fix(llm-agents): delete the flows three agent specs left behind (#1346) #1100
pr-validation.yml
on: pull_request
Detect changed specs
10s
TypeScript Check
1m 43s
ESLint
20s
Python unit tests
11s
QA-CHECKLIST guard
14s
Spec-doc dependency paths
12s
Run impacted E2E specs
7m 4s
Annotations
4 errors, 3 warnings, and 1 notice
|
Run impacted E2E specs
Process completed with exit code 1.
|
|
[chromium] › tests/tests-automations/regression/core-functionality/llm-agents/agent-max-iterations.spec.ts:164:9 › Agent Max Iterations [anthropic / claude-haiku-4-5] › agent stops when max iterations is reached @regression @agents @playground:
tests/tests-automations/regression/core-functionality/llm-agents/agent-max-iterations.spec.ts#L186
1) [chromium] › tests/tests-automations/regression/core-functionality/llm-agents/agent-max-iterations.spec.ts:164:9 › Agent Max Iterations [anthropic / claude-haiku-4-5] › agent stops when max iterations is reached @regression @agentS @playground
Retry #2 ───────────────────────────────────────────────────────────────────────────────────────
Error: expect(locator).toContainText(expected) failed
Locator: getByTestId('div-chat-message').last()
Expected pattern: /model call limits exceeded/i
Received string: "I'll fetch that URL for you and retrieve the version value."
Timeout: 30000ms
Call log:
- Expect "toContainText" with timeout 30000ms
- waiting for getByTestId('div-chat-message').last()
34 × locator resolved to <div data-testid="div-chat-message" class="flex w-full flex-col dark:text-white">…</div>
- unexpected value "I'll fetch that URL for you and retrieve the version value."
184 | const bubble = await runAndGetBubble(page);
185 | // Limit enforced: the agent stopped at the configured cap of 1.
> 186 | await expect(bubble).toContainText(LIMIT_MESSAGE, { timeout: 30000 });
| ^
187 | // run limit (1/1) ties the stop to max_iterations=1.
188 | await expect(bubble).toContainText(/\(\s*1\s*\/\s*1\s*\)/, { timeout: 10000 });
189 | });
at /home/runner/work/langflow-e2e/langflow-e2e/tests/tests-automations/regression/core-functionality/llm-agents/agent-max-iterations.spec.ts:186:32
at /home/runner/work/langflow-e2e/langflow-e2e/tests/tests-automations/regression/core-functionality/llm-agents/agent-max-iterations.spec.ts:183:9
|
|
[chromium] › tests/tests-automations/regression/core-functionality/llm-agents/agent-max-iterations.spec.ts:164:9 › Agent Max Iterations [anthropic / claude-haiku-4-5] › agent stops when max iterations is reached @regression @agents @playground:
tests/tests-automations/regression/core-functionality/llm-agents/agent-max-iterations.spec.ts#L186
1) [chromium] › tests/tests-automations/regression/core-functionality/llm-agents/agent-max-iterations.spec.ts:164:9 › Agent Max Iterations [anthropic / claude-haiku-4-5] › agent stops when max iterations is reached @regression @agentS @playground
Retry #1 ───────────────────────────────────────────────────────────────────────────────────────
Error: expect(locator).toContainText(expected) failed
Locator: getByTestId('div-chat-message').last()
Expected pattern: /model call limits exceeded/i
Received string: "I'll fetch that URL for you."
Timeout: 30000ms
Call log:
- Expect "toContainText" with timeout 30000ms
- waiting for getByTestId('div-chat-message').last()
34 × locator resolved to <div data-testid="div-chat-message" class="flex w-full flex-col dark:text-white">…</div>
- unexpected value "I'll fetch that URL for you."
184 | const bubble = await runAndGetBubble(page);
185 | // Limit enforced: the agent stopped at the configured cap of 1.
> 186 | await expect(bubble).toContainText(LIMIT_MESSAGE, { timeout: 30000 });
| ^
187 | // run limit (1/1) ties the stop to max_iterations=1.
188 | await expect(bubble).toContainText(/\(\s*1\s*\/\s*1\s*\)/, { timeout: 10000 });
189 | });
at /home/runner/work/langflow-e2e/langflow-e2e/tests/tests-automations/regression/core-functionality/llm-agents/agent-max-iterations.spec.ts:186:32
at /home/runner/work/langflow-e2e/langflow-e2e/tests/tests-automations/regression/core-functionality/llm-agents/agent-max-iterations.spec.ts:183:9
|
|
[chromium] › tests/tests-automations/regression/core-functionality/llm-agents/agent-max-iterations.spec.ts:164:9 › Agent Max Iterations [anthropic / claude-haiku-4-5] › agent stops when max iterations is reached @regression @agents @playground:
tests/tests-automations/regression/core-functionality/llm-agents/agent-max-iterations.spec.ts#L186
1) [chromium] › tests/tests-automations/regression/core-functionality/llm-agents/agent-max-iterations.spec.ts:164:9 › Agent Max Iterations [anthropic / claude-haiku-4-5] › agent stops when max iterations is reached @regression @agentS @playground
Error: expect(locator).toContainText(expected) failed
Locator: getByTestId('div-chat-message').last()
Expected pattern: /model call limits exceeded/i
Received string: "I'll fetch that URL for you."
Timeout: 30000ms
Call log:
- Expect "toContainText" with timeout 30000ms
- waiting for getByTestId('div-chat-message').last()
34 × locator resolved to <div data-testid="div-chat-message" class="flex w-full flex-col dark:text-white">…</div>
- unexpected value "I'll fetch that URL for you."
184 | const bubble = await runAndGetBubble(page);
185 | // Limit enforced: the agent stopped at the configured cap of 1.
> 186 | await expect(bubble).toContainText(LIMIT_MESSAGE, { timeout: 30000 });
| ^
187 | // run limit (1/1) ties the stop to max_iterations=1.
188 | await expect(bubble).toContainText(/\(\s*1\s*\/\s*1\s*\)/, { timeout: 10000 });
189 | });
at /home/runner/work/langflow-e2e/langflow-e2e/tests/tests-automations/regression/core-functionality/llm-agents/agent-max-iterations.spec.ts:186:32
at /home/runner/work/langflow-e2e/langflow-e2e/tests/tests-automations/regression/core-functionality/llm-agents/agent-max-iterations.spec.ts:183:9
|
|
Run impacted E2E specs
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/cache@v4. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
|
|
Run impacted E2E specs
No files were found with the provided path: playwright-report/. No artifacts will be uploaded.
|
|
Run impacted E2E specs
select-pr-model-target: provider "openai" probed "inactive" — pinning the lane to it would skip every parametrized spec, so the lane keeps its default per-provider parametrization (costlier, but it covers something). collect-models reported: 10 of 41 candidate model(s) failed validation with the SAME model-independent error — stopped early (tried: gpt-4o-mini, gpt-4o, gpt-4.1-mini, gpt-4.1-nano, gpt-4.1, gpt-4o-mini-search-preview, gpt-4o-search-preview, gpt-5.6-sol, gpt-5.6-luna, gpt-5.6); last error: You have no credits remaining. Add credits to continue using the API at https://platform.openai.com/settings/organization/billing/.
|
|
🎭 Playwright Run Summary
1 failed
[chromium] › tests/tests-automations/regression/core-functionality/llm-agents/agent-max-iterations.spec.ts:164:9 › Agent Max Iterations [anthropic / claude-haiku-4-5] › agent stops when max iterations is reached @regression @agentS @playground
4 skipped
3 did not run
5 passed (2.4m)
|
Artifacts
Produced during runtime
| Name | Size | Digest | |
|---|---|---|---|
|
test-results-pr-31132990852
|
18.8 MB |
sha256:32b16e8a2c6edfd13403c00c36586d04b07c07ec5eb49ddd03c19b0ac443233e
|
|
|
tokens-pr-31132990852
|
1.63 KB |
sha256:ce594d78c3f4735fad4fcd4d0fbd2e192cbe38f97fcbcf6893a2b5c3e7d5e6b5
|
|