litellm/tests/e2e
yuneng-jiang 5bcced0187
feat(ui): redesign the playground chat around a single composer and inspector (#46934)
* feat(ui): add clean-slate playground chat prototype

* feat(ui): replace the playground chat with the redesigned composer and inspector

* fix(ui): close the playground chat gaps found in self-review

Resend only complete text exchanges, so empty replies, MCP direct calls and
transcriptions no longer leak into chat history. A stopped request can no longer
append output, attach its gateway trace to a newer reply or clear the newer
request's loading state. MCP selections are only pruned once both the server and
toolset lists load. The MCP tool picker lists toolsets again and calls the server
that backs the chosen tool, and a saved model the current key cannot use is
cleared when the model list loads, matching the old chat

Also vendors the scroll-fade-x utility the attachment primitive uses

* fix(ui): resolve playground toolset tools per server and drop late session ids

A toolset now lists only its own tools, each resolved on the server the toolset
names, so the args form and the call always target the same tool. A saved
toolset no longer asks for tools with its own id while the toolset list loads,
and a failed tool list says so instead of claiming the server has no tools

A stopped request can no longer overwrite the Responses session id, starting a
new chat drops a request that is still running, embeddings replies are no longer
resent as chat history, and a saved model missing from an already cached model
list is cleared too. A failing toolset list falls back right away instead of
retrying while the MCP pickers show loading

* fix(ui): guard playground sends and label inspector stats

Pressing Enter twice no longer sends the same message twice, an attachment the
new endpoint cannot take is dropped when the endpoint changes, a stopped
Responses request can no longer show its code output on a newer reply, and a
reply that broke mid-stream is no longer resent as history

The inspector's speed, cost and routing stats get the same icons as the reply
footer, and the footer's metrics now line up with its copy and Inspect buttons

* fix(ui): write playground key settings only through the encoded storage path

Key source, virtual key and custom headers now go through their own write loop, separate from the plain settings, so a key value can never take the plain sessionStorage branch

* fix(ui): restore playground BYOK connect and reconnect

Picking a BYOK server for a direct tool call now shows a key button next to the
server picker, so the key can be connected without leaving the MCP endpoint. A
connected BYOK server gets a Replace key action in the MCP dialog, also shown
when its tools fail to load, and saving a key reloads that server's tool list

* revert: restore the single playground settings storage loop

Reverts ca4e742115. The CodeQL finding covers the same encoded sessionStorage handling the old chat used, so it is left as is

* test(ui): type the BYOK credential mock without deep instantiation

* fix(ui): let users back out of replacing a BYOK key

The replace-key form in the MCP dialog now has Cancel, and it resets when another server is picked or the dialog closes, so a working key is never forced to be overwritten

* refactor(ui): name the MCP dialog row focus handler

* fix(ui): accept exact custom models, tags and decimal temperatures in the playground

A typed model or tag that is a prefix of a listed one could not be used,
because Enter picked the partial match and the custom action only showed
when nothing matched. The custom value is now a list option whenever no
exact match exists. Temperature gets an editable input beside the slider
so values finer than the 0.1 step can be sent again.

* fix(ui): stop claiming no guardrails ran when the gateway sent no headers

Direct MCP calls, A2A agents and any request that fails before headers
arrive built their trace from an empty header set, so the inspector said
no guardrails or policies ran. The gateway fields are now left unset in
that case and the inspector says the endpoint does not report them.

* fix(ui): leave policies unknown when the gateway headers are hidden

The proxy exposes x-litellm-applied-guardrails to other origins but not
x-litellm-applied-policies, so a dashboard on another origin read every
request as having run no policies. Policies are now unknown unless the
call id header is readable, and the inspector says so.
2026-10-16 14:04:36 -07:00
..
a2a test(e2e): tag a2a, access_control, other, secret_manager and migrations tests with Subject metadata (#44965) 2026-10-07 12:11:55 -07:00
access_control fix(proxy/auth): expand all-team-models sentinel for project model access checks (#43734) 2026-10-10 15:49:27 -07:00
batches test(e2e): move the harness self-tests out of tests/e2e (#45172) 2026-10-07 22:20:02 +00:00
claude_code test: fix stale and flaky tests across CircleCI, GHA and Buildkite (#45530) 2026-10-09 11:40:14 -07:00
coverage_registry fix(bedrock): forward Nova Sonic realtime tool calls with their arguments (#46214) 2026-10-16 01:10:53 +00:00
gateway test(e2e): perf rig (out-of-process mocks, PerformanceTestCase runner, per-request limits) and the small_bodies_5rps case (#46713) 2026-10-15 20:14:40 +00:00
guardrails test: migrate SDK and proxy-booting legacy CircleCI tests to their tiers (#45758) 2026-10-11 00:17:21 -07:00
llm_translation fix(bedrock): forward Nova Sonic realtime tool calls with their arguments (#46214) 2026-10-16 01:10:53 +00:00
logging test: migrate tests/llm_translation into unit, integration and e2e tiers (#45759) 2026-10-11 07:58:53 +00:00
management feat(teams): let proxy admins grant team admins the right to raise their team budget (#45404) 2026-10-09 13:39:08 -07:00
mcp fix(mcp): leave out tool texts too long to embed instead of failing tool search (#43554) 2026-10-14 14:53:00 -07:00
migrations fix(proxy-extras): hold only Prisma's lock key during migrate deploy so it never waits on the request log index build (#46660) 2026-10-15 14:47:33 -07:00
other fix(proxy): enforce the personal max_budget on proxy-admin JWTs (#43070) 2026-10-12 16:04:12 -07:00
perf test(perf): cap every background Postgres statement at 0.9 calls per request (#46957) 2026-10-16 19:58:32 +00:00
quota_management ci: run every CircleCI check from the integration workflow (#45938) 2026-10-11 07:39:16 -07:00
router test(e2e): tag router, batches and mcp tests with Subject metadata and record client steps (#44964) 2026-10-07 10:32:58 -07:00
secret_manager test: migrate SDK and proxy-booting legacy CircleCI tests to their tiers (#45758) 2026-10-11 00:17:21 -07:00
ui feat(ui): redesign the playground chat around a single composer and inspector (#46934) 2026-10-16 14:04:36 -07:00
AGENTS.md test(e2e): perf datastore limits count the Postgres statements and Redis commands a request waits on, background work reported on its own (#46798) 2026-10-15 20:10:17 -07:00
conftest.py test(e2e): rename load to perf and consolidate the opt-in into E2E_PERF_TESTS (#46077) 2026-10-12 13:54:03 -07:00
CONTRIBUTING.md ci: run every CircleCI check from the integration workflow (#45938) 2026-10-11 07:39:16 -07:00
e2e_config.py test(e2e): rename load to perf and consolidate the opt-in into E2E_PERF_TESTS (#46077) 2026-10-12 13:54:03 -07:00
e2e_db.py test(e2e): guard destructive spend-log truncate behind an explicit opt-in (#33751) 2026-07-20 08:47:39 -07:00
e2e_http.py test(e2e): perf rig (out-of-process mocks, PerformanceTestCase runner, per-request limits) and the small_bodies_5rps case (#46713) 2026-10-15 20:14:40 +00:00
e2e_metadata.py test(e2e): add enum values, auto-discovering label gates and secret hiding for e2e metadata (#44949) 2026-10-06 17:03:35 -07:00
fixture_bundle.py test: add strict stateless provider replay identity 2026-09-14 16:55:43 -07:00
fixture_canonical.py feat(e2e): key the provider cache per test and mount Bedrock behind it 2026-09-16 02:15:46 -07:00
fixture_mode.py fix(e2e): own a shared fixture's deployment by the fixture's node, not the first test 2026-09-16 17:35:05 -07:00
fixture_profile.py test: preserve strict replay numeric spelling 2026-09-14 17:11:56 -07:00
idp.py test(e2e): add enum values, auto-discovering label gates and secret hiding for e2e metadata (#44949) 2026-10-06 17:03:35 -07:00
idp_realm.json test(e2e): harden JWT fixtures and cover management lifecycles 2026-09-11 16:36:12 -07:00
junit_properties.py test(e2e): move the harness self-tests out of tests/e2e (#45172) 2026-10-07 22:20:02 +00:00
lifecycle.py test(e2e): add enum values, auto-discovering label gates and secret hiding for e2e metadata (#44949) 2026-10-06 17:03:35 -07:00
memory_readings.py test(e2e): hold every worker under an idle RSS budget before any traffic (#42552) 2026-09-22 14:47:14 -07:00
models.py fix(bedrock)!: replay redacted_thinking on Converse and keep its data as Claude's own string (#46532) 2026-10-14 19:08:14 -07:00
otel_client.py test(e2e): record steps for raw transport calls and poll helpers (#45150) 2026-10-07 15:21:26 -07:00
PROVIDER_CACHE.md test(e2e): move the harness self-tests out of tests/e2e (#45172) 2026-10-07 22:20:02 +00:00
provider_cache.py fix(e2e): bind provider-cache recordings to the deployment's test, not the serving process 2026-09-16 17:08:17 -07:00
provider_cache_redis.py chore(e2e): report the key components behind a mount that never converges 2026-09-16 15:01:08 -07:00
provider_cache_routing.py revert(e2e): unmount Gemini, its api_base means two things 2026-09-16 08:37:25 -07:00
provider_edge.py test(e2e): record steps for raw transport calls and poll helpers (#45150) 2026-10-07 15:21:26 -07:00
provider_edge_bedrock.py fix(bedrock)!: replay redacted_thinking on Converse and keep its data as Claude's own string (#46532) 2026-10-14 19:08:14 -07:00
proxy_client.py feat(e2e): record each e2e test's steps, starting with ProxyClient (#42393) 2026-09-30 19:33:53 -07:00
pytest.ini test(e2e): rename load to perf and consolidate the opt-in into E2E_PERF_TESTS (#46077) 2026-10-12 13:54:03 -07:00
stack_lock.py test(e2e): run the memory cell alone on the shared stack (#42518) 2026-09-22 15:13:37 -07:00
transport.py test(e2e): record steps for raw transport calls and poll helpers (#45150) 2026-10-07 15:21:26 -07:00