feat(hooks): add grep-output-truncator for context-aware output limiting
This commit is contained in:
131
src/hooks/grep-output-truncator.ts
Normal file
131
src/hooks/grep-output-truncator.ts
Normal file
@@ -0,0 +1,131 @@
|
||||
import type { PluginInput } from "@opencode-ai/plugin"
|
||||
|
||||
const ANTHROPIC_ACTUAL_LIMIT = 200_000
|
||||
const CHARS_PER_TOKEN_ESTIMATE = 4
|
||||
const TARGET_MAX_TOKENS = 50_000
|
||||
|
||||
interface AssistantMessageInfo {
|
||||
role: "assistant"
|
||||
tokens: {
|
||||
input: number
|
||||
output: number
|
||||
reasoning: number
|
||||
cache: { read: number; write: number }
|
||||
}
|
||||
}
|
||||
|
||||
interface MessageWrapper {
|
||||
info: { role: string } & Partial<AssistantMessageInfo>
|
||||
}
|
||||
|
||||
function estimateTokens(text: string): number {
|
||||
return Math.ceil(text.length / CHARS_PER_TOKEN_ESTIMATE)
|
||||
}
|
||||
|
||||
function truncateToTokenLimit(output: string, maxTokens: number): { result: string; truncated: boolean } {
|
||||
const currentTokens = estimateTokens(output)
|
||||
|
||||
if (currentTokens <= maxTokens) {
|
||||
return { result: output, truncated: false }
|
||||
}
|
||||
|
||||
const lines = output.split("\n")
|
||||
|
||||
if (lines.length <= 3) {
|
||||
const maxChars = maxTokens * CHARS_PER_TOKEN_ESTIMATE
|
||||
return {
|
||||
result: output.slice(0, maxChars) + "\n\n[Output truncated due to context window limit]",
|
||||
truncated: true,
|
||||
}
|
||||
}
|
||||
|
||||
const headerLines = lines.slice(0, 3)
|
||||
const contentLines = lines.slice(3)
|
||||
|
||||
const headerText = headerLines.join("\n")
|
||||
const headerTokens = estimateTokens(headerText)
|
||||
const availableTokens = maxTokens - headerTokens - 50
|
||||
|
||||
if (availableTokens <= 0) {
|
||||
return {
|
||||
result: headerText + "\n\n[Content truncated due to context window limit]",
|
||||
truncated: true,
|
||||
}
|
||||
}
|
||||
|
||||
let resultLines: string[] = []
|
||||
let currentTokenCount = 0
|
||||
|
||||
for (const line of contentLines) {
|
||||
const lineTokens = estimateTokens(line + "\n")
|
||||
if (currentTokenCount + lineTokens > availableTokens) {
|
||||
break
|
||||
}
|
||||
resultLines.push(line)
|
||||
currentTokenCount += lineTokens
|
||||
}
|
||||
|
||||
const truncatedContent = [...headerLines, ...resultLines].join("\n")
|
||||
const removedCount = contentLines.length - resultLines.length
|
||||
|
||||
return {
|
||||
result: truncatedContent + `\n\n[${removedCount} more lines truncated due to context window limit]`,
|
||||
truncated: true,
|
||||
}
|
||||
}
|
||||
|
||||
export function createGrepOutputTruncatorHook(ctx: PluginInput) {
|
||||
const GREP_TOOLS = ["safe_grep", "Grep"]
|
||||
|
||||
const toolExecuteAfter = async (
|
||||
input: { tool: string; sessionID: string; callID: string },
|
||||
output: { title: string; output: string; metadata: unknown }
|
||||
) => {
|
||||
if (!GREP_TOOLS.includes(input.tool)) return
|
||||
|
||||
const { sessionID } = input
|
||||
|
||||
try {
|
||||
const response = await ctx.client.session.messages({
|
||||
path: { id: sessionID },
|
||||
})
|
||||
|
||||
const messages = (response.data ?? response) as MessageWrapper[]
|
||||
|
||||
const assistantMessages = messages
|
||||
.filter((m) => m.info.role === "assistant")
|
||||
.map((m) => m.info as AssistantMessageInfo)
|
||||
|
||||
if (assistantMessages.length === 0) return
|
||||
|
||||
const totalInputTokens = assistantMessages.reduce((sum, m) => {
|
||||
const inputTokens = m.tokens?.input ?? 0
|
||||
const cacheReadTokens = m.tokens?.cache?.read ?? 0
|
||||
return sum + inputTokens + cacheReadTokens
|
||||
}, 0)
|
||||
|
||||
const remainingTokens = ANTHROPIC_ACTUAL_LIMIT - totalInputTokens
|
||||
|
||||
const maxOutputTokens = Math.min(
|
||||
remainingTokens * 0.5,
|
||||
TARGET_MAX_TOKENS
|
||||
)
|
||||
|
||||
if (maxOutputTokens <= 0) {
|
||||
output.output = "[Output suppressed - context window exhausted]"
|
||||
return
|
||||
}
|
||||
|
||||
const { result, truncated } = truncateToTokenLimit(output.output, maxOutputTokens)
|
||||
if (truncated) {
|
||||
output.output = result
|
||||
}
|
||||
} catch {
|
||||
// Graceful degradation
|
||||
}
|
||||
}
|
||||
|
||||
return {
|
||||
"tool.execute.after": toolExecuteAfter,
|
||||
}
|
||||
}
|
||||
@@ -3,3 +3,4 @@ export { createContextWindowMonitorHook } from "./context-window-monitor"
|
||||
export { createSessionNotification } from "./session-notification"
|
||||
export { createSessionRecoveryHook } from "./session-recovery"
|
||||
export { createCommentCheckerHooks } from "./comment-checker"
|
||||
export { createGrepOutputTruncatorHook } from "./grep-output-truncator"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import type { Plugin } from "@opencode-ai/plugin"
|
||||
import { createBuiltinAgents } from "./agents"
|
||||
import { createTodoContinuationEnforcer, createContextWindowMonitorHook, createSessionRecoveryHook, createCommentCheckerHooks } from "./hooks"
|
||||
import { createTodoContinuationEnforcer, createContextWindowMonitorHook, createSessionRecoveryHook, createCommentCheckerHooks, createGrepOutputTruncatorHook } from "./hooks"
|
||||
import { updateTerminalTitle } from "./features/terminal"
|
||||
import { builtinTools } from "./tools"
|
||||
import { createBuiltinMcps } from "./mcp"
|
||||
@@ -44,6 +44,7 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
|
||||
const contextWindowMonitor = createContextWindowMonitorHook(ctx)
|
||||
const sessionRecovery = createSessionRecoveryHook(ctx)
|
||||
const commentChecker = createCommentCheckerHooks()
|
||||
const grepOutputTruncator = createGrepOutputTruncatorHook(ctx)
|
||||
|
||||
updateTerminalTitle({ sessionId: "main" })
|
||||
|
||||
@@ -185,6 +186,7 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
|
||||
},
|
||||
|
||||
"tool.execute.after": async (input, output) => {
|
||||
await grepOutputTruncator["tool.execute.after"](input, output)
|
||||
await contextWindowMonitor["tool.execute.after"](input, output)
|
||||
await commentChecker["tool.execute.after"](input, output)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user