E2e workflow (#21)

Reviewed-on: #21
Co-authored-by: Mathias Scheider <mathias2784@web.de>

README.md

@@ -17,13 +17,28 @@ Create a `.env` file in the project root with the LLM connection details and the
 prefix used to identify metadata written by PhotoTools3:
 
 ```dotenv
-llm_api_base_url=https://your-openai-compatible-api/v1
+llm_api_base_url=http://localhost:1234/v1
 llm_api_key=your-api-key
 llm_default_temperature=0.2
 metadata_prefix=photools3:
+LOG_LEVEL=DEBUG
+LLM_REQUEST_TIMEOUT_SECONDS=10
+LLM_MAX_COMPLETION_TOKENS=1024
+LLM_MAX_RETRIES=5
+LLM_MAX_KEYWORDS=15
 ```
 
 Keyword suggestions are restricted to the vocabulary in `config/keywords.txt`.
+`LOG_LEVEL=DEBUG` enables detailed per-request and per-photo timings.
+`LLM_MAX_RETRIES` controls retries for malformed or structurally invalid
+responses; `5` means up to 6 requests for a photo. A valid response with
+unsupported keywords gets at most one targeted correction retry, then remaining
+invalid keywords are discarded.
+Each request is limited by `LLM_REQUEST_TIMEOUT_SECONDS`; a timeout reloads the
+LM Studio model before retrying. `LLM_MAX_COMPLETION_TOKENS` caps the generated
+response length. When all retries are exhausted, the model is reloaded before
+the failed photo is reported. `LLM_MAX_KEYWORDS` sets the maximum number of
+distinct keywords requested and stored per photo; excess keywords are discarded.
 
 ## Generate metadata