diff --git a/.vscode/settings.json b/.vscode/settings.json
index 31a2b397..ee842630 100644
--- a/.vscode/settings.json
+++ b/.vscode/settings.json
@@ -104,6 +104,7 @@
 		"stretchr",
 		"talkpanel",
 		"Telos",
+		"testpattern",
 		"Thacker",
 		"tidwall",
 		"topp",
diff --git a/completions/_fabric b/completions/_fabric
index 35101838..7659bb05 100644
--- a/completions/_fabric
+++ b/completions/_fabric
@@ -113,6 +113,7 @@ _fabric() {
     '(--suppress-think)--suppress-think[Suppress text enclosed in thinking tags]' \
     '(--think-start-tag)--think-start-tag[Start tag for thinking sections (default: <think>)]:start tag:' \
     '(--think-end-tag)--think-end-tag[End tag for thinking sections (default: </think>)]:end tag:' \
+    '(--disable-responses-api)--disable-responses-api[Disable OpenAI Responses API (default: false)]' \
     '(-h --help)'{-h,--help}'[Show this help message]' \
     '*:arguments:'
 }
diff --git a/completions/fabric.bash b/completions/fabric.bash
index cd9caf37..ca47e804 100644
--- a/completions/fabric.bash
+++ b/completions/fabric.bash
@@ -13,7 +13,7 @@ _fabric() {
   _get_comp_words_by_ref -n : cur prev words cword
 
   # Define all possible options/flags
-  local opts="--pattern -p --variable -v --context -C --session --attachment -a --setup -S --temperature -t --topp -T --stream -s --presencepenalty -P --raw -r --frequencypenalty -F --listpatterns -l --listmodels -L --listcontexts -x --listsessions -X --updatepatterns -U --copy -c --model -m --modelContextLength --output -o --output-session --latest -n --changeDefaultModel -d --youtube -y --playlist --transcript --transcript-with-timestamps --comments --metadata --language -g --scrape_url -u --scrape_question -q --seed -e --wipecontext -w --wipesession -W --printcontext --printsession --readability --input-has-vars --dry-run --serve --serveOllama --address --api-key --config --search --search-location --image-file --image-size --image-quality --image-compression --image-background --suppress-think --think-start-tag --think-end-tag --version --listextensions --addextension --rmextension --strategy --liststrategies --listvendors --shell-complete-list --help -h"
+  local opts="--pattern -p --variable -v --context -C --session --attachment -a --setup -S --temperature -t --topp -T --stream -s --presencepenalty -P --raw -r --frequencypenalty -F --listpatterns -l --listmodels -L --listcontexts -x --listsessions -X --updatepatterns -U --copy -c --model -m --modelContextLength --output -o --output-session --latest -n --changeDefaultModel -d --youtube -y --playlist --transcript --transcript-with-timestamps --comments --metadata --language -g --scrape_url -u --scrape_question -q --seed -e --wipecontext -w --wipesession -W --printcontext --printsession --readability --input-has-vars --dry-run --serve --serveOllama --address --api-key --config --search --search-location --image-file --image-size --image-quality --image-compression --image-background --suppress-think --think-start-tag --think-end-tag --disable-responses-api --version --listextensions --addextension --rmextension --strategy --liststrategies --listvendors --shell-complete-list --help -h"
 
   # Helper function for dynamic completions
   _fabric_get_list() {
diff --git a/completions/fabric.fish b/completions/fabric.fish
index 82e7164f..7e464ba7 100755
--- a/completions/fabric.fish
+++ b/completions/fabric.fish
@@ -101,4 +101,5 @@ complete -c fabric -l liststrategies -d "List all strategies"
 complete -c fabric -l listvendors -d "List all vendors"
 complete -c fabric -l shell-complete-list -d "Output raw list without headers/formatting (for shell completion)"
 complete -c fabric -l suppress-think -d "Suppress text enclosed in thinking tags"
+complete -c fabric -l disable-responses-api -d "Disable OpenAI Responses API (default: false)"
 complete -c fabric -s h -l help -d "Show this help message"
diff --git a/internal/cli/example.yaml b/internal/cli/example.yaml
index 38d3e1fc..deb039f9 100644
--- a/internal/cli/example.yaml
+++ b/internal/cli/example.yaml
@@ -24,3 +24,7 @@ raw: false
 suppressThink: false
 thinkStartTag: "<think>"
 thinkEndTag: "</think>"
+
+# OpenAI Responses API settings
+# (use this for llama-server or other OpenAI-compatible local servers)
+disableResponsesAPI: true