experiment(confidence-engine): expose reconstruction provider seam
This commit is contained in:
@@ -122,6 +122,12 @@
|
||||
- An experiment-only OpenAI Responses API provider apparatus exists for `gpt-5.6-terra`, using the same current v0.5 prompt and canonical reconstruction schema. Production provider selection remains Ollama/Qwen.
|
||||
- No live OpenAI calls have occurred. Next boundary: a bounded live semantic comparison, not production migration.
|
||||
|
||||
## Reconstruction provider injection seam
|
||||
|
||||
- OpenAI provider apparatus exists at `860ee6f`; the canonical helper was previously blocked because `startCase()` and `analyseScenario()` created providers internally.
|
||||
- An optional reconstruction-provider injection seam now carries an experiment provider through the same production analysis path. Production callers still default to configured Ollama/Qwen through `getProvider()`.
|
||||
- No live calls occurred. Next boundary: exactly one live OpenAI fixed-scenario run through the canonical helper; this is not a production provider migration.
|
||||
|
||||
## Current product architecture
|
||||
|
||||
Three distinct routes, not a single page:
|
||||
|
||||
Reference in New Issue
Block a user