robbond/confidence-engine
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

experiment(confidence-engine): route UI journey provider centrally

Browse Source
This commit is contained in:
robbond
2026-09-07 09:35:53 +01:00
parent 642a969b18
commit bb3082d633
15 changed files with 158 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/current-handoff.md
+7 -1
View File
@@ -19,7 +19,7 @@ unless new end-to-end user-flow evidence reopens one of those boundaries.
**Immediate next evidence question:**
Can the real browser UI run an entire investigation using OpenAI/Terra for every LLM stage, without any stage silently reverting to the default Ollama/Qwen provider?
Measure one real browser investigation configured for OpenAI/Terra across every LLM stage, including user-visible latency, call sequence, and cost.
If YES, the next live experiment is one timed/costed OpenAI UI investigation measuring:
- user-visible latency
@@ -27,6 +27,12 @@ If YES, the next live experiment is one timed/costed OpenAI UI investigation mea
- token usage where available
- approximate cost per investigation
## Server-owned UI journey provider experiment
- Server-only `CONFIDENCE_ENGINE_EXPERIMENT_PROVIDER=openai` centrally resolves the existing OpenAI provider and `gpt-5.6-terra`; without it, normal production resolution remains Ollama/Qwen. An OpenAI key alone does not switch providers.
- Browser request contracts and client state remain unchanged. Deterministic coverage includes initial start, normal update, episode reconsideration, focused deconstruction, overview synthesis, and Current Understanding synthesis.
- Zero live calls occurred. Next boundary: one real Playwright-driven Terra investigation measuring user-visible latency, actual LLM-call sequence, and OpenAI usage/cost.
## Repository checkpoint
- **Branch:** `feature/initial-decomposition-v0.61`