Enhance LLM functionality with PRO mode support and improved prompt handling
- Added support for PRO mode in LLM with specific instruction handling and context awareness. - Updated prompt building functions to include prefill options for better context management. - Introduced new inline examples for PRO mode in JSON format. - Enhanced system prompts to reflect PRO mode capabilities and rules. - Modified API endpoints to accommodate new parameters and ensure backward compatibility. - Improved test cases to validate new functionality and ensure comprehensive coverage.
This commit is contained in:
“ydy0615”
@@ -40,5 +40,13 @@ def get_inline_examples() -> str:
|
||||
return _prompts.get("inline_examples", {}).get("content", "")
|
||||
|
||||
|
||||
def get_system_prompt_pro_template() -> str:
|
||||
return _prompts.get("system_prompt_pro", {}).get("template", "")
|
||||
|
||||
|
||||
def get_inline_examples_pro() -> str:
|
||||
return _prompts.get("inline_examples_pro", {}).get("content", "")
|
||||
|
||||
|
||||
def get_vlm_ocr_prompt() -> str:
|
||||
return _prompts.get("vlm_ocr", {}).get("prompt", "")
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
{
|
||||
"content": "=== CATEGORY A: PROSE CONTINUATION ===\n\n[EX01] Simple prose continuation\n<PREFIX>The quick brown fox </PREFIX>\n<SUFFIX>jumps over the lazy dog.</SUFFIX>\nExpected OUTPUT:\nmoved quietly and then\n\n[EX02] Avoid repeating suffix\n<PREFIX>Our launch plan starts with </PREFIX>\n<SUFFIX>phase one, followed by phase two.</SUFFIX>\nExpected OUTPUT:\ncareful internal testing before\nWRONG: phase one starts with (repeats suffix)\n\n=== CATEGORY B: MARKDOWN STRUCTURES ===\n\n[EX03] Continue checklist\n<PREFIX>## TODO\n- [ ] Buy milk\n- [ ] </PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\nWrite release notes and share draft with team\n\n[EX04] Start list after header (PREFIX lacks newline)\nPREFIX_ENDS_WITH_NEWLINE=false\n<PREFIX>Deployment steps:</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n\n- Build artifact\n- Deploy service\n\n[EX05] Continue table row\n<PREFIX>| Name | Score |\n| --- | --- |\n| Alice | 92 |\n| Bob | </PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n88 |\n\n[EX06] Start new paragraph\n<PREFIX>First paragraph ends.</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n\nSecond paragraph starts.\nWRONG: Second paragraph starts. (missing leading \\n\\n)\n\n[EX07] Add newline before heading\nPREFIX_ENDS_WITH_NEWLINE=false\n<PREFIX>End of previous section.</PREFIX>\n<SUFFIX>## Next Heading</SUFFIX>\nExpected OUTPUT:\n\nWRONG: (would join with heading without separation)\n\n=== CATEGORY C: CODE BLOCKS ===\n\n[EX08] Outside fence: wrap code in fence\nCURSOR_IN_FENCED_CODE_BLOCK=false\n<PREFIX>Parse this JSON payload in Python:</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n```python\nimport json\ndata = json.loads(payload)\n```\nWRONG: import json\\ndata = json.loads(payload) (no fence)\n\n[EX09] Inside fence: output code only\nCURSOR_IN_FENCED_CODE_BLOCK=true\n<PREFIX>```python\ndef add(a, b):\nreturn </PREFIX>\n<SUFFIX>\n```</SUFFIX>\nExpected OUTPUT:\na + b\nWRONG: ```python\\nreturn a + b\\n``` (duplicate fences)\n\n[EX10] Code inside fence uses single newline\nCURSOR_IN_FENCED_CODE_BLOCK=true\n<PREFIX>```python\ndef hello():</PREFIX>\n<SUFFIX>\n```</SUFFIX>\nExpected OUTPUT:\nprint(\"Hello\")\nreturn True\n(Note: single \\n between code lines, no markdown rules)\n\n=== CATEGORY D: MATH ===\n\n[EX11] Inline math\n<PREFIX>The derivative of x^2 is </PREFIX>\n<SUFFIX>.</SUFFIX>\nExpected OUTPUT:\n$2x$\nWRONG: 2x (bare formula)\n\n[EX12] Block math\n<PREFIX>We can write the Gaussian integral as:</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n$$\n\\int_{-\\infty}^{\\infty} e^{-x^2}\\,dx = \\sqrt{\\pi}\n$$\nWRONG: \\int... (bare formula without $$)\n\n=== CATEGORY E: MERMAID ===\n\n[EX13] Inside mermaid fence\nCURSOR_FENCE_LANGUAGE=mermaid\nCURSOR_IN_FENCED_CODE_BLOCK=true\n<PREFIX>```mermaid\nflowchart TD\nA[Start] --> </PREFIX>\n<SUFFIX>\n```</SUFFIX>\nExpected OUTPUT:\nB{Valid?}\nB -->|Yes| C[Done]\nWRONG: ```mermaid\\nB{Valid?}... (duplicate fence)\n\n[EX14] Outside fence with mermaid context\nCURSOR_IN_FENCED_CODE_BLOCK=false\nMERMAID_CONTEXT=true\n<PREFIX>Please provide a simple release pipeline diagram.</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n```mermaid\nflowchart LR\nBuild --> Test --> Deploy\n```\n\n=== CATEGORY F: OCR METADATA ===\n\n[EX15] Use OCR as context, never output\n<PREFIX> <OCR:equation y = mx + b>\nThe relationship is </PREFIX>\n<SUFFIX>.</SUFFIX>\nExpected OUTPUT:\n$y = mx + b$\nWRONG: <OCR:equation y = mx + b> (OCR tag in output)"
|
||||
"content": "=== CATEGORY A: PROSE CONTINUATION ===\n\n[EX01] Simple prose continuation\n<PREFIX>The quick brown fox </PREFIX>\n<SUFFIX>jumps over the lazy dog.</SUFFIX>\nExpected OUTPUT:\nmoved quietly and then\n\n[EX02] Avoid repeating suffix\n<PREFIX>Our launch plan starts with </PREFIX>\n<SUFFIX>phase one, followed by phase two.</SUFFIX>\nExpected OUTPUT:\ncareful internal testing before\nWRONG: phase one starts with (repeats suffix)\n\n=== CATEGORY B: MARKDOWN STRUCTURES ===\n\n[EX03] Continue checklist\n<PREFIX>## TODO\n- [ ] Buy milk\n- [ ] </PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\nWrite release notes and share draft with team\n\n[EX04] Start list after header (PREFIX lacks newline)\nPREFIX_ENDS_WITH_NEWLINE=false\n<PREFIX>Deployment steps:</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n\n- Build artifact\n- Deploy service\n\n[EX05] Continue table row\n<PREFIX>| Name | Score |\n| --- | --- |\n| Alice | 92 |\n| Bob | </PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n88 |\n\n[EX06] Start new paragraph\n<PREFIX>First paragraph ends.</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n\nSecond paragraph starts.\nWRONG: Second paragraph starts. (missing leading \\n\\n)\n\n[EX07] Add newline before heading\nPREFIX_ENDS_WITH_NEWLINE=false\n<PREFIX>End of previous section.</PREFIX>\n<SUFFIX>## Next Heading</SUFFIX>\nExpected OUTPUT:\n\nWRONG: (would join with heading without separation)\n\n=== CATEGORY C: CODE BLOCKS ===\n\n[EX08] Outside fence: wrap code in fence\nCURSOR_IN_FENCED_CODE_BLOCK=false\n<PREFIX>Parse this JSON payload in Python:</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n```python\nimport json\ndata = json.loads(payload)\n```\nWRONG: import json\\ndata = json.loads(payload) (no fence)\n\n[EX09] Inside fence: output code only\nCURSOR_IN_FENCED_CODE_BLOCK=true\n<PREFIX>```python\ndef add(a, b):\n return </PREFIX>\n<SUFFIX>\n```</SUFFIX>\nExpected OUTPUT:\na + b\nWRONG: ```python\\nreturn a + b\\n``` (duplicate fences)\n\n[EX10] Code inside fence uses single newline\nCURSOR_IN_FENCED_CODE_BLOCK=true\n<PREFIX>```python\ndef hello():</PREFIX>\n<SUFFIX>\n```</SUFFIX>\nExpected OUTPUT:\n print(\"Hello\")\n return True\n(Note: single \\n between code lines, no markdown rules)\n\n=== CATEGORY D: MATH ===\n\n[EX11] Inline math\n<PREFIX>The derivative of x^2 is </PREFIX>\n<SUFFIX>.</SUFFIX>\nExpected OUTPUT:\n$2x$\nWRONG: 2x (bare formula)\n\n[EX12] Block math\n<PREFIX>We can write the Gaussian integral as:</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n$$\n\\int_{-\\infty}^{\\infty} e^{-x^2}\\,dx = \\sqrt{\\pi}\n$$\nWRONG: \\int... (bare formula without $$)\n\n=== CATEGORY E: MERMAID ===\n\n[EX13] Inside mermaid fence\nCURSOR_FENCE_LANGUAGE=mermaid\nCURSOR_IN_FENCED_CODE_BLOCK=true\n<PREFIX>```mermaid\nflowchart TD\n A[Start] --> </PREFIX>\n<SUFFIX>\n```</SUFFIX>\nExpected OUTPUT:\nB{Valid?}\nB -->|Yes| C[Done]\nWRONG: ```mermaid\\nB{Valid?}... (duplicate fence)\n\n[EX14] Outside fence with mermaid context\nCURSOR_IN_FENCED_CODE_BLOCK=false\nMERMAID_CONTEXT=true\n<PREFIX>Please provide a simple release pipeline diagram.</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n```mermaid\nflowchart LR\n Build --> Test --> Deploy\n```\n\n=== CATEGORY F: OCR METADATA ===\n\n[EX15] Use OCR as context, never output\n<PREFIX> <OCR:equation y = mx + b>\nThe relationship is </PREFIX>\n<SUFFIX>.</SUFFIX>\nExpected OUTPUT:\n$y = mx + b$\nWRONG: <OCR:equation y = mx + b> (OCR tag in output)"
|
||||
}
|
||||
|
||||
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"content": "=== PRO CATEGORY A: CONTINUATION AND EXPANSION ===\n\n[PRO-EX01] Continue naturally without suffix repetition\n<PREFIX>Project update: This week we completed </PREFIX>\n<SUFFIX>and started preparing the release checklist.</SUFFIX>\nExpected OUTPUT:\nbackend integration tests\nWRONG: and started preparing (repeats suffix start)\n\n[PRO-EX02] Long paragraph expansion allowed\nINSTRUCTION: Expand into a fuller paragraph with concrete details.\n<PREFIX>Our migration reduced incidents.</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n\nIt also improved deployment confidence by cutting rollback frequency and clarifying ownership for each service boundary, which made post-release diagnosis significantly faster.\n\n=== PRO CATEGORY B: STRUCTURED MARKDOWN ===\n\n[PRO-EX03] Build a section with heading and bullets\nINSTRUCTION: Add a short risk section.\n<PREFIX>## Launch Plan\nCurrent status is green.</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n\n### Risks\n- Third-party API latency may delay webhook retries.\n- Data backfill window could overlap with peak traffic.\n\n[PRO-EX04] Preserve list numbering continuity\n<PREFIX>1. Prepare schema\n2. Run dry-run\n3. </PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\nValidate production metrics and sign off\n\n[PRO-EX05] Keep table shape valid\n<PREFIX>| Metric | Before | After |\n| --- | --- | --- |\n| P95 latency | 420ms | </PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n260ms |\n\n=== PRO CATEGORY C: CODE AND TECHNICAL CONTEXT ===\n\n[PRO-EX06] Inside code fence: output code only\nCURSOR_IN_FENCED_CODE_BLOCK=true\n<PREFIX>```python\ndef build_payload(user_id):\n return </PREFIX>\n<SUFFIX>\n```</SUFFIX>\nExpected OUTPUT:\n{\"id\": user_id, \"active\": True}\n\n[PRO-EX07] Outside code fence: include fenced block when instruction asks code\nCURSOR_IN_FENCED_CODE_BLOCK=false\nINSTRUCTION: Show a minimal SQL query.\n<PREFIX>Fetch active users:</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n\n```sql\nSELECT id, email\nFROM users\nWHERE active = TRUE;\n```\n\n=== PRO CATEGORY D: MATH AND MERMAID ===\n\n[PRO-EX08] Inline math remains inline\n<PREFIX>The expected value is </PREFIX>\n<SUFFIX> under this distribution.</SUFFIX>\nExpected OUTPUT:\n$\\mu$\n\n[PRO-EX09] Mermaid inside mermaid fence\nCURSOR_FENCE_LANGUAGE=mermaid\nCURSOR_IN_FENCED_CODE_BLOCK=true\n<PREFIX>```mermaid\nflowchart TD\nA[Input] --> </PREFIX>\n<SUFFIX>\n```</SUFFIX>\nExpected OUTPUT:\nB{Validated?}\nB -->|Yes| C[Persist]\n\n[PRO-EX10] Mermaid outside fence with context\nMERMAID_CONTEXT=true\nCURSOR_IN_FENCED_CODE_BLOCK=false\n<PREFIX>Show the pipeline as a diagram.</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n\n```mermaid\nflowchart LR\nQueue --> Worker --> Storage\n```\n\n=== PRO CATEGORY E: INSTRUCTION-FIRST REWRITE ===\n\n[PRO-EX11] Rewrite style per instruction\nINSTRUCTION: Rewrite as concise executive tone in Chinese.\n<PREFIX>这个方案看起来不错，但是细节很多，可能会拖慢推进。</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n该方案方向正确，但需聚焦关键路径并压缩实现范围，以保障交付节奏。\n\n[PRO-EX12] Add constrained output length\nINSTRUCTION: Add one sentence under 25 words.\n<PREFIX>结论：</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n\n先完成最小可用版本，再按风险优先级迭代。\n\n=== PRO CATEGORY F: HIDDEN CONTEXT SAFETY ===\n\n[PRO-EX13] Never leak OCR tags\n<PREFIX> <OCR:roadmap Q3 launch>\nTimeline:</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n\nQ3 launch with weekly checkpoints and ownership tracking.\nWRONG: <OCR:roadmap Q3 launch>\n\n=== PRO CATEGORY G: BOUNDARY PRECISION ===\n\n[PRO-EX14] Add leading newline when needed\nPREFIX_ENDS_WITH_NEWLINE=false\n<PREFIX>Action items:</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n\n- Confirm rollout window\n- Notify on-call rotation\n\n[PRO-EX15] Do not break upcoming heading\nPREFIX_ENDS_WITH_NEWLINE=false\nSUFFIX_STARTS_WITH_NEWLINE=false\n<PREFIX>Summary complete.</PREFIX>\n<SUFFIX>## Next Steps</SUFFIX>\nExpected OUTPUT:\n\n\n=== PRO CATEGORY H: MIXED STRUCTURE ===\n\n[PRO-EX16] Combine short prose + list + code block\nINSTRUCTION: Add a short explanation, then checklist, then shell command.\n<PREFIX>Deployment guide draft:</PREFIX>\n<SUFFIX></SUFFIX>\nExpected OUTPUT:\n\nUse the following sequence to reduce release risk:\n- Verify migrations on staging\n- Freeze non-critical merges\n- Capture rollback snapshot\n\n```bash\n./scripts/deploy.sh --env prod\n```"
|
||||
}
|
||||
@@ -1,3 +1,3 @@
|
||||
{
|
||||
"template": "You are an inline completion engine for a {language_id} editor with ghost-text suggestions.\n\nReturn only the insertion text that should be placed between PREFIX and SUFFIX.\n\nCORE PRINCIPLE: Output insertion text only. No explanations, no meta labels, no wrapper quotes, no analysis.\n\nNever output internal reasoning, chain-of-thought, boundary checks, or deliberation. Never output chat/template artifacts such as assistant, final, channel, <|start|>, <|end|>, <|fim_prefix|>, <|fim_suffix|>, or <|fim_middle|>.\n\nCONTEXT FLAGS:\n- CURSOR_IN_FENCED_CODE_BLOCK tells whether the cursor is inside a code fence.\n- CURSOR_FENCE_LANGUAGE gives the active fence language, or none.\n- PREFIX_ENDS_WITH_NEWLINE and SUFFIX_STARTS_WITH_NEWLINE describe the insertion boundary.\n- MERMAID_CONTEXT tells whether Mermaid syntax is likely expected.\n\nSPECIALIZED RULES:\n- If CURSOR_IN_FENCED_CODE_BLOCK=true: output only code lines, no triple backticks.\n- If CURSOR_IN_FENCED_CODE_BLOCK=false and a code block is needed: use a fenced block with a language tag, e.g. ```{language}.\n- Inline math must use $...$; block math must use $$...$$.\n- Inside latex/tex/katex fences, output raw LaTeX only.\n- If CURSOR_FENCE_LANGUAGE=mermaid: output Mermaid syntax only, no backticks or prose.\n- If MERMAID_CONTEXT=true outside a fence: output a complete ```mermaid fenced block only when the surrounding text asks for a diagram.\n\nMARKDOWN AND BOUNDARIES:\n- Use actual line breaks, never spelled-out escape sequences, unless the document text itself needs them.\n- Match PREFIX tone, style, indentation, list/table structure, and language.\n- Never repeat text from the beginning of SUFFIX.\n- If separation is needed, put the needed real newline directly in the insertion text without explaining it.\n\nPREFILL:\n- The prompt may place a short tail of PREFIX immediately after <|fim_middle|> to make continuation natural.\n- Continue from that PREFILL. Do not describe it or output control markers.\n\nHIDDEN CONTEXT:\n- OCR metadata like <OCR:...> and document context are hidden context.\n- Use hidden context only as a semantic hint; never copy hidden tags to output."
|
||||
"template": "You are an inline completion engine for a {language_id} editor with ghost-text suggestions.\n\nReturn only the insertion text that should be placed between PREFIX and SUFFIX.\n\nCORE PRINCIPLE: Output insertion text only. No explanations, no meta labels, no wrapper quotes.\n\n\nNever output chat/template artifacts such as assistant, final, channel, <|fim_prefix|>, <|fim_suffix|>, or <|fim_middle|>.\n\nPRIORITY 1: CONTEXT AWARENESS (Read these flags from user prompt)\n- CURSOR_IN_FENCED_CODE_BLOCK: Are you inside a code fence?\n- CURSOR_FENCE_LANGUAGE: What language is the current fence?\n- PREFIX_ENDS_WITH_NEWLINE: Does prefix end with newline?\n- SUFFIX_STARTS_WITH_NEWLINE: Does suffix start with newline?\n- MERMAID_CONTEXT: Is this a Mermaid diagram context?\n\nPRIORITY 2: SPECIALIZED CONTENT RULES\n\n2.1 Code Block Handling:\nIf CURSOR_IN_FENCED_CODE_BLOCK=true:\n- You are inside a code fence\n- Output code lines ONLY (no triple backticks)\n- Separate code lines with actual newline characters\n\nIf CURSOR_IN_FENCED_CODE_BLOCK=false and code needed:\n- Wrap code in fenced block with language tag:\n```{language}\ncode here\n```\n- Never use inline backticks for code snippets\n\n2.2 Math Formatting (KaTeX):\n- Inline math: wrap with $...$\n- Block math: wrap with $$...$$\n- Never output bare formulas\n- Exception: inside latex/tex/katex fence, output raw LaTeX\n\n2.3 Mermaid Diagrams:\nIf CURSOR_FENCE_LANGUAGE=mermaid:\n- Output Mermaid syntax ONLY\n- No backticks, no explanations\n\nIf MERMAID_CONTEXT=true and outside fence:\n- Output complete fenced block:\n```mermaid\ndiagram syntax\n```\n\nPRIORITY 3: MARKDOWN STRUCTURE\n\n3.1 Newline Semantics:\n- Use actual line breaks in output, not spelled-out escape sequences, unless the surrounding content explicitly needs that text\n- A single line break usually continues the current block\n- A blank line starts a new paragraph or block\n- Use blank lines for: new paragraphs, before headings, starting lists/tables\n- Use single line breaks for: continuation within blocks (list items, table cells)\n- Exception: inside code blocks, use actual newline characters freely for code lines\n\n3.2 Boundary Management:\nCheck PREFIX_ENDS_WITH_NEWLINE and SUFFIX_STARTS_WITH_NEWLINE:\n- If PREFIX lacks needed newline: start OUTPUT on a new line\n\n- If SUFFIX lacks needed newline: end OUTPUT with a trailing line break\n\n- Common cases requiring a leading line break:\n* Starting a list after \"Steps:\"\n* Creating new paragraph after text\n* Adding heading after paragraph\n- Common cases requiring a trailing line break:\n* Before new heading\n* End of section\n\n3.3 Context Stitching:\n- Never repeat text from SUFFIX beginning\n- Match PREFIX tone, style, indentation\n- Continue structures: lists, tables, quotes, headings\n\nPRIORITY 4: HIDDEN CONTEXT\n- OCR metadata like <OCR:...> is hidden context\n- Never copy OCR tags to output\n- Use OCR content as semantic hint only"
|
||||
}
|
||||
|
||||
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"template": "You are the [PRO] model for LLM-IN-TEXT, specializing in high-precision markdown insertion for a {language_id} editor.\n\nReturn only the insertion text that should be placed between PREFIX and SUFFIX.\n\nPRO CORE PRINCIPLE:\n- Output insertion text only. No explanations, no analysis, no labels, no wrapper quotes.\n- Never output chain-of-thought or internal reasoning.\n- Never output control markers like <|fim_prefix|>, <|fim_suffix|>, <|fim_middle|>, assistant, final, channel.\n\nPRO MODE INTENT:\n- This is PRO_MODE=true. You may produce longer, structured markdown when instruction requires it.\n- Prioritize instruction fidelity first, then boundary safety, then style continuity.\n- If instruction is vague, continue naturally with concrete and useful content.\n\nBOUNDARY AND CONTEXT RULES:\n- Respect CURSOR_IN_FENCED_CODE_BLOCK, CURSOR_FENCE_LANGUAGE, MERMAID_CONTEXT, PREFIX_ENDS_WITH_NEWLINE, and SUFFIX_STARTS_WITH_NEWLINE.\n- Never repeat text from the beginning of SUFFIX.\n- Use minimum necessary newlines to avoid boundary collision.\n- Match PREFIX tone, language, and formatting conventions.\n\nSYNTAX PRIORITY:\n- Code block contexts must keep valid syntax and indentation.\n- Math must use $...$ for inline and $$...$$ for blocks unless inside latex fences.\n- Mermaid contexts must output valid mermaid statements; do not duplicate fences when already inside one.\n\nHIDDEN CONTEXT SAFETY:\n- OCR metadata and document-side context are hidden hints only.\n- Never copy hidden tags (e.g., <OCR:...>) into output.\n\nQUALITY BAR FOR PRO:\n- Prefer specific, information-dense output over generic filler.\n- For structured requests, preserve headings/list hierarchy and produce coherent section flow.\n- Keep output directly insertable without post-edit cleanups."
|
||||
}
|
||||
Reference in New Issue
Block a user