fix: return initial and enhanced chat outputs

README.md

@@ -22,12 +22,12 @@ Native-like Hermes dashboard plugin for local Ollama model management and chat.
 - Paste images directly into the composer and drag/drop images, PDFs, and text files
 - Streamed Ollama responses with a real Stop action that cancels the active request
 - Minimized-by-default expandable thinking/progress details with live stage, elapsed time, event, and character counters
-- Validation harness mode: choose one primary model and one or more independent validator models; validators review the primary draft, and the primary model applies valid corrections to compile one final answer. If the primary returns a report instead of an answer, the plugin retries finalization and never exposes validator-only text as the final response
+- Two-stage enhancement workflow: choose one primary model and one enhancement model; the primary creates the initial output, then the enhancement model receives that complete output and applies its own improvements before returning a complete enhanced output. The chat displays both labeled outputs and never displays review/validation commentary as the answer
 - Server-owned chat jobs continue after the browser closes and persist final answers for later resume. A newly opened dashboard discovers queued/running jobs from the shared server store and resumes observing them automatically.
 - SQLite is the default chat store for new users
 - Optional native PostgreSQL storage can be installed and linked explicitly from the plugin
 
-The chat supports two modes. With one selected model, it sends a normal direct request. With one primary model and at least one validator model selected, the plugin runs a validation harness: the primary creates a draft, validators independently review the request and draft in parallel, and the primary compiles one final user-facing answer from the draft and validation reports. Validator reports are returned as supporting evidence, while only the compiled primary response is persisted and displayed as the answer.
+The chat supports two modes. With one selected model, it sends a normal direct request. With a primary model and one enhancement model selected, the plugin runs a two-stage workflow: the primary produces the initial output, the enhancement model receives the original request plus the complete initial output, and the enhancement model returns the complete improved output. Both outputs are persisted in the server-owned job result and displayed separately as **Initial output** and **Enhanced output**. If the enhancement model returns empty content or review commentary, it receives one strict retry; if that also fails, the initial output is used as the enhanced output rather than exposing commentary or failing the request.
 
 ## Chat storage and durability