diff --git a/examples/server/server.cpp b/examples/server/server.cpp index 1ae3a9fec..aedfca0d6 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -3249,7 +3249,7 @@ int main(int argc, char ** argv) { if (!params.api_keys.empty()) { // for now, if API key is set, web UI is unusable - svr->Get("/", [&](const httplib::Request & req, httplib::Response & res) { + svr->Get("/", [&](const httplib::Request &, httplib::Response & res) { return res.set_content("Web UI is disabled because API key is set.", "text/html; charset=utf-8"); }); } else { diff --git a/examples/server/tests/features/security.feature b/examples/server/tests/features/security.feature index eb82e7aca..0a3c5cc77 100644 --- a/examples/server/tests/features/security.feature +++ b/examples/server/tests/features/security.feature @@ -5,7 +5,7 @@ Feature: Security Background: Server startup with an api key defined Given a server listening on localhost:8080 And a model file tinyllamas/stories260K.gguf from HF repo ggml-org/models - And a server api key llama.cpp + And a server api key THIS_IS_THE_KEY Then the server is starting Then the server is healthy @@ -16,11 +16,11 @@ Feature: Security And a completion request with api error Examples: Prompts - | api_key | api_error | - | llama.cpp | no | - | llama.cpp | no | - | hackeme | raised | - | | raised | + | api_key | api_error | + | THIS_IS_THE_KEY | no | + | THIS_IS_THE_KEY | no | + | hackeme | raised | + | | raised | Scenario Outline: OAI Compatibility Given a system prompt test @@ -32,10 +32,10 @@ Feature: Security Given an OAI compatible chat completions request with api error Examples: Prompts - | api_key | api_error | - | llama.cpp | no | - | llama.cpp | no | - | hackme | raised | + | api_key | api_error | + | THIS_IS_THE_KEY | no | + | THIS_IS_THE_KEY | no | + | hackme | raised | Scenario Outline: OAI Compatibility (invalid response formats) Given a system prompt test @@ -55,7 +55,7 @@ Feature: Security Scenario Outline: CORS Options - Given a user api key llama.cpp + Given a user api key THIS_IS_THE_KEY When an OPTIONS request is sent from Then CORS header is set to diff --git a/examples/server/tests/features/steps/steps.py b/examples/server/tests/features/steps/steps.py index bcc132c0b..540a2ecd5 100644 --- a/examples/server/tests/features/steps/steps.py +++ b/examples/server/tests/features/steps/steps.py @@ -1299,7 +1299,8 @@ async def wait_for_slots_status(context, async with aiohttp.ClientSession(timeout=DEFAULT_TIMEOUT_SECONDS) as session: while True: - async with await session.get(f'{base_url}/slots', params=params) as slots_response: + headers = {'Authorization': f'Bearer {context.server_api_key}'} + async with await session.get(f'{base_url}/slots', params=params, headers=headers) as slots_response: status_code = slots_response.status slots = await slots_response.json() if context.debug: diff --git a/examples/server/utils.hpp b/examples/server/utils.hpp index 701a7851f..452606cca 100644 --- a/examples/server/utils.hpp +++ b/examples/server/utils.hpp @@ -90,7 +90,7 @@ inline std::string format_chat(const struct llama_model * model, const std::stri return formatted_chat; } -std::string llama_get_chat_template(const struct llama_model * model) { +static std::string llama_get_chat_template(const struct llama_model * model) { std::string template_key = "tokenizer.chat_template"; // call with NULL buffer to get the total size of the string int32_t res = llama_model_meta_val_str(model, template_key.c_str(), NULL, 0);