fix: per-node max_tokens + validation 502 guard + correct_jrxml output validity

- backend/llm.py: per-node max_tokens via get_llm(max_tokens=N), LLM_MAX_TOKENS env var (default 8192)
- agent/nodes.py: 5 generation nodes use max_tokens=32768, generate_skeleton retries at 65536
- agent/nodes.py: fix ns:field regex (<field → <[\w:]*field) to handle namespace prefixes
- agent/nodes.py: fix correct_jrxml never writing back to state["current_jrxml"]
- agent/nodes.py: correct_jrxml rejects non-JRXML output (no <jasperReport tag)
- agent/nodes.py: _strip_continuation_wrapper strips markdown/prefixes from continuation rounds
- agent/nodes.py: _extract_jrxml iterates multiple markdown code blocks, skips fragments
- agent/graph.py: route_after_validate skips correction loop when service_unavailable
- agent/graph.py: route_after_save skips validation for empty JRXML
- backend/validation.py: returns service_unavailable: True for ConnectError and HTTP 5xx
- Docs: CLAUDE.md v14 changelog, README.md LLM_MAX_TOKENS, .env.example LLM_MAX_TOKENS

This commit is contained in:

panda

2026-05-24 15:20:25 +08:00

parent e362f530ea

commit 4e14334030

8 changed files with 388 additions and 32 deletions

									
										.env.example
									
		+3
		
												View File
												
				@@ -14,6 +14,9 @@ OPENAI_BASE_URL=https://api.openai.com/v1

				LLM_MODEL=MiniMax-M2.7

				# 默认 max_tokens（各生成节点可覆盖为更高值）

				LLM_MAX_TOKENS=8192

				# 本地大语言模型（Ollama）

				LOCAL_LLM_MODEL=qwen2.5-coder:7b