Revert "Migrate classifier to chat completions"

This reverts commit d48557fe5b.

AGENTS.md

@@ -10,7 +10,7 @@ This file provides guidelines for codex agents contributing to the Sortana proje
 - `options/`: The options page HTML, JavaScript and bundled Bulma CSS (v1.0.3).
 - `details.html` and `details.js`: View AI reasoning and clear cache for a message.
 - `resources/`: Images and other static files.
-- `prompt_templates/`: Custom/legacy templated message material kept in-repo for non-native prompt flows.
+- `prompt_templates/`: Prompt template files for the AI service (openai, qwen, mistral, harmony).
 - `build-xpi.ps1`: PowerShell script to package the extension.
 - `build-xpi.sh`: Bash script to package the extension.
 - `resources/svg2img.ps1`: PowerShell script to regenerate themed PNG icons from SVGs.
@@ -35,10 +35,10 @@ There are currently no automated tests for this project. If you add tests in the
 
 ## Endpoint Notes
 
-Sortana targets `POST /v1/chat/completions`. The endpoint value stored in settings is a base URL; the full request URL is constructed by appending `/v1/chat/completions` (adding a slash when needed) and defaulting to `https://` if no scheme is provided. Endpoint normalization strips a trailing `/v1`, `/v1/chat/completions`, `/v1/completions`, or `/v1/models`.
+Sortana targets the `/v1/completions` API. The endpoint value stored in settings is a base URL; the full request URL is constructed by appending `/v1/completions` (adding a slash when needed) and defaulting to `https://` if no scheme is provided.
 The options page can query `/v1/models` from the same base URL to populate the Model dropdown; selecting **None** omits the `model` field from the request payload.
 Advanced options allow an optional API key plus `OpenAI-Organization` and `OpenAI-Project` headers; these headers are only sent when values are provided.
-Requests use a Chat Completions `messages` array and ask for strict JSON schema output via `response_format`. Built-in request formats send native `system` and `user` chat messages; only the custom format sends a single templated user message. Responses are parsed from `choices[0].message`, with `match` as a boolean and `reason` as a short string, and parsing falls back to the last JSON object if a backend prepends extra reasoning text. Unsupported OpenAI sampling fields are filtered out, and the saved `max_tokens` setting is translated to `max_completion_tokens`.
+Responses are expected to include a JSON object with `match` (or `matched`) plus a short `reason` string; the parser extracts the last JSON object in the response text and ignores any surrounding commentary.
 
 ## Documentation
 

README.md

@@ -4,21 +4,22 @@
 
 Sortana is an experimental Thunderbird add-on that integrates an AI-powered filter rule. 
 It allows you to classify email messages by sending their contents to a configurable
-HTTP endpoint. Sortana uses `POST /v1/chat/completions`; the options page stores a
+HTTP endpoint. Sortana uses the `/v1/completions` API; the options page stores a base
-base URL and appends `/v1/chat/completions` when sending classification requests.
+URL and appends `/v1/completions` when sending requests. The endpoint should respond
-The same base URL is used with `/v1/models` when refreshing the model list.
+with JSON indicating whether the message meets a specified criterion, including a
-Classification requests ask the model for structured JSON output with a required
+short reasoning summary.
-`match` boolean and `reason` string.
+Responses are parsed by extracting the last JSON object in the response text and
+expecting a `match` (or `matched`) boolean plus a `reason` string.
 
 ## Features
 
 - **Configurable endpoint** – set the classification service base URL on the options page.
 - **Model selection** – load available models from the endpoint and choose one (or omit the model field).
 - **Optional OpenAI auth headers** – provide an API key plus optional organization/project headers when needed.
-- **Request formats** – built-in formats use native chat messages; a custom format can still send one templated user message when needed.
+- **Prompt templates** – choose between OpenAI/ChatML, Qwen, Mistral, Harmony (gpt-oss), or provide your own custom template.
 - **Custom system prompts** – tailor the instructions sent to the model for more precise results.
 - **Persistent result caching** – classification results and reasoning are saved to disk so messages aren't re-evaluated across restarts.
-- **Advanced parameters** – tune generation settings like temperature and top‑p from the options page. Unsupported OpenAI sampling fields are filtered out automatically.
+- **Advanced parameters** – tune generation settings like temperature, top‑p and more from the options page.
 - **Markdown conversion** – optionally convert HTML bodies to Markdown before sending them to the AI service.
 - **Debug logging** – optional colorized logs help troubleshoot interactions with the AI service.
 - **Debug tab** – view the last request payload and a diff between the unaltered message text and the final prompt.
@@ -82,11 +83,10 @@ Sortana is implemented entirely with documented MailExtension/WebExtension APIs.
 ## Usage
 
 1. Open the add-on's options and set the base URL of your classification service
-   (Sortana will append `/v1/chat/completions`). Endpoints ending in `/v1`,
+   (Sortana will append `/v1/completions`). Use the Model dropdown to load
-   `/v1/chat/completions`, `/v1/completions`, or `/v1/models` are normalized back
+   `/v1/models` and select a model or choose **None** to omit the `model` field.
-   to the same base URL. Use the Model dropdown to load `/v1/models` and select a
+   Advanced settings include optional API key, organization, and project headers
-   model or choose **None** to omit the `model` field. Advanced settings include
+   for OpenAI-hosted endpoints.
-   optional API key, organization, and project headers for OpenAI-hosted endpoints.
  2. Use the **Classification Rules** section to add a criterion and optional
    actions such as tagging, moving, copying, forwarding, replying,
    deleting or archiving a message when it matches. Drag rules to
@@ -101,11 +101,6 @@ Sortana is implemented entirely with documented MailExtension/WebExtension APIs.
    configured rules.
 4. If the toolbar icon shows a red X, it will clear after a few seconds. Open the Errors tab in Options to review the latest failures.
 
-OpenAI Chat requests are sent with a `messages` array plus a strict
-`response_format` JSON schema. Sortana maps the saved `max_tokens` setting to
-`max_completion_tokens` for Chat Completions and only forwards OpenAI-supported
-sampling fields.
-
 ### Example Filters
 
 Here are some useful and fun example criteria you can use in your filters. Filters should be able to be answered as either `true` or `false`.

_locales/en-US/messages.json

@@ -4,12 +4,12 @@
   "doesntMatch": { "message": "doesn't match" },
   "options.title": { "message": "AI Filter Options" },
   "options.endpoint": { "message": "Endpoint" },
-  "options.template": { "message": "Request format" },
+  "options.template": { "message": "Prompt template" },
   "options.customTemplate": { "message": "Custom template" },
   "options.systemInstructions": { "message": "System instructions" },
   "options.reset": { "message": "Reset to default" },
   "options.placeholders": { "message": "Placeholders: {{system}}, {{email}}, {{query}}" },
-  "template.openai": { "message": "OpenAI Chat" },
+  "template.openai": { "message": "OpenAI / ChatML" },
   "template.qwen": { "message": "Qwen" },
   "template.mistral": { "message": "Mistral" },
   "template.harmony": { "message": "Harmony (gpt-oss)" },

manifest.json

@@ -1,7 +1,7 @@
 {
   "manifest_version": 2,
   "name": "Sortana",
-  "version": "2.5.0",
+  "version": "2.4.3",
   "default_locale": "en-US",
   "applications": {
     "gecko": {

modules/AiClassifier.js

@@ -4,7 +4,7 @@ import { DEFAULT_AI_PARAMS } from "./defaultParams.js";
 
 const storage = (globalThis.messenger ?? globalThis.browser).storage;
 
-const CHAT_COMPLETIONS_PATH = "/v1/chat/completions";
+const COMPLETIONS_PATH = "/v1/completions";
 const MODELS_PATH = "/v1/models";
 
 const SYSTEM_PREFIX = `You are an email-classification assistant.
@@ -14,26 +14,11 @@ Read the email below and the classification criterion provided by the user.
 const DEFAULT_CUSTOM_SYSTEM_PROMPT = "Determine whether the email satisfies the user's criterion.";
 
 const SYSTEM_SUFFIX = `
-Return JSON that matches the requested schema exactly.
+Return ONLY a JSON object on a single line of the form:
-Set "match" to true when the email satisfies the criterion, otherwise false.
+{"match": true, "reason": "<short explanation>"} - if the email satisfies the criterion
-Set "reason" to a short explanation grounded in the email contents.`;
+{"match": false, "reason": "<short explanation>"} - otherwise
 
-const RESPONSE_FORMAT = {
+Do not add any other keys, text, or formatting.`;
-  type: "json_schema",
-  json_schema: {
-    name: "email_classification",
-    strict: true,
-    schema: {
-      type: "object",
-      properties: {
-        match: { type: "boolean" },
-        reason: { type: "string" },
-      },
-      required: ["match", "reason"],
-      additionalProperties: false,
-    },
-  },
-};
 
 let gEndpointBase = "http://127.0.0.1:5000";
 let gEndpoint = buildEndpointUrl(gEndpointBase);
@@ -59,7 +44,7 @@ function normalizeEndpointBase(endpoint) {
   if (!base) {
     return "";
   }
-  base = base.replace(/\/v1(?:\/(?:chat\/completions|completions|models))?\/?$/i, "");
+  base = base.replace(/\/v1\/(completions|models)\/?$/i, "");
   return base;
 }
 
@@ -70,7 +55,7 @@ function buildEndpointUrl(endpointBase) {
   }
   const withScheme = /^https?:\/\//i.test(base) ? base : `https://${base}`;
   const needsSlash = withScheme.endsWith("/");
-  const path = CHAT_COMPLETIONS_PATH.replace(/^\//, "");
+  const path = COMPLETIONS_PATH.replace(/^\//, "");
   return `${withScheme}${needsSlash ? "" : "/"}${path}`;
 }
 
@@ -216,9 +201,7 @@ async function setConfig(config = {}) {
   if (typeof config.debugLogging === "boolean") {
     setDebug(config.debugLogging);
   }
-  if (gTemplateName === "openai") {
+  if (gTemplateName === "custom") {
-    gTemplateText = "";
-  } else if (gTemplateName === "custom") {
     gTemplateText = gCustomTemplate;
   } else {
     gTemplateText = await loadTemplate(gTemplateName);
@@ -260,35 +243,6 @@ function buildPrompt(body, criterion) {
   return template.replace(/{{\s*(\w+)\s*}}/g, (m, key) => data[key] || "");
 }
 
-function buildUserMessage(body, criterion) {
-  return `Email contents:
-${body}
-
-Classification criterion: ${criterion}`;
-}
-
-function buildMessages(body, criterion) {
-  if (gTemplateName !== "custom") {
-    return [
-      {
-        role: "system",
-        content: buildSystemPrompt(),
-      },
-      {
-        role: "user",
-        content: buildUserMessage(body, criterion),
-      },
-    ];
-  }
-
-  return [
-    {
-      role: "user",
-      content: buildPrompt(body, criterion),
-    },
-  ];
-}
-
 function getCachedResult(cacheKey) {
   if (!gCacheLoaded) {
     return null;
@@ -309,41 +263,14 @@ function getReason(cacheKey) {
   return cacheKey && entry ? entry.reason || null : null;
 }
 
-function buildOpenAiParams() {
+function buildPayload(text, criterion) {
-  const params = {};
+  let payloadObj = Object.assign({
-
+    prompt: buildPrompt(text, criterion)
-  if (Number.isFinite(gAiParams.max_tokens) && gAiParams.max_tokens > 0) {
+  }, gAiParams);
-    params.max_completion_tokens = Math.trunc(gAiParams.max_tokens);
-  }
-  if (Number.isFinite(gAiParams.temperature)) {
-    params.temperature = gAiParams.temperature;
-  }
-  if (Number.isFinite(gAiParams.top_p)) {
-    params.top_p = gAiParams.top_p;
-  }
-  if (Number.isFinite(gAiParams.presence_penalty)) {
-    params.presence_penalty = gAiParams.presence_penalty;
-  }
-  if (Number.isFinite(gAiParams.frequency_penalty)) {
-    params.frequency_penalty = gAiParams.frequency_penalty;
-  }
-  if (Number.isInteger(gAiParams.seed) && gAiParams.seed >= 0) {
-    params.seed = gAiParams.seed;
-  }
-
-  return params;
-}
-
-function buildPayloadObject(text, criterion) {
-  const payloadObj = {
-    messages: buildMessages(text, criterion),
-    response_format: RESPONSE_FORMAT,
-    ...buildOpenAiParams(),
-  };
   if (gModel) {
     payloadObj.model = gModel;
   }
-  return payloadObj;
+  return JSON.stringify(payloadObj);
 }
 
 function reportParseError(message, detail) {
@@ -363,39 +290,7 @@ function reportParseError(message, detail) {
   }
 }
 
-function extractMessageContent(content) {
-  if (typeof content === "string") {
-    return { text: content, refusal: "" };
-  }
-  if (!Array.isArray(content)) {
-    return { text: "", refusal: "" };
-  }
-
-  const textParts = [];
-  const refusalParts = [];
-  for (const part of content) {
-    if (!part || typeof part !== "object") {
-      continue;
-    }
-    if (part.type === "text" && typeof part.text === "string") {
-      textParts.push(part.text);
-    }
-    if (part.type === "refusal" && typeof part.refusal === "string") {
-      refusalParts.push(part.refusal);
-    }
-  }
-
-  return {
-    text: textParts.join("\n").trim(),
-    refusal: refusalParts.join("\n").trim(),
-  };
-}
-
 function extractLastJsonObject(text) {
-  if (typeof text !== "string" || !text) {
-    return null;
-  }
-
   let last = null;
   let start = -1;
   let depth = 0;
@@ -442,61 +337,31 @@ function extractLastJsonObject(text) {
 }
 
 function parseMatch(result) {
-  const message = result?.choices?.[0]?.message;
+  const rawText = result.choices?.[0]?.text || "";
-  if (!message || typeof message !== "object") {
+  const candidate = extractLastJsonObject(rawText);
-    reportParseError("AI response missing assistant message.", JSON.stringify(result).slice(0, 800));
+  if (!candidate) {
-    return { matched: false, reason: "" };
+    reportParseError("No JSON object found in AI response.", rawText.slice(0, 800));
-  }
-
-  if (typeof message.refusal === "string" && message.refusal.trim()) {
-    reportParseError("Model refused classification request.", message.refusal.slice(0, 800));
-    return { matched: false, reason: message.refusal.trim() };
-  }
-
-  if (message.parsed && typeof message.parsed === "object") {
-    const parsed = message.parsed;
-    if (typeof parsed.match === "boolean" && typeof parsed.reason === "string") {
-      return { matched: parsed.match, reason: parsed.reason };
-    }
-  }
-
-  const extracted = extractMessageContent(message.content);
-  if (extracted.refusal) {
-    reportParseError("Model refused classification request.", extracted.refusal.slice(0, 800));
-    return { matched: false, reason: extracted.refusal };
-  }
-  if (!extracted.text) {
-    reportParseError("AI response missing assistant message content.", JSON.stringify(message).slice(0, 800));
     return { matched: false, reason: "" };
   }
 
   let obj;
   try {
-    obj = JSON.parse(extracted.text);
+    obj = JSON.parse(candidate);
   } catch (e) {
-    const candidate = extractLastJsonObject(extracted.text);
+    reportParseError("Failed to parse JSON from AI response.", candidate.slice(0, 800));
-    if (!candidate) {
-      reportParseError("Failed to parse JSON from AI response.", extracted.text.slice(0, 800));
-      return { matched: false, reason: "" };
-    }
-    try {
-      obj = JSON.parse(candidate);
-    } catch (inner) {
-      reportParseError("Failed to parse JSON from AI response.", extracted.text.slice(0, 800));
-      return { matched: false, reason: "" };
-    }
-  }
-
-  if (typeof obj?.match !== "boolean") {
-    reportParseError("AI response missing valid match boolean.", extracted.text.slice(0, 800));
-    return { matched: false, reason: "" };
-  }
-  if (typeof obj?.reason !== "string") {
-    reportParseError("AI response missing valid reason string.", extracted.text.slice(0, 800));
     return { matched: false, reason: "" };
   }
 
-  return { matched: obj.match, reason: obj.reason };
+  const matchValue = Object.prototype.hasOwnProperty.call(obj, "match") ? obj.match : obj.matched;
+  const matched = matchValue === true;
+  if (matchValue !== true && matchValue !== false) {
+    reportParseError("AI response missing valid match boolean.", candidate.slice(0, 800));
+  }
+
+  const reasonValue = obj.reason ?? obj.reasoning ?? obj.explaination;
+  const reason = typeof reasonValue === "string" ? reasonValue : "";
+
+  return { matched, reason };
 }
 
 function cacheEntry(cacheKey, matched, reason) {
@@ -562,10 +427,9 @@ async function classifyText(text, criterion, cacheKey = null) {
     return cached;
   }
 
-  const payloadObj = buildPayloadObject(text, criterion);
+  const payload = buildPayload(text, criterion);
-  const payload = JSON.stringify(payloadObj);
   try {
-    await storage.local.set({ lastPayload: payloadObj });
+    await storage.local.set({ lastPayload: JSON.parse(payload) });
   } catch (e) {
     aiLog('failed to save last payload', { level: 'warn' }, e);
   }

options/options.html

@@ -93,13 +93,12 @@
                 </div>
 
                 <div class="field">
-                    <label class="label" for="template">Request format</label>
+                    <label class="label" for="template">Prompt template</label>
                     <div class="control">
                         <div class="select is-fullwidth">
                             <select id="template"></select>
                         </div>
                     </div>
-                    <p class="help">Built-in formats use native chat messages over Chat Completions. Custom format sends one templated user message.</p>
                 </div>
 
                 <div id="custom-template-container" class="field is-hidden">
@@ -204,7 +203,7 @@
                         </label>
                     </div>
                     <div class="field">
-                        <label class="label" for="max_tokens">Max completion tokens</label>
+                        <label class="label" for="max_tokens">Max tokens</label>
                         <div class="control">
                             <input class="input" type="number" id="max_tokens">
                         </div>