devs/profanity
2
0
Fork 0
mirror of https://git.jabber.space/devs/cproof.git synced 2026-07-30 15:46:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(ai): implement robust JSON model parsing

Browse Source 
Rewrote internal JSON parsing to correctly handle whitespace, escaped
quotes, and strict field context extraction. This prevents incorrect
field names or provider names from being added to the model list.

Added `ai_parse_models_from_json` public API to facilitate testing.

Changed `/ai models` default behavior to always fetch fresh models.
Replaced `--refresh` flag with `--cached` to display local cache.

Added comprehensive unit tests covering OpenAI and Perplexity formats,
array format, empty/null JSON, escaped quotes, and whitespace handling.
This commit is contained in:
Jabber Developer
2026-05-09 13:56:59 +00:00
parent 07d267b5bc
commit a898cb212d
6 changed files with 396 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

223
tests/unittests/test_ai_client.c
View File

@@ -644,3 +644,226 @@ test_ai_models_are_fresh_initial(void** state)
gboolean fresh_perplexity = ai_models_are_fresh("perplexity");
assert_true(fresh_perplexity == TRUE || fresh_perplexity == FALSE); /* Just verify no crash */
}
/* ========================================================================
* Model Parsing Tests
* ======================================================================== */
void
test_ai_parse_models_openai_format(void** state)
{
/* Test parsing OpenAI-compatible API response format */
/* Format: {"object":"list","data":[{"id":"model1",...},...]} */
ai_client_init();
AIProvider* provider = ai_add_provider("test", "https://test.api.com/v1", NULL);
/* JSON response from Perplexity/OpenAI API */
const gchar* json = "{\"object\":\"list\","
"\"data\":["
"{\"id\":\"anthropic/claude-haiku-4-5\",\"object\":\"model\",\"created\":0,\"owned_by\":\"anthropic\"},"
"{\"id\":\"anthropic/claude-opus-4-5\",\"object\":\"model\",\"created\":0,\"owned_by\":\"anthropic\"},"
"{\"id\":\"openai/gpt-5\",\"object\":\"model\",\"created\":0,\"owned_by\":\"openai\"},"
"{\"id\":\"google/gemini-3-flash-preview\",\"object\":\"model\",\"created\":0,\"owned_by\":\"google\"}"
"]}";
ai_parse_models_from_json(provider, json);
/* Verify models were parsed correctly */
assert_int_equal(4, g_list_length(provider->models));
/* Check specific models */
GList* models = provider->models;
assert_string_equal("anthropic/claude-haiku-4-5", models->data);
models = g_list_next(models);
assert_string_equal("anthropic/claude-opus-4-5", models->data);
models = g_list_next(models);
assert_string_equal("openai/gpt-5", models->data);
models = g_list_next(models);
assert_string_equal("google/gemini-3-flash-preview", models->data);
ai_provider_unref(provider);
ai_client_shutdown();
}
void
test_ai_parse_models_perplexity_format(void** state)
{
/* Test parsing actual Perplexity API response with all models from curl test */
ai_client_init();
AIProvider* provider = ai_add_provider("perplexity", "https://api.perplexity.ai/", NULL);
const gchar* json = "{\"object\":\"list\","
"\"data\":["
"{\"id\":\"anthropic/claude-haiku-4-5\",\"object\":\"model\",\"created\":0,\"owned_by\":\"anthropic\"},"
"{\"id\":\"anthropic/claude-opus-4-5\",\"object\":\"model\",\"created\":0,\"owned_by\":\"anthropic\"},"
"{\"id\":\"anthropic/claude-opus-4-6\",\"object\":\"model\",\"created\":0,\"owned_by\":\"anthropic\"},"
"{\"id\":\"anthropic/claude-opus-4-7\",\"object\":\"model\",\"created\":0,\"owned_by\":\"anthropic\"},"
"{\"id\":\"anthropic/claude-sonnet-4-5\",\"object\":\"model\",\"created\":0,\"owned_by\":\"anthropic\"},"
"{\"id\":\"anthropic/claude-sonnet-4-6\",\"object\":\"model\",\"created\":0,\"owned_by\":\"anthropic\"},"
"{\"id\":\"google/gemini-3-flash-preview\",\"object\":\"model\",\"created\":0,\"owned_by\":\"google\"},"
"{\"id\":\"google/gemini-3.1-pro-preview\",\"object\":\"model\",\"created\":0,\"owned_by\":\"google\"},"
"{\"id\":\"nvidia/nemotron-3-super-120b-a12b\",\"object\":\"model\",\"created\":0,\"owned_by\":\"nvidia\"},"
"{\"id\":\"openai/gpt-5\",\"object\":\"model\",\"created\":0,\"owned_by\":\"openai\"},"
"{\"id\":\"openai/gpt-5-mini\",\"object\":\"model\",\"created\":0,\"owned_by\":\"openai\"},"
"{\"id\":\"openai/gpt-5.1\",\"object\":\"model\",\"created\":0,\"owned_by\":\"openai\"},"
"{\"id\":\"openai/gpt-5.2\",\"object\":\"model\",\"created\":0,\"owned_by\":\"openai\"},"
"{\"id\":\"openai/gpt-5.4\",\"object\":\"model\",\"created\":0,\"owned_by\":\"openai\"},"
"{\"id\":\"openai/gpt-5.4-mini\",\"object\":\"model\",\"created\":0,\"owned_by\":\"openai\"},"
"{\"id\":\"openai/gpt-5.4-nano\",\"object\":\"model\",\"created\":0,\"owned_by\":\"openai\"},"
"{\"id\":\"openai/gpt-5.5\",\"object\":\"model\",\"created\":0,\"owned_by\":\"openai\"},"
"{\"id\":\"perplexity/sonar\",\"object\":\"model\",\"created\":0,\"owned_by\":\"perplexity\"},"
"{\"id\":\"xai/grok-4-1-fast-non-reasoning\",\"object\":\"model\",\"created\":0,\"owned_by\":\"xai\"},"
"{\"id\":\"xai/grok-4.20-multi-agent\",\"object\":\"model\",\"created\":0,\"owned_by\":\"xai\"},"
"{\"id\":\"xai/grok-4.20-non-reasoning\",\"object\":\"model\",\"created\":0,\"owned_by\":\"xai\"},"
"{\"id\":\"xai/grok-4.20-reasoning\",\"object\":\"model\",\"created\":0,\"owned_by\":\"xai\"},"
"{\"id\":\"xai/grok-4.3\",\"object\":\"model\",\"created\":0,\"owned_by\":\"xai\"}"
"]}";
ai_parse_models_from_json(provider, json);
/* Verify all 23 models were parsed correctly */
assert_int_equal(23, g_list_length(provider->models));
/* Verify NO field names or owned_by values are in the model list */
/* The bug was that "id", "object", "model", "created", "owned_by" and provider names
* like "anthropic", "google", "openai", "nvidia", "perplexity", "xai" were extracted */
GList* models = provider->models;
while (models) {
const gchar* model = (const gchar*)models->data;
/* These should never be model IDs */
assert_false(g_strcmp0(model, "id") == 0);
assert_false(g_strcmp0(model, "object") == 0);
assert_false(g_strcmp0(model, "model") == 0);
assert_false(g_strcmp0(model, "created") == 0);
assert_false(g_strcmp0(model, "owned_by") == 0);
assert_false(g_strcmp0(model, "list") == 0);
/* These are owned_by values, not model IDs */
assert_false(g_strcmp0(model, "anthropic") == 0);
assert_false(g_strcmp0(model, "google") == 0);
assert_false(g_strcmp0(model, "openai") == 0);
assert_false(g_strcmp0(model, "nvidia") == 0);
assert_false(g_strcmp0(model, "perplexity") == 0);
assert_false(g_strcmp0(model, "xai") == 0);
models = g_list_next(models);
}
/* Verify first and last model IDs */
models = provider->models;
assert_string_equal("anthropic/claude-haiku-4-5", models->data);
models = g_list_last(models);
assert_string_equal("xai/grok-4.3", models->data);
ai_provider_unref(provider);
ai_client_shutdown();
}
void
test_ai_parse_models_array_format(void** state)
{
/* Test parsing simple array format: ["model1", "model2", ...] */
ai_client_init();
AIProvider* provider = ai_add_provider("test", "https://test.api.com/v1", NULL);
const gchar* json = "[\"model1\", \"model2\", \"model3\"]";
ai_parse_models_from_json(provider, json);
assert_int_equal(3, g_list_length(provider->models));
GList* models = provider->models;
assert_string_equal("model1", models->data);
models = g_list_next(models);
assert_string_equal("model2", models->data);
models = g_list_next(models);
assert_string_equal("model3", models->data);
ai_provider_unref(provider);
ai_client_shutdown();
}
void
test_ai_parse_models_empty_json(void** state)
{
/* Test parsing empty/invalid JSON */
ai_client_init();
AIProvider* provider = ai_add_provider("test", "https://test.api.com/v1", NULL);
ai_parse_models_from_json(provider, "");
assert_null(provider->models);
assert_int_equal(0, g_list_length(provider->models));
ai_parse_models_from_json(provider, "{\"invalid\": true}");
assert_null(provider->models);
assert_int_equal(0, g_list_length(provider->models));
ai_provider_unref(provider);
ai_client_shutdown();
}
void
test_ai_parse_models_null_handling(void** state)
{
/* Test NULL handling */
ai_client_init();
AIProvider* provider = ai_add_provider("test", "https://test.api.com/v1", NULL);
/* NULL json should not crash */
ai_parse_models_from_json(provider, NULL);
assert_null(provider->models);
ai_provider_unref(provider);
ai_client_shutdown();
}
void
test_ai_parse_models_escaped_quotes(void** state)
{
/* Test parsing model IDs with escaped quotes */
ai_client_init();
AIProvider* provider = ai_add_provider("test", "https://test.api.com/v1", NULL);
const gchar* json = "{\"object\":\"list\","
"\"data\":["
"{\"id\":\"test/model\\\"with\\\"quotes\",\"object\":\"model\",\"created\":0,\"owned_by\":\"test\"}"
"]}";
ai_parse_models_from_json(provider, json);
assert_int_equal(1, g_list_length(provider->models));
/* Model ID should have the escaped quotes handled */
GList* models = provider->models;
assert_non_null(models);
ai_provider_unref(provider);
ai_client_shutdown();
}
void
test_ai_parse_models_with_whitespace(void** state)
{
/* Test parsing JSON with whitespace after colons */
ai_client_init();
AIProvider* provider = ai_add_provider("test", "https://test.api.com/v1", NULL);
/* JSON with spaces after colons (common in formatted JSON) */
const gchar* json = "{ \"object\": \"list\", "
"\"data\": [ "
"{ \"id\": \"model-with-spaces\", \"object\": \"model\", \"created\": 0, \"owned_by\": \"test\" }"
"]}";
ai_parse_models_from_json(provider, json);
assert_int_equal(1, g_list_length(provider->models));
GList* models = provider->models;
assert_string_equal("model-with-spaces", models->data);
ai_provider_unref(provider);
ai_client_shutdown();
}