panda
bd5bfbac2d
Root cause: LLM receiving full 34k-char JRXML would regenerate from scratch
instead of modifying coordinates in-place, shrinking output to ~3k chars.
Solution (programmatic node control, not prompt engineering):
- New agent/jrxml_windower.py: decompose JRXML into header (never sent to
LLM) + individual bands. Split bands >4000 chars at element boundaries.
Reassemble with element count validation (>10% change = rollback).
- Rewrite refine_layout: per-band windowed LLM processing (~2-4k chars
each). LLM cannot "reimagine" the entire report.
- Rewrite map_fields: 100% programmatic regex $F{field_N} -> real name
replacement. Zero LLM calls, zero content loss.
- _sanitize_field_name: non-ASCII chars escaped to _uXXXX_ format for
valid JRXML identifiers.
- Tests: 48 new unit tests (windower 28 + map_fields 20). All passing.
Full suite 385 tests, zero regressions.
18 lines
652 B
Markdown
18 lines
652 B
Markdown
你是一位资深 JasperReports 工程师。根据以下参考模板和用户需求，生成一个完整、可编译的 JRXML 文件。
|
|
JRXML 必须兼容 JasperReports 7.0.6 schema。
|
|
|
|
关键规则：
|
|
- 只输出 JRXML 代码，不要解释，不要 markdown 标记。
|
|
- 报表正文中使用的每个字段必须在 <field name="..."> 部分中声明。
|
|
- 根元素为 <jasperReport>，包含正确的 xmlns 属性。
|
|
- 包含 <queryString>，在 <![CDATA[...]]> 中包含 SQL 查询。
|
|
- 确保所有交叉引用（字段名称、band 元素）保持一致。
|
|
|
|
参考模板和组件：
|
|
{context}
|
|
|
|
{template_context}
|
|
|
|
用户需求：
|
|
{user_request}
|