mirror of
https://github.com/AgentSeal/codeburn.git
synced 2026-07-26 01:14:56 +00:00
feat: add JetBrains (IntelliJ/DataGrip) session discovery and parsing (#433)
* feat(copilot): add JetBrains (IntelliJ/DataGrip) session discovery and parsing The Copilot provider previously only discovered sessions from: - ~/.copilot/session-state/ (legacy VS Code format) - VS Code workspace storage directories IntelliJ and other JetBrains IDEs store Copilot chat sessions in ~/.copilot/jb/<session-id>/partition-*.jsonl using a slightly different event format. This commit adds: - discoverJetBrainsSessions(): finds all .jsonl files under ~/.copilot/jb/ - isJetBrainsFormat(): detects JB event format (no session.start header) - parseJetBrainsEvents(): parses JB events (assistant.message with text/ thinking, tool.execution_start for tool names, tool call ID prefixes for model inference) - inferJBProjectName(): extracts project name from tool execution paths Closes #N/A * fix: address PR review feedback for JetBrains Copilot support - Add 'sep' to path import (fixes ReferenceError in project inference) - Use incrementing index as dedup key fallback when messageId is absent to prevent undercounting tokens/cost - Move project inference to parse time using already-loaded content (avoids bypassing readSessionFile's 128MB safety cap) - Tighten isJetBrainsFormat to only match user.message_rendered and partition.created (avoids false-positive on legacy files starting with user.message) - Add dedicated inferModelFromEvents for JB format that checks data.model (100x weight) and tool call ID prefixes on tool.execution_start/complete events - Remove dead first-pass loop that was never read - Add jbDirOverride param to createCopilotProvider for test fixtures
This commit is contained in:
Zuber Khan
GitHub
parent
4a384cd31d
commit
e7920fc6aa
1 changed files with 249 additions and 7 deletions
|
|
@ -1,6 +1,6 @@
|
|||
import { existsSync } from 'fs'
|
||||
import { readdir, readFile, stat } from 'fs/promises'
|
||||
import { basename, dirname, join, posix, win32 } from 'path'
|
||||
import { basename, dirname, join, posix, sep, win32 } from 'path'
|
||||
import { homedir } from 'os'
|
||||
|
||||
import { readSessionFile } from '../fs-utils.js'
|
||||
|
|
@ -243,6 +243,34 @@ function inferModelFromToolCallIds(events: TranscriptEvent[]): string {
|
|||
return 'copilot-auto'
|
||||
}
|
||||
|
||||
/** Model inference for JB events — checks data.model (100x weight) and tool call
|
||||
* ID prefixes on tool.execution_start/complete events. */
|
||||
function inferModelFromEvents(events: JBEvent[]): string {
|
||||
const modelCounts = new Map<string, number>()
|
||||
|
||||
for (const e of events) {
|
||||
const data = e.data as { model?: string; toolCallId?: string }
|
||||
if (typeof data.model === 'string' && data.model) {
|
||||
modelCounts.set(data.model, (modelCounts.get(data.model) ?? 0) + 100)
|
||||
}
|
||||
|
||||
if (e.type === 'tool.execution_start' || e.type === 'tool.execution_complete') {
|
||||
const toolCallId = data.toolCallId ?? ''
|
||||
for (const hint of transcriptToolCallModelHints) {
|
||||
if (!toolCallId.startsWith(hint.prefix)) continue
|
||||
modelCounts.set(hint.model, (modelCounts.get(hint.model) ?? 0) + 1)
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (modelCounts.size > 0) {
|
||||
return [...modelCounts.entries()].sort((a, b) => b[1] - a[1])[0]![0]
|
||||
}
|
||||
|
||||
return 'copilot-auto'
|
||||
}
|
||||
|
||||
function parseTranscriptEvents(content: string, sessionId: string, seenKeys: Set<string>): ParsedProviderCall[] {
|
||||
const results: ParsedProviderCall[] = []
|
||||
const lines = content.split('\n').filter(l => l.trim())
|
||||
|
|
@ -334,6 +362,134 @@ function isTranscriptFormat(content: string): boolean {
|
|||
}
|
||||
}
|
||||
|
||||
function isJetBrainsFormat(content: string): boolean {
|
||||
const firstLine = content.split('\n')[0] ?? ''
|
||||
try {
|
||||
const event = JSON.parse(firstLine)
|
||||
// JB format starts with user.message_rendered or partition.created (JB-specific).
|
||||
// We intentionally exclude user.message here since legacy files can also start
|
||||
// with that event type — routing them to the JB parser would misparse them.
|
||||
return (
|
||||
event.type === 'user.message_rendered' ||
|
||||
event.type === 'partition.created'
|
||||
)
|
||||
} catch {
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
// --- JetBrains (IntelliJ/DataGrip) format parser ---
|
||||
|
||||
type JBEvent = {
|
||||
type: string
|
||||
timestamp?: string
|
||||
id?: string
|
||||
data: Record<string, unknown>
|
||||
}
|
||||
|
||||
function parseJetBrainsEvents(content: string, sessionId: string, seenKeys: Set<string>): ParsedProviderCall[] {
|
||||
const results: ParsedProviderCall[] = []
|
||||
const lines = content.split('\n').filter(l => l.trim())
|
||||
const events: JBEvent[] = []
|
||||
|
||||
for (const line of lines) {
|
||||
try {
|
||||
events.push(JSON.parse(line))
|
||||
} catch {
|
||||
continue
|
||||
}
|
||||
}
|
||||
|
||||
// Reuse the shared model inference logic: check explicit data.model fields
|
||||
// (weighted 100x) and tool call ID prefix heuristics from both assistant.message
|
||||
// toolRequests and tool.execution_start/complete events (JB-specific).
|
||||
const model = inferModelFromEvents(events)
|
||||
|
||||
// Collect tool names per turn
|
||||
const toolsByTurn = new Map<string, string[]>()
|
||||
let currentTurnId = ''
|
||||
let userMsg = ''
|
||||
let msgIndex = 0
|
||||
|
||||
for (const e of events) {
|
||||
if (e.type === 'user.message_rendered') {
|
||||
userMsg = ((e.data.renderedMessage as string) ?? '').slice(0, 500)
|
||||
}
|
||||
if (e.type === 'user.message') {
|
||||
const msg = (e.data.content as string) ?? ''
|
||||
if (msg) userMsg = msg.slice(0, 500)
|
||||
}
|
||||
|
||||
if (e.type === 'assistant.turn_start') {
|
||||
currentTurnId = (e.data.turnId as string) ?? ''
|
||||
}
|
||||
|
||||
if (e.type === 'tool.execution_start') {
|
||||
const toolName = (e.data.toolName as string) ?? ''
|
||||
const normalized = normalizeToolName(toolName)
|
||||
if (normalized) {
|
||||
const msgId = currentTurnId || 'unknown'
|
||||
const existing = toolsByTurn.get(msgId) ?? []
|
||||
existing.push(normalized)
|
||||
toolsByTurn.set(msgId, existing)
|
||||
}
|
||||
}
|
||||
|
||||
if (e.type === 'assistant.message') {
|
||||
const data = e.data as { messageId?: string; content?: string; text?: string; reasoningText?: string; thinking?: { text?: string }; iterationNumber?: number; outputTokens?: number }
|
||||
const contentText = data.text ?? data.content ?? ''
|
||||
const reasoningText = data.reasoningText ?? data.thinking?.text ?? ''
|
||||
|
||||
// Skip empty messages (streaming placeholders)
|
||||
if (contentText.length === 0 && reasoningText.length === 0) continue
|
||||
|
||||
// Use messageId if available, otherwise fall back to an incrementing index
|
||||
// to avoid dedup collisions when messageId is absent.
|
||||
const messageId = data.messageId ?? e.id ?? ''
|
||||
const dedupId = messageId || String(msgIndex++)
|
||||
const dedupKey = `copilot:jb:${sessionId}:${dedupId}:${data.iterationNumber ?? 0}`
|
||||
if (seenKeys.has(dedupKey)) continue
|
||||
seenKeys.add(dedupKey)
|
||||
|
||||
let outputTokens = data.outputTokens ?? 0
|
||||
let reasoningTokens = 0
|
||||
if (outputTokens === 0) {
|
||||
outputTokens = Math.ceil(contentText.length / CHARS_PER_TOKEN)
|
||||
reasoningTokens = Math.ceil(reasoningText.length / CHARS_PER_TOKEN)
|
||||
}
|
||||
|
||||
const inputTokens = Math.ceil(userMsg.length / CHARS_PER_TOKEN)
|
||||
const tools = toolsByTurn.get(currentTurnId || messageId) ?? []
|
||||
const costUSD = calculateCost(model, inputTokens, outputTokens + reasoningTokens, 0, 0, 0)
|
||||
|
||||
results.push({
|
||||
provider: 'copilot',
|
||||
model,
|
||||
inputTokens,
|
||||
outputTokens,
|
||||
cacheCreationInputTokens: 0,
|
||||
cacheReadInputTokens: 0,
|
||||
cachedInputTokens: 0,
|
||||
reasoningTokens,
|
||||
webSearchRequests: 0,
|
||||
costUSD,
|
||||
tools,
|
||||
bashCommands: [],
|
||||
timestamp: e.timestamp ?? '',
|
||||
speed: 'standard',
|
||||
deduplicationKey: dedupKey,
|
||||
userMessage: userMsg,
|
||||
sessionId,
|
||||
})
|
||||
|
||||
// Only count user message once per assistant turn
|
||||
userMsg = ''
|
||||
}
|
||||
}
|
||||
|
||||
return results
|
||||
}
|
||||
|
||||
function createParser(source: SessionSource, seenKeys: Set<string>): SessionParser {
|
||||
return {
|
||||
async *parse(): AsyncGenerator<ParsedProviderCall> {
|
||||
|
|
@ -343,9 +499,21 @@ function createParser(source: SessionSource, seenKeys: Set<string>): SessionPars
|
|||
? basename(source.path, '.jsonl')
|
||||
: basename(dirname(source.path))
|
||||
|
||||
const calls = isTranscriptFormat(content)
|
||||
? parseTranscriptEvents(content, sessionId, seenKeys)
|
||||
: parseLegacyEvents(content, sessionId, seenKeys)
|
||||
let calls: ParsedProviderCall[]
|
||||
if (isTranscriptFormat(content)) {
|
||||
calls = parseTranscriptEvents(content, sessionId, seenKeys)
|
||||
} else if (isJetBrainsFormat(content)) {
|
||||
calls = parseJetBrainsEvents(content, sessionId, seenKeys)
|
||||
// Infer project name from tool paths now that content is loaded
|
||||
const inferredProject = inferJBProjectFromContent(content)
|
||||
if (inferredProject) {
|
||||
for (const call of calls) {
|
||||
call.project = inferredProject
|
||||
}
|
||||
}
|
||||
} else {
|
||||
calls = parseLegacyEvents(content, sessionId, seenKeys)
|
||||
}
|
||||
|
||||
for (const call of calls) {
|
||||
yield call
|
||||
|
|
@ -409,6 +577,78 @@ async function readWorkspaceProject(workspaceDir: string): Promise<string> {
|
|||
return basename(workspaceDir)
|
||||
}
|
||||
|
||||
function getJetBrainsSessionDir(override?: string): string {
|
||||
return override ?? join(homedir(), '.copilot', 'jb')
|
||||
}
|
||||
|
||||
async function discoverJetBrainsSessions(jbDir: string): Promise<SessionSource[]> {
|
||||
const sources: SessionSource[] = []
|
||||
|
||||
let sessionDirs: string[]
|
||||
try {
|
||||
sessionDirs = await readdir(jbDir)
|
||||
} catch {
|
||||
return sources
|
||||
}
|
||||
|
||||
for (const sessionId of sessionDirs) {
|
||||
const sessionPath = join(jbDir, sessionId)
|
||||
const s = await stat(sessionPath).catch(() => null)
|
||||
if (!s?.isDirectory()) continue
|
||||
|
||||
let partitions: string[]
|
||||
try {
|
||||
partitions = await readdir(sessionPath)
|
||||
} catch {
|
||||
continue
|
||||
}
|
||||
|
||||
for (const file of partitions) {
|
||||
if (!file.endsWith('.jsonl')) continue
|
||||
const filePath = join(sessionPath, file)
|
||||
const fs = await stat(filePath).catch(() => null)
|
||||
if (!fs?.isFile()) continue
|
||||
sources.push({ path: filePath, project: sessionId, provider: 'copilot' })
|
||||
}
|
||||
}
|
||||
|
||||
return sources
|
||||
}
|
||||
|
||||
/** Infer a project name from tool execution paths in already-loaded content. */
|
||||
function inferJBProjectFromContent(content: string): string | null {
|
||||
const homeParts = homedir().split(sep)
|
||||
const homeDepth = homeParts.length
|
||||
const lines = content.split('\n')
|
||||
const limit = Math.min(lines.length, 200)
|
||||
|
||||
for (let i = 0; i < limit; i++) {
|
||||
const line = lines[i]
|
||||
if (!line) continue
|
||||
try {
|
||||
const e = JSON.parse(line)
|
||||
if (e.type === 'tool.execution_start') {
|
||||
const args = e.data?.arguments
|
||||
if (typeof args === 'object' && args !== null && typeof args.path === 'string') {
|
||||
const pathVal: string = args.path
|
||||
const parts = pathVal.split('/')
|
||||
if (parts.length > homeDepth + 1) {
|
||||
const afterHome = parts.slice(homeDepth)
|
||||
if (afterHome.length >= 2) {
|
||||
return basename(afterHome.slice(0, afterHome.length > 2 ? 2 : afterHome.length).join('/'))
|
||||
|| afterHome[0] || null
|
||||
}
|
||||
return afterHome[0] || null
|
||||
}
|
||||
}
|
||||
}
|
||||
} catch {
|
||||
continue
|
||||
}
|
||||
}
|
||||
return null
|
||||
}
|
||||
|
||||
async function discoverLegacySessions(sessionStateDir: string): Promise<SessionSource[]> {
|
||||
const sources: SessionSource[] = []
|
||||
|
||||
|
|
@ -472,9 +712,10 @@ async function discoverVSCodeTranscripts(workspaceStorageDir: string): Promise<S
|
|||
return sources
|
||||
}
|
||||
|
||||
export function createCopilotProvider(sessionStateDir?: string, workspaceStorageDirOverride?: string): Provider {
|
||||
export function createCopilotProvider(sessionStateDir?: string, workspaceStorageDirOverride?: string, jbDirOverride?: string): Provider {
|
||||
const legacyDir = getCopilotSessionStateDir(sessionStateDir)
|
||||
const vscodeDirs = workspaceStorageDirOverride != null ? [workspaceStorageDirOverride] : getVSCodeWorkspaceStorageDirs()
|
||||
const jbDir = getJetBrainsSessionDir(jbDirOverride)
|
||||
|
||||
return {
|
||||
name: 'copilot',
|
||||
|
|
@ -495,11 +736,12 @@ export function createCopilotProvider(sessionStateDir?: string, workspaceStorage
|
|||
},
|
||||
|
||||
async discoverSessions(): Promise<SessionSource[]> {
|
||||
const [legacy, ...vscodeResults] = await Promise.all([
|
||||
const [legacy, jb, ...vscodeResults] = await Promise.all([
|
||||
discoverLegacySessions(legacyDir),
|
||||
discoverJetBrainsSessions(jbDir),
|
||||
...vscodeDirs.map(discoverVSCodeTranscripts),
|
||||
])
|
||||
return [...legacy, ...vscodeResults.flat()]
|
||||
return [...legacy, ...jb, ...vscodeResults.flat()]
|
||||
},
|
||||
|
||||
createSessionParser(source: SessionSource, seenKeys: Set<string>): SessionParser {
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue