Skip to content

feat: Bump to LangChain 1.0 and drop community package requirement #1311

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jsonbailey merged 8 commits into from
Apr 27, 2026
+14 −19
Merged

feat: Bump to LangChain 1.0 and drop community package requirement #1311

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
063879b
fix dependency errors by bumping @langchain/community to the latest r…
epietrowicz Apr 22, 2026
70163b6
fix: drop @langchain/community peer dep and restrict langchain to 1.x
jsonbailey Apr 27, 2026
9d1b9f7
Merge remote-tracking branch 'origin/main' into pr-1311-langchain-deps
jsonbailey Apr 27, 2026
a849c6f
Merge branch 'main' into bugfix/fix-deps-error
jsonbailey Apr 27, 2026
c55f06b
fix: use standard usage_metadata for token extraction in 1.x
jsonbailey Apr 27, 2026
c7dde19
Merge remote-tracking branch 'epietrowicz/bugfix/fix-deps-error' into…
jsonbailey Apr 27, 2026
004e9f5
fix: remove legacy tokenUsage fallback
jsonbailey Apr 27, 2026
49fd2c1
test: update token usage test to use usage_metadata
jsonbailey Apr 27, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 4 additions & 6 deletions packages/ai-providers/server-ai-langchain/__tests__/LangChainProvider.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,12 +76,10 @@ describe('LangChainProvider', () => {
describe('getAIMetricsFromResponse', () => {
it('creates metrics with success=true and token usage', () => {
const mockResponse = new AIMessage('Test response');
mockResponse.response_metadata = {
tokenUsage: {
totalTokens: 100,
promptTokens: 50,
completionTokens: 50,
},
mockResponse.usage_metadata = {
total_tokens: 100,
input_tokens: 50,
output_tokens: 50,
};

const result = LangChainProvider.getAIMetricsFromResponse(mockResponse);
Expand Down
14 changes: 6 additions & 8 deletions packages/ai-providers/server-ai-langchain/package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,11 +43,10 @@
"author": "LaunchDarkly",
"license": "Apache-2.0",
"devDependencies": {
"@langchain/community": "^0.3.0",
"@langchain/core": "^0.3.0",
"@langchain/core": "^1.1.41",
"@launchdarkly/server-sdk-ai": "^0.17.1",
"@opentelemetry/api": "^1.9.0",
"@traceloop/instrumentation-langchain": "^0.22.0",
"@traceloop/instrumentation-langchain": "^0.26.0",
"@trivago/prettier-plugin-sort-imports": "^4.1.1",
"@types/jest": "^29.5.3",
"@typescript-eslint/eslint-plugin": "^6.20.0",
Expand All @@ -58,19 +57,18 @@
"eslint-plugin-jest": "^27.6.3",
"eslint-plugin-prettier": "^5.0.0",
"jest": "^29.6.1",
"langchain": "^0.3.0",
"langchain": "^1.3.4",
"prettier": "^3.0.0",
"ts-jest": "^29.1.1",
"tsup": "^8.5.1",
"typescript": "5.1.6"
},
"peerDependencies": {
"@langchain/community": "^0.2.0 || ^0.3.0",
"@langchain/core": "^0.2.0 || ^0.3.0",
"@langchain/core": "^1.0.0",
"@launchdarkly/server-sdk-ai": "^0.17.0",
"@opentelemetry/api": "^1.0.0",
"@traceloop/instrumentation-langchain": "^0.22.0",
"langchain": "^0.2.0 || ^0.3.0"
"@traceloop/instrumentation-langchain": "^0.26.0",
"langchain": "^1.0.0"
},
"peerDependenciesMeta": {
"@opentelemetry/api": {
Expand Down
9 changes: 4 additions & 5 deletions packages/ai-providers/server-ai-langchain/src/LangChainProvider.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -213,12 +213,11 @@ export class LangChainProvider extends AIProvider {
static getAIMetricsFromResponse(response: AIMessage): LDAIMetrics {
// Extract token usage if available
let usage: LDTokenUsage | undefined;
if (response?.response_metadata?.tokenUsage) {
const { tokenUsage } = response.response_metadata;
if (response?.usage_metadata) {
usage = {
total: tokenUsage.totalTokens || 0,
input: tokenUsage.promptTokens || 0,
output: tokenUsage.completionTokens || 0,
total: response.usage_metadata.total_tokens,
input: response.usage_metadata.input_tokens,
output: response.usage_metadata.output_tokens,
};
}

Expand Down
Loading