mirror of
https://github.com/ollama/ollama.git
synced 2026-09-21 13:38:14 -05:00
Daniel Hiltgen
0f25c31bd5
* qwen3.8: support developer instructions Qwen3.8 does not define a developer role, while OpenAI-compatible coding agents commonly send developer instructions before user messages. Fold the leading system/developer instruction prefix into a single system turn before Qwen3.8 validation, preserving instruction precedence without changing Qwen3.5 or other renderer behavior. Add streaming tool-call integration coverage for the native Ollama, OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages request shapes. Each case exercises prior assistant tool calls, tool results, follow-up rendering, and parsed tool-call output. Add Qwen3.8 to the release tools sweep. Removes an unnecessary unit test that should not have been included in the original 3.8 PR. * review comments
50 lines
2.1 KiB
Go
50 lines
2.1 KiB
Go
//go:build integration && fast
|
|
|
|
package integration
|
|
|
|
var (
|
|
fastNumPredictModel = "llama3.2:1b"
|
|
fastChatModels = []integrationModel{
|
|
{Name: "gemma4", MinVRAMGB: 8},
|
|
{Name: "gemma4:12b", MinVRAMGB: 16},
|
|
{Name: "qwen3.5:2b-nvfp4", MinVRAMGB: 4},
|
|
}
|
|
fastEmbedModels = []string{"qwen3-embedding"}
|
|
fastVisionTextModels = []string{"gemma4"}
|
|
fastToolsModels = []string{"qwen3.5:2b"}
|
|
fastToolsStressModels = []string{"lfm2.5"}
|
|
fastAudioModels = []string{"gemma4:e2b"}
|
|
)
|
|
|
|
func init() {
|
|
// API/basic/context/concurrency smoke cases
|
|
registerIntegrationCases(
|
|
integrationTestCase("api-generate", smol, runAPIGenerate),
|
|
integrationTestCase("api-chat", smol, runAPIChat),
|
|
integrationTestCase("api-list-models", "", runAPIListModels),
|
|
integrationTestCase("api-show-model", "llama3.2", runAPIShowModel),
|
|
integrationTestCase("generate-logprobs", smol, runAPIGenerateLogprobs),
|
|
integrationTestCase("chat-logprobs", smol, runAPIChatLogprobs),
|
|
integrationTestCase("blue-sky", smol, runBlueSky),
|
|
integrationTestCase("thinking-enabled", smol, runThinkingEnabled),
|
|
integrationTestCase("thinking-suppressed", smol, runThinkingSuppressed),
|
|
integrationModelTestCase("num-predict", fastNumPredictModel, runNumPredict),
|
|
integrationTestCase("embedding-api", "all-minilm", runAllMiniLMEmbeddings),
|
|
integrationTestCase("embed-api-truncate", "all-minilm", runAllMiniLMEmbedTruncate),
|
|
integrationTestCase("context-long-input", smol, runLongInputContext),
|
|
integrationTestCase("context-exhaustion", smol, runContextExhaustion),
|
|
integrationTestCase("generate-history", smol, runGenerateWithHistory),
|
|
integrationTestCase("concurrent-chat", smol, runConcurrentChat),
|
|
)
|
|
|
|
// Model-parametric cases
|
|
registerModelMinVRAM(fastChatModels)
|
|
registerChatCases(testModels(modelNames(fastChatModels)))
|
|
registerEmbeddingCases(testModels(fastEmbedModels))
|
|
registerVisionTextCases(testModels(fastVisionTextModels))
|
|
registerToolCases(testModels(fastToolsModels))
|
|
registerToolRouteCases(testModels(fastToolsModels))
|
|
registerToolStressCases(testModels(fastToolsStressModels))
|
|
registerAudioTranscriptionCases(testModels(fastAudioModels))
|
|
}
|