fix: workflow inference chain — surface llama-server errors, user-turn-last, bundle-relative prompts

- LlamaCppInferenceProvider: check HTTP status and surface the real error body instead of masking it as a ChatCompletionResponse deserialization failure
- PromptRenderer: render the live conversation layer (L1) last so the user turn is the final message (fixes Qwen 'No user query found' 500 when L3 recall is present)
- TomlWorkflowLoader: resolve stage prompts relative to the workflow file's own dir (bundle), CWD-independent; config-dir fallback for globals
- SessionOrchestrator: hard-fail a stage whose declared prompt can't resolve (was a silent user-less request)
- move healthcheck prompts next to the example workflow (examples/workflows/prompts/)
This commit is contained in:
2026-06-01 23:23:29 +04:00
parent 55a18b4b3a
commit 94f7ad0ee9
6 changed files with 50 additions and 23 deletions
@@ -12,6 +12,14 @@ data class ChatMessage(
)
object PromptRenderer {
// L1 (live conversation, ends with the current user turn) must render last so
// the model template sees the user query as the final message. Background/memory
// layers (L2, L3, L4) are injected before it.
private val nonL0RenderOrder: Comparator<ContextLayer> = Comparator { a, b ->
val priority = { layer: ContextLayer -> if (layer == ContextLayer.L1) Int.MAX_VALUE else layer.ordinal }
priority(a) - priority(b)
}
fun render(contextPack: ContextPack): List<ChatMessage> {
val sorted = contextPack.layers.entries.sortedBy { it.key.ordinal }
val systemContent = sorted
@@ -19,19 +27,22 @@ object PromptRenderer {
.flatMap { it.value }
.joinToString("\n\n") { it.content }
.takeIf { it.isNotBlank() }
val conversationMessages = sorted.filter { it.key != ContextLayer.L0 }.flatMap { (_, entries) ->
entries.map { entry ->
ChatMessage(
role = when (entry.role) {
EntryRole.SYSTEM -> "system"
EntryRole.ASSISTANT -> "assistant"
EntryRole.TOOL -> "tool"
EntryRole.USER -> "user"
},
content = entry.content,
)
val conversationMessages = contextPack.layers.entries
.filter { it.key != ContextLayer.L0 }
.sortedWith(Comparator.comparing({ it.key }, nonL0RenderOrder))
.flatMap { (_, entries) ->
entries.map { entry ->
ChatMessage(
role = when (entry.role) {
EntryRole.SYSTEM -> "system"
EntryRole.ASSISTANT -> "assistant"
EntryRole.TOOL -> "tool"
EntryRole.USER -> "user"
},
content = entry.content,
)
}
}
}
val messages = buildList {
systemContent?.let { add(ChatMessage("system", it)) }
addAll(conversationMessages)