fix: workflow inference chain — surface llama-server errors, user-turn-last, bundle-relative prompts · 94f7ad0ee9 - correx

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:

kami

2026-06-01 23:23:29 +04:00

parent 55a18b4b3a

commit 94f7ad0ee9

6 changed files with 50 additions and 23 deletions

examples/workflows/prompts/healthcheck_execute.md

View File

@@ -0,0 +1,4 @@
 # healthcheck_execute.md
 Run `scripts/healthcheck.sh` and report the results.
 If the script fails, report the error and exit code.