceeds the
// threshold and writes the (possibly modified) JSON to stdout.
//
// Field-name coverage:
// • tool_response — documented hook event format for PostToolUse
// • tool_result — alternative name seen in some Claude Code versions
// Content may be a plain string or an array of typed blocks (text/image/…).
const filterScript = [
`const c=[];`,
`process.stdin.on('data',d=>c.push(d));`,
`process.stdin.on('end',()=>{`,
`const raw=Buffer.concat(c).toString('utf-8');`,
`let o;try{o=JSON.parse(raw);}catch{process.stdout.write(raw);return;}`,
`const MAX=${maxOutputBytes};`,
`function trunc(s){`,
`if(typeof s!=='string')return s;`,
`const b=Buffer.from(s,'utf-8');`,
`if(b.length<=MAX)return s;`,
`return b.slice(0,MAX).toString('utf-8')+'\\n[...'+(b.length-MAX)+' bytes truncated by paperclip-rtk]';`,
`}`,
`const tr=o&&(o.tool_response||o.tool_result);`,
`if(tr){`,
`if(typeof tr.content==='string'){tr.content=trunc(tr.content);}`,
`else if(Array.isArray(tr.content)){`,
`tr.content=tr.content.map(function(b){`,
`if(b&&typeof b==='object'&&typeof b.text==='string'){`,
`return Object.assign({},b,{text:trunc(b.text)});`,
`}return b;`,
`});`,
`}`,
`}`,
`process.stdout.write(JSON.stringify(o));`,
`});`,
].join("");
// --- Settings script --------------------------------------------------------
// Reads the existing ~/.claude/settings.json (if any), merges in the RTK
// PostToolUse hook, and writes the file back. All other settings sections
// are preserved; only PostToolUse is replaced so we own the full hook list
// for this run.
const settingsScript = [
`const fs=require('fs'),pt=require('path');`,
`const p=pt.join(process.env.HOME,'.claude','settings.json');`,
`let s={};try{s=JSON.parse(fs.readFileSync(p,'utf-8'));}catch(e){}`,
`s.hooks=s.hooks||{};`,
`s.hooks.PostToolUse=[{matcher:'.*',hooks:[{type:'command',command:'node /tmp/.rtk-filter.js'}]}];`,
`fs.mkdirSync(pt.dirname(p),{recursive:true});`,
`fs.writeFileSync(p,JSON.stringify(s));`,
].join("");
// Encode as base64 so the strings can be embedded directly in a shell command
// without any quoting concerns (base64 alphabet: A-Za-z0-9+/=).
const filterB64 = Buffer.from(filterScript, "utf-8").toString("base64");
const settingsB64 = Buffer.from(settingsScript, "utf-8").toString("base64");
return [
// Write the filter script
`node -e "require('fs').writeFileSync('/tmp/.rtk-filter.js',Buffer.from('${filterB64}','base64').toString('utf-8'))"`,
// Install the Claude Code PostToolUse hook (merge into existing settings)
`node -e "eval(Buffer.from('${settingsB64}','base64').toString('utf-8'))"`,
].join(" && ");
}
/** Prompts above this size (bytes) are staged via a Secret instead of an
* init container env var, protecting against the ~1 MiB PodSpec limit. */
const LARGE_PROMPT_THRESHOLD_BYTES = 256 * 1024;
@@ -255,6 +335,8 @@ export function buildJobManifest(input: JobBuildInput): JobBuildResult {
const nodeSelector = parseKeyValueConfig(config.nodeSelector);
const tolerations = Array.isArray(config.tolerations) ? config.tolerations : [];
const extraLabels = parseKeyValueConfig(config.labels);
const enableRtk = asBoolean(config.enableRtk, false);
const rtkMaxOutputBytes = asNumber(config.rtkMaxOutputBytes, 50000);
// Resolve working directory — use workspace cwd, fall back to /paperclip
const workspaceContext = parseObject(context.paperclipWorkspace);
@@ -408,7 +490,13 @@ export function buildJobManifest(input: JobBuildInput): JobBuildResult {
// Build the claude command string for the main container
const claudeArgsEscaped = claudeArgs.map((a) => `'${a.replace(/'/g, "'\\''")}'`).join(" ");
const mainCommand = `cat /tmp/prompt/prompt.txt | claude ${claudeArgsEscaped}`;
const claudeInvocation = `cat /tmp/prompt/prompt.txt | claude ${claudeArgsEscaped}`;
// When RTK output filtering is enabled, prepend the Node.js hook setup.
// This writes a filter script and a Claude Code settings file that installs
// it as a PostToolUse hook — no external binary or init container required.
const mainCommand = enableRtk
? `${buildRtkSetupCommands(rtkMaxOutputBytes)} && ${claudeInvocation}`
: claudeInvocation;
// Decide prompt delivery strategy: env var (small) or Secret volume (large).
const promptBytes = Buffer.byteLength(prompt, "utf-8");