diff --git a/routes/email_helpers.py b/routes/email_helpers.py index c8639e1c7..257f5f921 100644 --- a/routes/email_helpers.py +++ b/routes/email_helpers.py @@ -247,6 +247,7 @@ import re as _re_reply _REPLY_OPEN_RE = _re_reply.compile(r"<<<\s*(?:REPLY|SUMMARY|OUTPUT)\s*>>+", _re_reply.I) _REPLY_CLOSE_RE = _re_reply.compile(r"<<<\s*END\s*>>+", _re_reply.I) _REPLY_ROLE_MARKER_RE = _re_reply.compile(r"?|?", _re_reply.I) +_SUMMARY_BULLET_RE = _re_reply.compile(r"^(?:[-*\u2022]\s+|\d+[.)]\s+)") def _extract_reply(text: str) -> str: @@ -277,6 +278,125 @@ def _extract_reply(text: str) -> str: return _strip_think(t).strip() +def _build_email_summary_messages(sender: str, subject: str, body_for_llm: str) -> list[dict[str, str]]: + return [ + { + "role": "system", + "content": ( + "You are an email summarizer. Format: 1-3 short bullet points " + "(use '- '). Cover: main point, action items, deadlines. If the " + "email has attachments (marked '--- ATTACHMENTS ---'), USE THEIR " + "CONTENTS - pull invoice totals, deadlines, key clauses, concrete " + "numbers/dates from PDFs/docs into the bullets. Be terse.\n\n" + "OUTPUT FORMAT: Put ONLY the bullet points between these exact " + "markers, each on its own line:\n" + "<<>>\n" + "- ...\n" + "<<>>\n" + "Any reasoning must come BEFORE <<>> (ideally inside " + "...). Only the text between the markers is kept." + ), + }, + { + "role": "user", + "content": ( + f"From: {sender}\nSubject: {subject}\n\n{body_for_llm[:12000]}" + "\n\n---\n\nSummarize the email. Output the bullets between " + "<<>> and <<>>." + ), + }, + ] + + +async def _generate_email_summary( + url: str, + model: str, + sender: str, + subject: str, + body_for_llm: str, + *, + headers: dict | None = None, + max_tokens: int = 8192, + timeout: int = 180, +) -> str: + """Generate an interactive email summary through the shared LLM adapter.""" + from src.llm_core import llm_call_async + + raw = await llm_call_async( + url=url, + model=model, + messages=_build_email_summary_messages(sender, subject, body_for_llm), + temperature=0.3, + max_tokens=max_tokens, + headers=headers, + timeout=timeout, + workload="foreground", + ) + return _normalize_email_summary(raw) + + +async def _generate_scheduled_email_summary( + url: str, + model: str, + sender: str, + subject: str, + body_for_llm: str, + *, + headers: dict | None = None, + owner: str | None = None, + max_tokens: int = 8192, + timeout: int = 180, +) -> str: + """Generate a scheduled summary through the background task candidate chain.""" + from src.task_endpoint import task_llm_call_async + + raw = await task_llm_call_async( + messages=_build_email_summary_messages(sender, subject, body_for_llm), + fallback_url=url, + fallback_model=model, + fallback_headers=headers, + owner=owner, + temperature=0.3, + max_tokens=max_tokens, + timeout=timeout, + ) + return _normalize_email_summary(raw) + + +def _normalize_email_summary(raw) -> str: + """Extract a stable cache/UI summary from provider output.""" + raw_text = raw or "" + if _REPLY_OPEN_RE.search(raw_text): + summary = _extract_reply(raw_text) + if summary: + return summary + + cleaned = _strip_think(raw_text).strip() + bullets = [ + line.strip() + for line in cleaned.splitlines() + if _SUMMARY_BULLET_RE.match(line.strip()) + ] + if bullets: + return "\n".join(bullets) + return cleaned.strip() + + +EMAIL_SUMMARY_ERROR_CODE = "email_summary_unavailable" +EMAIL_SUMMARY_ERROR_MESSAGE = "Failed to summarize" + + +def _email_summary_failure_log_detail(exc: BaseException) -> str: + """Return useful provider-failure metadata without echoing exception text.""" + detail = f"type={type(exc).__name__}" + status = getattr(exc, "status_code", None) + if status is None: + status = getattr(getattr(exc, "response", None), "status_code", None) + if isinstance(status, int): + detail += f" status={status}" + return detail + + def _apply_email_style_mechanics(text: str) -> str: """Enforce deterministic writing-style mechanics that models often miss.""" if not text: diff --git a/routes/email_pollers.py b/routes/email_pollers.py index 5d96bd0f9..a2507989d 100644 --- a/routes/email_pollers.py +++ b/routes/email_pollers.py @@ -40,6 +40,7 @@ from routes.email_helpers import ( _pre_retrieve_context, _attach_compose_uploads, _cleanup_compose_uploads, _q, SCHEDULED_DB, _EMAIL_REPLY_SYS_PROMPT_BASE, _email_cache_owner_clause, + _generate_scheduled_email_summary, _email_summary_failure_log_detail, ) logger = logging.getLogger(__name__) @@ -653,6 +654,7 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None no_msgid = 0 examined = 0 _summaries_created = 0 + _summary_failed = 0 _events_created = 0 _replies_drafted = 0 _reply_failed = 0 @@ -785,16 +787,17 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None if need_sum: try: - summary = await task_llm_call_async( - messages=[ - {"role": "system", "content": "You are an email summarizer. Format: 1-3 short bullet points (use '- '). Cover: main point, action items, deadlines. If the email has attachments (marked '--- ATTACHMENTS ---'), USE THEIR CONTENTS — pull out invoice totals, deadlines, key clauses, any concrete numbers/dates in PDFs/docs, and reflect them in the bullets. Be terse.\n\nOUTPUT FORMAT: Put ONLY the bullet points between these exact markers, each on its own line:\n<<>>\n- ...\n<<>>\nAny reasoning or planning must come BEFORE <<>> (ideally inside ...). Only the text between the markers is kept."}, - {"role": "user", "content": f"From: {sender}\nSubject: {subject}\n\n{body_for_llm[:12000]}\n\n---\n\nSummarize the email. Output the bullets between <<>> and <<>>."}, - ], - fallback_url=url, fallback_model=model, fallback_headers=headers, + summary = await _generate_scheduled_email_summary( + url=url, + model=model, + sender=sender, + subject=subject, + body_for_llm=body_for_llm, + headers=req_headers, owner=account_owner or None, - temperature=0.3, max_tokens=16384, timeout=240, + max_tokens=16384, + timeout=240, ) - summary = _extract_reply((summary or "").strip()) if summary: _c = _sql3.connect(SCHEDULED_DB) _c.execute(""" @@ -808,10 +811,19 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None _summaries_created += 1 _uid_text = uid.decode() if isinstance(uid, bytes) else str(uid) _detail_lines.append(f"summary · {_folder}#{_uid_text} · {subject or '(no subject)'} — {sender or '(unknown sender)'}") + else: + _summary_failed += 1 + _uid_text = uid.decode() if isinstance(uid, bytes) else str(uid) + _detail_lines.append(f"summary empty · {_folder}#{_uid_text} · {subject or '(no subject)'} — {sender or '(unknown sender)'}") except Exception as e: + _summary_failed += 1 _uid_text = uid.decode() if isinstance(uid, bytes) else str(uid) _detail_lines.append(f"summary failed · {_folder}#{_uid_text} · {subject or '(no subject)'} — {sender or '(unknown sender)'}") - logger.warning(f"Auto-summary {uid} failed: {e}") + logger.warning( + "Auto-summary uid=%s failed %s", + _uid_text, + _email_summary_failure_log_detail(e), + ) if need_reply: await _emit_progress(progress_cb, f"Drafting reply {processed + 1}/{_max_process} · checked {examined}/{len(uid_list)}") @@ -1320,6 +1332,8 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None parts.append(f"processed {processed} new") if auto_sum: parts.append(f"summarized {_summaries_created}") + if _summary_failed: + parts.append(f"{_summary_failed} summary failed") if auto_reply_draft: parts.append(f"drafted {_replies_drafted} repl" + ("y" if _replies_drafted == 1 else "ies")) if _reply_failed: diff --git a/routes/email_routes.py b/routes/email_routes.py index 3c8e407bd..76a744ce1 100644 --- a/routes/email_routes.py +++ b/routes/email_routes.py @@ -57,7 +57,8 @@ from routes.email_helpers import ( _extract_attachment_to_disk, _extract_html, _extract_text, _fetch_sender_thread_context, _pre_retrieve_context, _EMAIL_REPLY_SYS_PROMPT_BASE, _POOL_HOOKS, - _friendly_email_auth_error, + _friendly_email_auth_error, _email_summary_failure_log_detail, + _generate_email_summary, EMAIL_SUMMARY_ERROR_CODE, EMAIL_SUMMARY_ERROR_MESSAGE, SendEmailRequest, ExtractStyleRequest, ATTACHMENTS_DIR, COMPOSE_UPLOADS_DIR, SCHEDULED_DB, attachment_extract_dir, _email_cache_owner_clause, email_translation_body_hash, @@ -4766,8 +4767,6 @@ def setup_email_routes(): """Generate a quick AI summary of an email body.""" try: from src.endpoint_resolver import resolve_endpoint - from src.llm_core import _uses_max_completion_tokens, _restricts_temperature - import requests as _req body = data.get("body", "") subject = data.get("subject", "") @@ -4778,7 +4777,11 @@ def setup_email_routes(): if account_id: _assert_owns_account(account_id, owner) if not body: - return {"success": False, "error": "No body provided"} + return { + "success": False, + "error": "No body provided", + "error_code": "email_summary_missing_body", + } # If we know which UID this is, fetch the raw message and pull # attachment text so the summary can reference invoice totals, @@ -4807,53 +4810,43 @@ def setup_email_routes(): if not url: url, model, headers = resolve_endpoint("default", owner=owner) if not url or not model: - return {"success": False, "error": "No LLM endpoint configured"} + return { + "success": False, + "error": "No model configured for email summaries", + "error_code": "email_summary_not_configured", + } req_headers = {"Content-Type": "application/json"} if headers: req_headers.update(headers) - tok_key = "max_completion_tokens" if _uses_max_completion_tokens(model) else "max_tokens" - payload = { - "model": model, - "messages": [ - {"role": "system", "content": "You are an email summarizer. Format: 1-3 short bullet points (use '- '). Cover: main point, action items, deadlines. If the email has attachments (marked '--- ATTACHMENTS ---'), USE THEIR CONTENTS — pull invoice totals, deadlines, key clauses, concrete numbers/dates from PDFs/docs into the bullets. Be terse.\n\nOUTPUT FORMAT: Put ONLY the bullet points between these exact markers, each on its own line:\n<<>>\n- ...\n<<>>\nAny reasoning must come BEFORE <<>> (ideally inside ...). Only the text between the markers is kept."}, - {"role": "user", "content": f"From: {sender}\nSubject: {subject}\n\n{body_for_llm[:12000]}\n\n---\n\nSummarize the email. Output the bullets between <<>> and <<>>."}, - ], - tok_key: 8192, - "temperature": 0.3, - "stream": False, - } - # Reasoning models (o1/o3/o4/gpt-5) reject an explicit temperature. - if _restricts_temperature(model): - payload.pop("temperature", None) - resp = await asyncio.to_thread( - _req.post, url, json=payload, headers=req_headers, timeout=180 - ) - if not resp.ok: - return {"success": False, "error": f"LLM HTTP {resp.status_code}"} - rdata = resp.json() - msg = (rdata.get("choices") or [{}])[0].get("message", {}) - content = (msg.get("content") or "").strip() - content = _extract_reply(content) + try: + content = await _generate_email_summary( + url=url, + model=model, + sender=sender, + subject=subject, + body_for_llm=body_for_llm, + headers=req_headers, + max_tokens=8192, + timeout=180, + ) + except Exception as e: + logger.warning( + "Email summary LLM call failed %s", + _email_summary_failure_log_detail(e), + ) + return { + "success": False, + "error": EMAIL_SUMMARY_ERROR_MESSAGE, + "error_code": EMAIL_SUMMARY_ERROR_CODE, + } if not content: - # Model put everything in reasoning_content — extract bullet points - rc = (msg.get("reasoning_content") or "").strip() - # Find bullet-point style output (lines starting with -, •, *, or numbered) - bullet_lines = [] - for line in rc.split("\n"): - stripped = line.strip() - if re.match(r"^[-•*]\s+|^\d+[.)]\s+", stripped): - bullet_lines.append(stripped) - if bullet_lines: - content = "\n".join(bullet_lines) - else: - # Last resort: take the last paragraph - paragraphs = [p.strip() for p in rc.split("\n\n") if p.strip()] - content = paragraphs[-1] if paragraphs else rc[:500] - - if not content: - return {"success": False, "error": "Empty response from model"} + return { + "success": False, + "error": "The model returned an empty summary", + "error_code": "email_summary_empty", + } # Cache the summary if we have a message_id mid = data.get("message_id", "") @@ -4876,8 +4869,15 @@ def setup_email_routes(): return {"success": True, "summary": content, "model_used": model} except Exception as e: - logger.error(f"Failed to summarize: {e}") - return {"success": False, "error": "Mail operation failed"} + logger.error( + "Email summary route failed %s", + _email_summary_failure_log_detail(e), + ) + return { + "success": False, + "error": EMAIL_SUMMARY_ERROR_MESSAGE, + "error_code": EMAIL_SUMMARY_ERROR_CODE, + } @router.post("/translate") async def translate_email(data: dict, owner: str = Depends(require_owner)): diff --git a/src/tool_parsing.py b/src/tool_parsing.py index 2885cc00f..98dc1b5f6 100644 --- a/src/tool_parsing.py +++ b/src/tool_parsing.py @@ -187,8 +187,12 @@ _FUNCTION_MODEL_NAME_RE = re.compile( _FUNCTION_MODEL_PARAMS_OPEN_RE = re.compile(r"\s*", re.IGNORECASE) _FUNCTION_MODEL_PARAMS_CLOSE_RE = re.compile(r"", re.IGNORECASE) _QWEN_ROLE_MARKER_RE = re.compile(r"?|?", re.IGNORECASE) +# At least one pipe is required around `end`. Both pipes used to be optional +# (`\|?end\|?`), which also matched a bare `end` on its own line and deleted it +# from ordinary prose and from Ruby/Lua/shell snippets that close blocks with +# one; see #5547. `|end`, `end|`, `|end|` and `/|end|` still strip as before. _QWEN_BARE_MARKER_RE = re.compile( - r"(?:^|[\t\r\n ])(?:\|?end\|?|/?\|end\|)(?=[\t\r\n ]|$)|" + r"(?:^|[\t\r\n ])(?:/?\|end\||\|end|end\|)(?=[\t\r\n ]|$)|" r"(?:^|[\t\r\n ])assistan(?:t)?(?=[\t\r\n ]|$)", re.IGNORECASE, ) diff --git a/static/app.js b/static/app.js index 97f0ae77e..2f1e8d4bf 100644 --- a/static/app.js +++ b/static/app.js @@ -10,14 +10,14 @@ import modelsModule from './js/models.js?v=20260715startupcalm2'; import ragModule from './js/rag.js'; import presetsModule from './js/presets.js'; import searchModule from './js/search.js'; -import chatModule from './js/chat.js?v=20260722ctxheader4'; +import chatModule from './js/chat.js?v=20260801fix1'; import compareModule from './js/compare/index.js?v=20260723compareicon2'; import documentModule from './js/document.js?v=20260722emailfastindex1'; import searchChatModule from './js/search-chat.js'; import { makeWindowDraggable } from './js/windowDrag.js'; import markdownModule from './js/markdown.js'; import chatRenderer from './js/chatRenderer.js?v=20260722emailfastindex1'; -import sessionModule from './js/sessions.js?v=20260722ctxheader4'; +import sessionModule from './js/sessions.js'; import memoryModule from './js/memory.js?v=20260722memoryloading1'; import voiceRecorderModule from './js/voiceRecorder.js'; import censorModule from './js/censor.js'; @@ -1689,12 +1689,20 @@ function initializeEventListeners() { const newMemoryInput = el('new-memory-input'); if (newMemoryInput) { - newMemoryInput.addEventListener('keypress', (e) => { - if (e.key === 'Enter') { + // keydown, not the deprecated keypress: keypress is not guaranteed to + // fire for Enter everywhere, which left the Add Memory form with no + // working submit path (#5828). + newMemoryInput.addEventListener('keydown', (e) => { + if (e.key === 'Enter' && !e.isComposing) { + e.preventDefault(); memoryModule.addNewMemory(); } }); } + const newMemoryAddBtn = el('new-memory-add-btn'); + if (newMemoryAddBtn) { + newMemoryAddBtn.addEventListener('click', () => memoryModule.addNewMemory()); + } // Voice recording is handled by the dual-purpose send/mic button (see below) @@ -3908,85 +3916,10 @@ function startOdysseusApp() { const messageInput = el('message'); const modelPickerWrap = document.getElementById('model-picker-wrap'); - function _readComposerPromptHistory() { - const chatBox = document.getElementById('chat-history'); - if (!chatBox) return []; - return Array.from(chatBox.querySelectorAll('.msg-user')) - .reverse() - .map(msg => { - const body = msg.querySelector('.body'); - return msg.dataset?.raw || (body ? body.textContent : '') || ''; - }) - .filter(Boolean); - } - - if (messageInput && !messageInput._odysseusPromptRecallCapture) { - messageInput._odysseusPromptRecallCapture = true; - let recallHistory = []; - let recallIndex = -1; - let lastRecalled = ''; - const norm = (v) => String(v || '').replace(/\r\n/g, '\n').trimEnd(); - messageInput.addEventListener('input', () => { - if (norm(messageInput.value) === norm(lastRecalled)) return; - recallHistory = []; - recallIndex = -1; - lastRecalled = ''; - try { delete messageInput.dataset.odysseusRecallIndex; } catch {} - }, true); - messageInput.addEventListener('keydown', (e) => { - if (e.key !== 'ArrowUp' && e.key !== 'ArrowDown') return; - if (e.shiftKey || e.altKey || e.ctrlKey || e.metaKey || e.isComposing) return; - if (window._ghostAutocomplete?.isActive?.()) return; - const fresh = _readComposerPromptHistory(); - const history = fresh.length ? fresh : recallHistory; - if (!history.length) return; - const current = norm(messageInput.value); - let currentIndex = current ? history.findIndex(item => norm(item) === current) : -1; - if (current && currentIndex < 0 && current === norm(lastRecalled)) currentIndex = recallIndex; - if (current && currentIndex < 0) { - const markedIndex = Number(messageInput.dataset.odysseusRecallIndex); - if (Number.isInteger(markedIndex) && markedIndex >= 0 && markedIndex < history.length) { - currentIndex = markedIndex; - } - } - e.preventDefault(); - e.stopPropagation(); - e.stopImmediatePropagation(); - if (e.key === 'ArrowDown') { - if (currentIndex < 0) return; - const nextIndex = currentIndex - 1; - if (nextIndex < 0) { - recallHistory = history; - recallIndex = -1; - lastRecalled = ''; - try { delete messageInput.dataset.odysseusRecallIndex; } catch {} - messageInput.value = ''; - try { messageInput.selectionStart = messageInput.selectionEnd = 0; } catch {} - try { uiModule.autoResize(messageInput); } catch {} - return; - } - const recalled = history[nextIndex]; - recallHistory = history; - recallIndex = nextIndex; - lastRecalled = recalled; - try { messageInput.dataset.odysseusRecallIndex = String(nextIndex); } catch {} - messageInput.value = recalled; - try { messageInput.selectionStart = messageInput.selectionEnd = recalled.length; } catch {} - try { uiModule.autoResize(messageInput); } catch {} - return; - } - const nextIndex = currentIndex >= 0 ? Math.min(currentIndex + 1, history.length - 1) : 0; - const recalled = history[nextIndex]; - if (!recalled) return; - recallHistory = history; - recallIndex = nextIndex; - lastRecalled = recalled; - try { messageInput.dataset.odysseusRecallIndex = String(nextIndex); } catch {} - messageInput.value = recalled; - try { messageInput.selectionStart = messageInput.selectionEnd = recalled.length; } catch {} - try { uiModule.autoResize(messageInput); } catch {} - }, true); - } + // ArrowUp/ArrowDown prompt recall on #message lives in + // static/js/composerArrowUpRecall.js (wired from chat.js). Do not re-add a + // copy here: two capture-phase listeners on the same textarea meant the one + // without the draft guard won and ate unsent multi-line prompts (#5862). const _sendIcon = ''; const _micIcon = ''; diff --git a/static/index.html b/static/index.html index 8257660fe..fea4e20ac 100644 --- a/static/index.html +++ b/static/index.html @@ -250,9 +250,9 @@ - + - + @@ -365,6 +365,7 @@ Add a memory — e.g. 'I prefer concise replies' +
@@ -1005,7 +1006,7 @@ var tips = mobile ? phone : desktop; var el = document.getElementById('welcome-tip'); if (el) { - el.textContent = 'Pick a model if you want, or just type.'; + el.textContent = tips[Math.floor(Math.random() * tips.length)]; } fetch('/api/version').then(function(r){return r.json()}).then(function(d){ if (d.version) window._appVersion = d.version; @@ -2504,7 +2505,7 @@ - + @@ -2522,7 +2523,7 @@ - + diff --git a/static/js/chat.js b/static/js/chat.js index ea2d8c1bb..3c8bbe850 100644 --- a/static/js/chat.js +++ b/static/js/chat.js @@ -349,6 +349,9 @@ import { wireArrowUpRecall, getUserMessagesFromChatHistory } from './composerArr async function _adoptOpenedSessionBeforeAutoCreate() { if (!sessionModule || !sessionModule.getCurrentSessionId || sessionModule.getCurrentSessionId()) return true; + // Don't adopt a stale session when the user explicitly started a New Chat + // (pending state set) — the send path must materialize the pending session. + if (sessionModule.hasPendingChat && sessionModule.hasPendingChat()) return false; const activeRowId = document.querySelector('.list-item.active-session[data-session-id], .session-item.active[data-session-id]')?.dataset?.sessionId || ''; const hashId = _hashSessionCandidate(); const lastSelectedId = String(window.__odysseusLastSelectedSessionId || '').trim(); @@ -1403,6 +1406,8 @@ import { wireArrowUpRecall, getUserMessagesFromChatHistory } from './composerArr currentAccumulated = ''; currentHolder = null; + let abortCtrl = null; + let streamingTTS = false; try { // Re-enable auto-scroll when user sends a message uiModule.setAutoScroll(true); @@ -1716,7 +1721,7 @@ import { wireArrowUpRecall, getUserMessagesFromChatHistory } from './composerArr } - const abortCtrl = new AbortController(); + abortCtrl = new AbortController(); abortCtrl._reason = ''; currentAbort = abortCtrl; @@ -1897,7 +1902,7 @@ import { wireArrowUpRecall, getUserMessagesFromChatHistory } from './composerArr let isThinking = false; let thinkingStartTime = null; // Streaming TTS: synthesize sentence-by-sentence during streaming - const streamingTTS = !!(window.aiTTSManager && window.aiTTSManager.autoPlay && window.aiTTSManager.available); + streamingTTS = !!(window.aiTTSManager && window.aiTTSManager.autoPlay && window.aiTTSManager.available); if (streamingTTS) window.aiTTSManager.streamingStart(); // Multi-bubble agent tracking let roundHolder = holder; // Current AI text bubble (changes per round) @@ -4787,7 +4792,8 @@ import { wireArrowUpRecall, getUserMessagesFromChatHistory } from './composerArr if (msgIndex < 0) return; const bodyEl = userMsgElement.querySelector('.body'); - const currentText = bodyEl ? bodyEl.textContent.trim().replace(/\s*\[\d+ attachment\(s\)\]$/, '') : ''; + let currentText = (userMsgElement.dataset.raw || (bodyEl ? bodyEl.textContent : '') || '').trim(); + currentText = currentText.replace(/\s*\[\d+ attachment\(s\)\]$/, ''); // Replace body with an editable textarea const editor = document.createElement('textarea'); diff --git a/static/js/chatRenderer.js b/static/js/chatRenderer.js index 10709679d..1d6e2e4a9 100644 --- a/static/js/chatRenderer.js +++ b/static/js/chatRenderer.js @@ -478,7 +478,10 @@ const DSML_STRAY_RE = /<\s*\/?\s*[｜|]+\s*DSML\s*[｜|]+[^>]*>/gi; const DSML_INVOKE_RE = /<\s*[｜|]+\s*DSML\s*[｜|]+\s*invoke\b[^>]*>[\s\S]*?(?:<\s*\/\s*[｜|]+\s*DSML\s*[｜|]+\s*invoke\s*>|$)/gi; const RAW_OPENAI_TOOL_JSON_RE = /(?:\[\s*)?\{\s*"function"\s*:\s*\{[\s\S]*?\}\s*,\s*"id"\s*:\s*"[^"]*"\s*,\s*"type"\s*:\s*"function"\s*\}\s*\]?/gi; const QWEN_ROLE_MARKER_RE = /<\/?\|(?:assistant|assistan|user|system|tool)\|>?|<\/\|end\|>?/gi; -const QWEN_BARE_MARKER_RE = /(?:^|[\t\r\n ])(?:\|?end\|?|\/?\|end\|)(?=[\t\r\n ]|$)|(?:^|[\t\r\n ])assistan(?:t)?(?=[\t\r\n ]|$)/gi; +// Keep in sync with _QWEN_BARE_MARKER_RE in src/tool_parsing.py. At least one +// pipe is required around `end`: with both optional (`\|?end\|?`) this also ate +// a bare `end` on its own line, breaking Ruby/Lua/shell snippets (#5547). +const QWEN_BARE_MARKER_RE = /(?:^|[\t\r\n ])(?:\/?\|end\||\|end|end\|)(?=[\t\r\n ]|$)|(?:^|[\t\r\n ])assistan(?:t)?(?=[\t\r\n ]|$)/gi; // Self-narration about tool results (model echoing stdout/exit_code) const TOOL_NARRATION_RE = /(?:The (?:result|output) shows?:?\s*)?-?\s*(?:stdout|stderr|exit_code):\s*.+/gi; diff --git a/static/js/composerArrowUpRecall.js b/static/js/composerArrowUpRecall.js index e0b20d6b4..83141bfe9 100644 --- a/static/js/composerArrowUpRecall.js +++ b/static/js/composerArrowUpRecall.js @@ -143,9 +143,9 @@ export function wireArrowUpRecall(composer, getUserMessages, options = {}) { return; } - // ArrowUp owns prompt history in the chat composer. If the current text - // is not already a recalled prompt, start from newest instead of letting - // the browser move the caret inside the textarea. + // ArrowUp walks older prompts. An unmatched draft already returned above, + // so reaching here means the composer is empty or holds a recalled prompt + // — the caret-navigation case is never hijacked. const nextIndex = currentIndex >= 0 ? Math.min(currentIndex + 1, history.length - 1) : 0; const recalled = history[nextIndex]; if (!recalled) { diff --git a/static/js/emailLibrary.js b/static/js/emailLibrary.js index 6a0d3e294..32b906ddc 100644 --- a/static/js/emailLibrary.js +++ b/static/js/emailLibrary.js @@ -13,7 +13,7 @@ import { makeWindowDraggable } from './windowDrag.js'; import { _esc, _escLinkify, _extractName, _parseTurnMeta, _formatBubbleDate, _formatRecipients, _senderColor, _initials, - _sanitizeHtml, + _sanitizeHtml, _renderEmailSummaryError, _TALON_WROTE, _TALON_FROM, _TALON_SENT, _TALON_SUBJ, _TALON_TO, _TALON_ORIG_RE, _SIG_BLOAT_MIN_CHARS, } from './emailLibrary/utils.js'; @@ -7259,12 +7259,11 @@ async function _generateSummary(reader, data, btn) { if (label) label.textContent = 'Summary'; } } else { - content.innerHTML = `${_esc(result.error || 'Failed to summarize')}`; - panel.remove(); + _renderEmailSummaryError(content, result); } } catch (e) { sp.destroy(); - panel.remove(); + _renderEmailSummaryError(content, null); if (uiModule) uiModule.showError?.('Failed to summarize'); } finally { if (btn) btn.disabled = false; diff --git a/static/js/emailLibrary/utils.js b/static/js/emailLibrary/utils.js index 82a5c86ec..f634c9949 100644 --- a/static/js/emailLibrary/utils.js +++ b/static/js/emailLibrary/utils.js @@ -30,6 +30,25 @@ export function _esc(text) { return div.innerHTML; } +const _EMAIL_SUMMARY_ERROR_MESSAGES = Object.freeze({ + email_summary_missing_body: 'No email body to summarize', + email_summary_not_configured: 'No model configured for email summaries', + email_summary_empty: 'The model returned an empty summary', + email_summary_unavailable: 'Failed to summarize', +}); + +export function _emailSummaryErrorMessage(result) { + const code = String(result?.error_code || ''); + return _EMAIL_SUMMARY_ERROR_MESSAGES[code] || 'Failed to summarize'; +} + +export function _renderEmailSummaryError(container, result) { + const message = container.ownerDocument.createElement('span'); + message.style.color = 'var(--red)'; + message.textContent = _emailSummaryErrorMessage(result); + container.replaceChildren(message); +} + function _attrEsc(text) { return String(text ?? '') .replace(/"/g, '"') diff --git a/static/js/sessions.js b/static/js/sessions.js index cf59d478c..edf83c8a4 100644 --- a/static/js/sessions.js +++ b/static/js/sessions.js @@ -1847,6 +1847,10 @@ export async function selectSession(id, { keepSidebar = false, showLoading = tru const _isTransientChat = !!_meta && (_meta.folder === 'Assistant' || _meta.folder === 'Tasks'); if (!_isTransientChat) { Storage.set('lastSessionId', id); + // Update URL hash without triggering hashchange handler + if (window.location.hash !== '#' + id) { + history.replaceState(null, '', '#' + id); + } } // Restore character preset for persistent chats try { @@ -2313,6 +2317,7 @@ export async function materializePendingSession() { currentSessionId = payload.id; if (!isIncognito) { Storage.set('lastSessionId', payload.id); + history.replaceState(null, '', '#' + payload.id); } // Reload the sidebar in the background. Awaiting this used to block the first diff --git a/static/js/skills.js b/static/js/skills.js index 84974d446..b45403570 100644 --- a/static/js/skills.js +++ b/static/js/skills.js @@ -83,11 +83,9 @@ export async function loadSkills(cascade = false) { // Play the domino-in entrance on this load (set when the tab is opened, // not for the silent re-loads after an edit/delete). if (cascade) _cascadeNext = true; - if (cascade && loaded && !_loadPromise && _playSkillsCascade()) { - _cascadeNext = false; - updateCount(); - return; - } + // Always re-fetch when the tab is explicitly opened — the cascade + // animation is handled inside renderSkillsList() via _cascadeNext. + // Skipping the fetch here caused stale data on panel close/reopen (#5870). if (_loadPromise) return _loadPromise; _loadPromise = (async () => { try { diff --git a/tests/test_composer_arrow_up_recall_js.py b/tests/test_composer_arrow_up_recall_js.py index eadc3bc94..022fcbc02 100644 --- a/tests/test_composer_arrow_up_recall_js.py +++ b/tests/test_composer_arrow_up_recall_js.py @@ -306,3 +306,24 @@ def test_integration_recalls_from_chat_history_dom(): ) assert proc.returncode == 0, proc.stderr assert json.loads(proc.stdout.strip()) == {"value": "stored prompt", "prevented": True} + + +def test_prompt_recall_is_not_duplicated_in_app_js(): + """Only composerArrowUpRecall.js may own ArrowUp on #message (issue #5862). + + static/app.js once carried a near-verbatim copy of this recall logic, wired + as a second capture-phase listener on the same textarea. That copy lacked + the draft guard here, and because it called stopImmediatePropagation it won + regardless of registration order — so a typed multi-line prompt was replaced + by the last sent one instead of the caret moving up a line. + """ + app_js = (_REPO / "static" / "app.js").read_text(encoding="utf-8") + for marker in ( + "_odysseusPromptRecallCapture", + "_readComposerPromptHistory", + "odysseusRecallIndex", + ): + assert marker not in app_js, ( + f"static/app.js reintroduces prompt recall ({marker!r}); " + "it belongs to static/js/composerArrowUpRecall.js alone" + ) diff --git a/tests/test_email_summary_error_ui_js.py b/tests/test_email_summary_error_ui_js.py new file mode 100644 index 000000000..1afc3bec9 --- /dev/null +++ b/tests/test_email_summary_error_ui_js.py @@ -0,0 +1,52 @@ +import json +import shutil +import subprocess +from pathlib import Path + +import pytest + + +_REPO = Path(__file__).resolve().parent.parent +_UTILS = (_REPO / "static" / "js" / "emailLibrary" / "utils.js").as_posix() +_HAS_NODE = shutil.which("node") is not None + +pytestmark = pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH") + + +def test_email_summary_renderer_ignores_untrusted_provider_error_text(): + secret = ( + "endpoint=https://private.example.internal/v1 provider=ollama " + "model=private-model response_body=private-response " + "Authorization: Bearer token-secret-value" + ) + script = f""" + import {{ _renderEmailSummaryError }} from '{_UTILS}'; + const host = {{ + ownerDocument: {{ + createElement() {{ return {{ style: {{}}, textContent: '' }}; }}, + }}, + replaceChildren(node) {{ this.child = node; }}, + }}; + _renderEmailSummaryError(host, {{ + error_code: 'email_summary_unavailable', + error: {json.dumps(secret)}, + }}); + console.log(JSON.stringify({{ + text: host.child.textContent, + color: host.child.style.color, + }})); + """ + + proc = subprocess.run( + ["node", "--input-type=module"], + input=script, + capture_output=True, + text=True, + cwd=str(_REPO), + timeout=30, + ) + + assert proc.returncode == 0, proc.stderr + rendered = json.loads(proc.stdout) + assert rendered == {"text": "Failed to summarize", "color": "var(--red)"} + assert secret not in proc.stdout diff --git a/tests/test_email_summary_llm.py b/tests/test_email_summary_llm.py new file mode 100644 index 000000000..b0ab7b3be --- /dev/null +++ b/tests/test_email_summary_llm.py @@ -0,0 +1,406 @@ +import asyncio +import json +import logging +import os +import sqlite3 +import sys +import tempfile +from pathlib import Path + +import pytest + + +_TMP_DATA = Path(tempfile.mkdtemp(prefix="odysseus-email-summary-")) +os.environ.setdefault("DATA_DIR", str(_TMP_DATA)) +os.environ.setdefault("DATABASE_URL", f"sqlite:///{_TMP_DATA / 'app.db'}") + +PROJECT_ROOT = Path(__file__).resolve().parent.parent +if str(PROJECT_ROOT) not in sys.path: + sys.path.insert(0, str(PROJECT_ROOT)) + + +def _route_endpoint(router, path: str, method: str): + method = method.upper() + for route in router.routes: + if route.path == path and method in getattr(route, "methods", set()): + return route.endpoint + raise AssertionError(f"route not found: {method} {path}") + + +@pytest.mark.asyncio +async def test_generate_email_summary_uses_shared_llm_adapter(monkeypatch): + import routes.email_helpers as email_helpers + import src.llm_core as llm_core + + calls = {} + + async def fake_llm_call_async(url, model, messages, **kwargs): + calls["url"] = url + calls["model"] = model + calls["messages"] = messages + calls["kwargs"] = kwargs + return "thinking before marker\n<<>>\n- Pay the invoice by Friday.\n<<>>" + + monkeypatch.setattr(llm_core, "llm_call_async", fake_llm_call_async) + + summary = await email_helpers._generate_email_summary( + url="https://chatgpt.com/backend-api/codex/responses", + model="gpt-5.5", + sender="Billing ", + subject="Invoice due", + body_for_llm="Please pay invoice 123 by Friday.", + headers={"Authorization": "Bearer test"}, + max_tokens=1234, + timeout=45, + ) + + assert summary == "- Pay the invoice by Friday." + assert calls["url"] == "https://chatgpt.com/backend-api/codex/responses" + assert calls["model"] == "gpt-5.5" + assert calls["kwargs"]["headers"] == {"Authorization": "Bearer test"} + assert calls["kwargs"]["temperature"] == 0.3 + assert calls["kwargs"]["max_tokens"] == 1234 + assert calls["kwargs"]["timeout"] == 45 + assert calls["kwargs"]["workload"] == "foreground" + assert calls["messages"][0]["role"] == "system" + assert calls["messages"][1]["role"] == "user" + + +@pytest.mark.asyncio +async def test_scheduled_email_summary_uses_background_fallback_chain(monkeypatch): + import routes.email_helpers as email_helpers + import src.llm_core as llm_core + import src.task_endpoint as task_endpoint + + candidates = [ + ("http://primary.invalid/v1", "primary-model", {"X-Candidate": "primary"}), + ("http://fallback.invalid/v1", "fallback-model", {"X-Candidate": "fallback"}), + ] + resolve_calls = [] + wait_calls = [] + llm_calls = [] + + def fake_resolve_task_candidates(**kwargs): + resolve_calls.append(kwargs) + return candidates + + async def fake_wait_for_interactive_quiet(label): + wait_calls.append(label) + return False + + async def fake_llm_call_async(url, model, messages, **kwargs): + llm_calls.append((url, model, messages, kwargs)) + if model == "primary-model": + raise RuntimeError("primary unavailable") + return "<<>>\n- Used the fallback model.\n<<>>" + + monkeypatch.setattr(task_endpoint, "resolve_task_candidates", fake_resolve_task_candidates) + monkeypatch.setattr(task_endpoint, "wait_for_interactive_quiet", fake_wait_for_interactive_quiet) + monkeypatch.setattr(llm_core, "llm_call_async", fake_llm_call_async) + + summary = await email_helpers._generate_scheduled_email_summary( + url="http://caller-fallback.invalid/v1", + model="caller-fallback-model", + sender="Sender ", + subject="Scheduled subject", + body_for_llm="Please summarize this scheduled email.", + headers={"Authorization": "Bearer test"}, + owner="alice", + max_tokens=321, + timeout=54, + ) + + assert summary == "- Used the fallback model." + assert resolve_calls == [{ + "fallback_url": "http://caller-fallback.invalid/v1", + "fallback_model": "caller-fallback-model", + "fallback_headers": {"Authorization": "Bearer test"}, + "owner": "alice", + }] + assert wait_calls == ["background task LLM"] + assert [call[1] for call in llm_calls] == ["primary-model", "fallback-model"] + assert all(call[3]["workload"] == "background" for call in llm_calls) + assert all(call[3]["max_tokens"] == 321 for call in llm_calls) + assert all(call[3]["timeout"] == 54 for call in llm_calls) + + +@pytest.mark.asyncio +async def test_scheduled_local_summary_is_preempted_by_foreground_call(monkeypatch): + import routes.email_helpers as email_helpers + import src.llm_core as llm_core + import src.task_endpoint as task_endpoint + + local_url = "http://127.0.0.1:11434/v1/chat/completions" + background_started = asyncio.Event() + never_release = asyncio.Event() + observed_workloads = [] + + monkeypatch.setenv("ODYSSEUS_LOCAL_MODEL_GATE", "true") + monkeypatch.setenv("BACKGROUND_TASK_FOREGROUND_GATE", "false") + monkeypatch.setattr(llm_core, "_LOCAL_MODEL_LOCK", asyncio.Lock()) + monkeypatch.setattr(llm_core, "_LOCAL_MODEL_CURRENT", {}) + monkeypatch.setattr(llm_core, "_LOCAL_MODEL_WAITING_FOREGROUND", 0) + monkeypatch.setattr( + task_endpoint, + "resolve_task_candidates", + lambda **_kwargs: [(local_url, "scheduled-model", {})], + ) + + async def fake_wait_for_interactive_quiet(_label): + return False + + async def gated_llm_call(url, model, messages, **kwargs): + assert messages + workload = kwargs.get("workload") + observed_workloads.append(workload) + async with llm_core._local_model_slot(url, model, workload=workload): + background_started.set() + await never_release.wait() + return "unreachable" + + monkeypatch.setattr(task_endpoint, "wait_for_interactive_quiet", fake_wait_for_interactive_quiet) + monkeypatch.setattr(llm_core, "llm_call_async", gated_llm_call) + + background_task = asyncio.create_task(email_helpers._generate_scheduled_email_summary( + url=local_url, + model="scheduled-model", + sender="Sender", + subject="Scheduled", + body_for_llm="Scheduled body", + owner="alice", + )) + foreground_task = None + try: + await asyncio.wait_for(background_started.wait(), timeout=1) + + async def run_foreground(): + async with llm_core._local_model_slot( + local_url, + "interactive-model", + workload="foreground", + ): + return True + + foreground_task = asyncio.create_task(run_foreground()) + with pytest.raises(asyncio.CancelledError): + await asyncio.wait_for(background_task, timeout=1) + assert await asyncio.wait_for(foreground_task, timeout=1) is True + assert observed_workloads == ["background"] + finally: + for task in (background_task, foreground_task): + if task is not None and not task.done(): + task.cancel() + + +@pytest.mark.asyncio +async def test_manual_email_summary_uses_shared_helper_and_caches(tmp_path, monkeypatch): + import routes.email_helpers as email_helpers + import routes.email_routes as email_routes + import src.endpoint_resolver as endpoint_resolver + + db_path = tmp_path / "scheduled_emails.db" + monkeypatch.setattr(email_helpers, "SCHEDULED_DB", db_path) + monkeypatch.setattr(email_routes, "SCHEDULED_DB", db_path) + email_helpers._init_scheduled_db() + + resolve_calls = [] + + def fake_resolve_endpoint(kind, owner=None): + resolve_calls.append((kind, owner)) + assert kind == "utility" + assert owner == "alice" + return ( + "https://chatgpt.com/backend-api/codex/responses", + "gpt-5.5", + {"Authorization": "Bearer test"}, + ) + + helper_calls = {} + + async def fake_generate_email_summary(**kwargs): + helper_calls.update(kwargs) + return "- Manual summary" + + monkeypatch.setattr(endpoint_resolver, "resolve_endpoint", fake_resolve_endpoint) + monkeypatch.setattr(email_routes, "_generate_email_summary", fake_generate_email_summary) + + router = email_routes.setup_email_routes() + summarize = _route_endpoint(router, "/api/email/summarize", "POST") + + result = await summarize( + { + "body": "This is a long enough email body for manual summary.", + "subject": "Manual subject", + "from": "Sender ", + "message_id": "", + "folder": "INBOX", + }, + owner="alice", + ) + + assert result == { + "success": True, + "summary": "- Manual summary", + "model_used": "gpt-5.5", + } + assert resolve_calls == [("utility", "alice")] + assert helper_calls["url"] == "https://chatgpt.com/backend-api/codex/responses" + assert helper_calls["model"] == "gpt-5.5" + assert helper_calls["headers"]["Authorization"] == "Bearer test" + assert helper_calls["headers"]["Content-Type"] == "application/json" + + conn = sqlite3.connect(db_path) + try: + row = conn.execute( + "SELECT owner, summary, model_used FROM email_summaries WHERE message_id=?", + ("",), + ).fetchone() + finally: + conn.close() + assert row == ("alice", "- Manual summary", "gpt-5.5") + + +@pytest.mark.asyncio +@pytest.mark.parametrize("exception_kind", ["http", "runtime"]) +async def test_manual_email_summary_never_exposes_provider_exception( + monkeypatch, + caplog, + exception_kind, +): + from fastapi import HTTPException + import routes.email_routes as email_routes + import src.endpoint_resolver as endpoint_resolver + + secret_detail = ( + "endpoint=https://private.example.internal/v1 provider=ollama " + "model=private-model response_body=private-response " + "Authorization: Bearer token-secret-value" + ) + + def fake_resolve_endpoint(kind, owner=None): + assert kind == "utility" + assert owner == "alice" + return ( + "https://private.example.internal/v1", + "private-model", + {"Authorization": "Bearer token-secret-value"}, + ) + + async def fail_summary(**_kwargs): + if exception_kind == "http": + raise HTTPException(status_code=502, detail=secret_detail) + raise RuntimeError(secret_detail) + + monkeypatch.setattr(endpoint_resolver, "resolve_endpoint", fake_resolve_endpoint) + monkeypatch.setattr(email_routes, "_generate_email_summary", fail_summary) + caplog.set_level(logging.WARNING, logger=email_routes.__name__) + + router = email_routes.setup_email_routes() + summarize = _route_endpoint(router, "/api/email/summarize", "POST") + result = await summarize( + { + "body": "This email body is long enough to summarize.", + "subject": "Sensitive provider failure", + "from": "Sender ", + }, + owner="alice", + ) + + assert result == { + "success": False, + "error": "Failed to summarize", + "error_code": "email_summary_unavailable", + } + exposed = json.dumps(result) + caplog.text + for marker in ( + "private.example.internal", + "ollama", + "private-model", + "private-response", + "token-secret-value", + ): + assert marker not in exposed + assert f"type={'HTTPException' if exception_kind == 'http' else 'RuntimeError'}" in caplog.text + + +@pytest.mark.asyncio +async def test_scheduled_email_summary_uses_shared_helper_and_caches(tmp_path, monkeypatch): + import routes.email_helpers as email_helpers + import routes.email_pollers as email_pollers + + db_path = tmp_path / "scheduled_emails.db" + monkeypatch.setattr(email_helpers, "SCHEDULED_DB", db_path) + monkeypatch.setattr(email_pollers, "SCHEDULED_DB", db_path) + email_helpers._init_scheduled_db() + + raw_email = ( + b"From: Sender \r\n" + b"To: Alice \r\n" + b"Subject: Scheduled subject\r\n" + b"Message-ID: \r\n" + b"Date: Tue, 01 Jan 2026 12:00:00 +0000\r\n" + b"Content-Type: text/plain; charset=utf-8\r\n" + b"\r\n" + + (b"Please review this scheduled summary email. " * 8) + ) + + class FakeImap: + def __init__(self): + self.logout_calls = 0 + + def select(self, _folder, readonly=True): + return "OK", [] + + def uid(self, command, *args): + if command == "SEARCH": + return "OK", [b"1"] + if command == "FETCH": + return "OK", [(b"1 (RFC822)", raw_email)] + raise AssertionError(f"unexpected uid command: {command!r} {args!r}") + + def logout(self): + self.logout_calls += 1 + + fake_conn = FakeImap() + + def fake_resolve_task_candidates(owner=None): + assert owner == "alice" + return [( + "https://chatgpt.com/backend-api/codex/responses", + "gpt-5.5", + {"Authorization": "Bearer test"}, + )] + + helper_calls = {} + + async def fake_generate_email_summary(**kwargs): + helper_calls.update(kwargs) + return "- Scheduled summary" + + monkeypatch.setattr(email_pollers, "_load_settings", lambda: {"email_auto_summarize": True}) + monkeypatch.setattr(email_pollers, "_owner_for_email_account", lambda _account_id: "alice") + monkeypatch.setattr(email_pollers, "_imap_connect", lambda account_id=None, owner="": fake_conn) + monkeypatch.setattr(email_pollers, "_get_email_config", lambda account_id=None, owner="": {"from_address": "alice@example.com"}) + monkeypatch.setattr(email_pollers, "resolve_task_candidates", fake_resolve_task_candidates) + monkeypatch.setattr(email_pollers, "_generate_scheduled_email_summary", fake_generate_email_summary) + + result = await email_pollers._auto_summarize_pass_single(account_id="acct-alice") + + assert "summarized 1" in result + assert "summary failed" not in result + assert helper_calls["url"] == "https://chatgpt.com/backend-api/codex/responses" + assert helper_calls["model"] == "gpt-5.5" + assert helper_calls["headers"]["Authorization"] == "Bearer test" + assert helper_calls["headers"]["Content-Type"] == "application/json" + assert helper_calls["owner"] == "alice" + assert fake_conn.logout_calls == 1 + + conn = sqlite3.connect(db_path) + try: + row = conn.execute( + "SELECT owner, summary, model_used FROM email_summaries WHERE message_id=?", + ("",), + ).fetchone() + finally: + conn.close() + assert row == ("alice", "- Scheduled summary", "gpt-5.5") diff --git a/tests/test_memory_add_submit_regression.py b/tests/test_memory_add_submit_regression.py new file mode 100644 index 000000000..450d63003 --- /dev/null +++ b/tests/test_memory_add_submit_regression.py @@ -0,0 +1,54 @@ +"""The Brain > Add Memory form must be submittable (#5828). + +The form previously had no submit button and relied on a deprecated +``keypress`` listener for Enter, which is not guaranteed to fire on all +platforms — leaving the form with no working submit path. Pins: + +- a visible, keyboard-accessible submit button next to the category select; +- the button wired to ``memoryModule.addNewMemory()``; +- Enter handled via ``keydown`` with ``preventDefault()`` (and no lingering + ``keypress`` handler on the input). +""" +from pathlib import Path + +APP_JS = Path("static/app.js") +INDEX_HTML = Path("static/index.html") + + +def _add_memory_row(html): + start = html.index('id="new-memory-input"') + end = html.index("
", html.index('id="new-memory-add-btn"', start)) + return html[start:end] + + +def test_add_memory_form_renders_a_submit_button(): + html = INDEX_HTML.read_text() + row = _add_memory_row(html) + + assert 'id="new-memory-category"' in row, "button must sit in the same row as the form fields" + btn_start = row.index('id="new-memory-add-btn"') + btn_tag = row[row.rindex("", btn_start)] + assert 'type="button"' in btn_tag, "must not rely on implicit submit semantics" + + +def _new_memory_wiring_block(source): + start = source.index("const newMemoryInput = el('new-memory-input');") + end = source.index("// Voice recording", start) + return source[start:end] + + +def test_submit_button_is_wired_to_add_new_memory(): + block = _new_memory_wiring_block(APP_JS.read_text()) + + assert "el('new-memory-add-btn')" in block + assert "addEventListener('click', () => memoryModule.addNewMemory())" in block + + +def test_enter_uses_keydown_with_prevent_default(): + block = _new_memory_wiring_block(APP_JS.read_text()) + + assert "addEventListener('keydown'" in block + assert "addEventListener('keypress'" not in block, "keypress is deprecated and unreliable for Enter" + assert "e.preventDefault();" in block + assert "!e.isComposing" in block, "IME composition must not submit the form" + assert "memoryModule.addNewMemory();" in block diff --git a/tests/test_tool_parsing_bare_end_marker.py b/tests/test_tool_parsing_bare_end_marker.py new file mode 100644 index 000000000..6167c8dde --- /dev/null +++ b/tests/test_tool_parsing_bare_end_marker.py @@ -0,0 +1,96 @@ +"""Regression: the Qwen bare-marker scrub must not eat a lone `end` (#5547). + +`_QWEN_BARE_MARKER_RE` cleans Qwen turn markers that leak into content. Its +`end` branch was `\\|?end\\|?` — both pipes optional — so it also matched a bare +`end` surrounded by whitespace and replaced it with a space. Any message +containing Ruby, Lua or shell code that closes a block with a lone `end` had +those lines silently deleted, in the stored text and in the rendered message. + +Requiring at least one pipe keeps every real marker (`|end`, `end|`, `|end|`, +`/|end|`) stripping as before. The same pattern is duplicated in +static/js/chatRenderer.js, so the JS copy is checked here too — the two must +not drift. +""" +import json +import re +import shutil +import subprocess +from pathlib import Path + +import pytest + +import src.agent_tools # noqa: F401 (break agent_tools<->tool_parsing import cycle) +from src.tool_parsing import strip_tool_blocks + +_REPO = Path(__file__).resolve().parent.parent +_CHAT_RENDERER = _REPO / "static" / "js" / "chatRenderer.js" + +# Inputs that must survive untouched, and the substring that proves they did. +KEPT = [ + ("loop do\n puts \"yo\"\nend\n", "\nend"), # the reported Ruby case + ("if x then\nend", "\nend"), + ("function f()\nend\n", "\nend"), + ("a end b", "a end b"), + ("append end", "append end"), + ("END", "END"), + ("\nEnd\n", "End"), +] + +# Real markers — at least one pipe, plus the role word — with the exact output +# they must still produce. Asserted as equality rather than "marker not in out" +# so narrowing the pattern can't pass by deleting more than it should. +STRIPPED = [ + ("a |end| b", "a b"), + ("a /|end| b", "a b"), + ("a |end b", "a b"), + ("a end| b", "a b"), + ("x assistant y", "x y"), +] + + +@pytest.mark.parametrize("text,kept", KEPT) +def test_bare_end_survives_stripping(text, kept): + assert kept in strip_tool_blocks(text) + + +@pytest.mark.parametrize("text,expected", STRIPPED) +def test_piped_end_markers_are_still_stripped(text, expected): + assert strip_tool_blocks(text) == expected + + +def test_bare_end_inside_a_fenced_block_survives(): + """The scrub runs over the whole message, fenced regions included.""" + out = strip_tool_blocks("Here:\n```ruby\nloop do\n puts 1\nend\n```\nDone.") + assert "\nend\n" in out + + +def _js_bare_marker_regex_source(): + src = _CHAT_RENDERER.read_text(encoding="utf-8") + m = re.search(r"^const QWEN_BARE_MARKER_RE = (/.*/[gimsuy]*);$", src, re.MULTILINE) + assert m, "QWEN_BARE_MARKER_RE literal not found in chatRenderer.js" + return m.group(1) + + +def test_js_copy_of_the_pattern_matches_the_python_one(): + """Guard the duplication: the JS branch must require a pipe too.""" + if shutil.which("node") is None: + pytest.skip("node binary not on PATH") + + cases = [text for text, _ in KEPT] + [text for text, _ in STRIPPED] + script = ( + "const RE = %s;\n" + "const cases = JSON.parse(process.argv[1]);\n" + "console.log(JSON.stringify(cases.map(c => c.replace(RE, ' '))));" + % _js_bare_marker_regex_source() + ) + result = subprocess.run( + ["node", "--input-type=module", "-e", script, json.dumps(cases)], + cwd=_REPO, capture_output=True, timeout=15, text=True, + ) + assert result.returncode == 0, f"node failed:\n{result.stderr}" + got = json.loads(result.stdout.splitlines()[-1]) + + for (text, kept), out in zip(KEPT, got): + assert kept in out, f"JS regex dropped {kept!r} from {text!r}" + for (text, expected), out in zip(STRIPPED, got[len(KEPT):]): + assert out == expected, f"JS regex: {text!r} -> {out!r}, expected {expected!r}"