special prompts validation for config errors. see #766

claude-spec/04-api-integrations.md

@@ -51,6 +51,24 @@ Content script `js/lib/diff.js` is injected into ChatGPT pages for diff-view sup
 - Worker: `js/workers/model-worker-anthropic.js`
 - Settings keys: `anthropic_api_key`, `anthropic_model`, `anthropic_version`, `anthropic_max_tokens`, `anthropic_system_prompt`, `anthropic_temperature`
 
+## Configuration Validation
+
+For special prompts (`mzta_specialCommand`), required fields are validated in `initWorker()` (`js/mzta-special-commands.js`) **before** the worker is created. If a required field is empty, an `Error` with `isConfigError = true` is thrown. Validation covers:
+
+| Provider | Required fields |
+|----------|----------------|
+| `chatgpt_api` | `chatgpt_api_key`, `chatgpt_model` |
+| `google_gemini_api` | `google_gemini_api_key`, `google_gemini_model` |
+| `ollama_api` | `ollama_host`, `ollama_model` |
+| `openai_comp_api` | `openai_comp_host`, `openai_comp_model` |
+| `anthropic_api` | `anthropic_api_key`, `anthropic_model`, `anthropic_version` |
+
+Validation is skipped when `use_specific_api = true` (i.e., the prompt's own `api_type` overrides the global setting — credentials come from the prompt config, not global prefs).
+
+The `isConfigError` flag on the thrown error tells callers in `mzta-background.js` to display the error in the panel **without saving it to storage** — so the user can fix settings and retry cleanly.
+
+For regular prompts (`openChatGPT()`), validation still happens inside the listener callback after the API webchat window is created (unchanged behavior).
+
 ## Web Worker Pattern
 
 For all API-based providers (everything except ChatGPT Web), the call goes through a Web Worker:

js/mzta-special-commands.js

@@ -22,6 +22,33 @@
     integration_options_config
  } from "../options/mzta-options-default.js";
  import { taLogger } from './mzta-logger.js';
+
+ function validateAPIConfig(llm, prefs) {
+    switch (llm) {
+        case 'chatgpt_api':
+            if (!prefs.chatgpt_api_key) return browser.i18n.getMessage('chatgpt_empty_apikey');
+            if (!prefs.chatgpt_model)   return browser.i18n.getMessage('chatgpt_empty_model');
+            break;
+        case 'google_gemini_api':
+            if (!prefs.google_gemini_api_key) return browser.i18n.getMessage('google_gemini_empty_apikey');
+            if (!prefs.google_gemini_model)   return browser.i18n.getMessage('google_gemini_empty_model');
+            break;
+        case 'ollama_api':
+            if (!prefs.ollama_host)  return browser.i18n.getMessage('ollama_empty_host');
+            if (!prefs.ollama_model) return browser.i18n.getMessage('ollama_empty_model');
+            break;
+        case 'openai_comp_api':
+            if (!prefs.openai_comp_host)  return browser.i18n.getMessage('OpenAIComp_empty_host');
+            if (!prefs.openai_comp_model) return browser.i18n.getMessage('OpenAIComp_empty_model');
+            break;
+        case 'anthropic_api':
+            if (!prefs.anthropic_api_key) return browser.i18n.getMessage('anthropic_empty_apikey');
+            if (!prefs.anthropic_model)   return browser.i18n.getMessage('anthropic_empty_model');
+            if (!prefs.anthropic_version) return browser.i18n.getMessage('anthropic_empty_version');
+            break;
+    }
+    return null;
+ }
  
  export class mzta_specialCommand {
     
@@ -92,6 +119,15 @@
 
         const prefs_api = await browser.storage.sync.get(prefsToGet);
 
+        if (!use_specific_api) {
+            const configError = validateAPIConfig(this.llm, prefs_api);
+            if (configError) {
+                const err = new Error(configError);
+                err.isConfigError = true;
+                throw err;
+            }
+        }
+
         let workerInitMessage = {
             type: 'init',
             do_debug: this.do_debug,

mzta-background.js

@@ -705,7 +705,7 @@ async function _generateSummaryForMessage(headerMessageId, tabId = null, options
 
     } catch (error) {
         console.error("[ThunderAI] Error generating summary:", error);
-        await summaryStore.saveError(headerMessageId, error.message || String(error));
+        if (!error.isConfigError) await summaryStore.saveError(headerMessageId, error.message || String(error));
         if (tabId) browser.tabs.sendMessage(tabId, { command: "showSummary", data: { error: true, message: error.message || "Failed to generate summary" } });
         taWorkingStatus.stopWorking();
     }
@@ -805,7 +805,7 @@ async function _generateTranslationForMessage(headerMessageId, tabId = null, opt
 
     } catch (error) {
         console.error("[ThunderAI] Error generating translation:", error);
-        await translationStore.saveError(headerMessageId, error.message || String(error));
+        if (!error.isConfigError) await translationStore.saveError(headerMessageId, error.message || String(error));
         if (tabId) browser.tabs.sendMessage(tabId, { command: "showTranslation", data: { error: true, message: error.message || "Failed to generate translation" } });
         taWorkingStatus.stopWorking();
     }
@@ -984,8 +984,12 @@ async function _generateSpamReportForMessage(headerMessageId, options = {}) {
 
     } catch (error) {
         console.error("[ThunderAI] Error generating spam report:", error);
-        let err_data = await spamReport.saveError(headerMessageId, error.message || String(error));
-        await updateSpamPanel(headerMessageId, "showSpamReport", err_data);
+        if (error.isConfigError) {
+            await updateSpamPanel(headerMessageId, "showSpamReport", { spamValue: -999, explanation: error.message || String(error) });
+        } else {
+            let err_data = await spamReport.saveError(headerMessageId, error.message || String(error));
+            await updateSpamPanel(headerMessageId, "showSpamReport", err_data);
+        }
         return { success: false };
     }
 }