Add context-only mode: Claude Code writes blocks, no API needed

New architecture: MCP provides context, Claude Code writes.

New functions:
- get_block_context(case_id, block_id) → returns full context package
  (prompt, source docs, claims, direction, precedents, style guide)
  WITHOUT calling Anthropic API
- save_block_content(case_id, block_id, content) → saves block to DB

New MCP tools: get_block_context, save_block_content

The old write_block (API-based) still works as fallback.
The new flow uses Claude Code's own model (Opus 4.6, 1M context)
which has no separate API billing.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-04-03 16:18:25 +00:00
parent 7033d2d3ee
commit 9d0a73a1dc
3 changed files with 160 additions and 0 deletions

View File

@@ -223,6 +223,26 @@ async def get_decision_template(case_number: str) -> str:
return await drafting.get_decision_template(case_number)
@mcp.tool()
async def get_block_context(
case_number: str,
block_id: str,
instructions: str = "",
) -> str:
"""קבלת הקשר מלא לכתיבת בלוק — ללא API. Claude Code כותב ושומר."""
return await drafting.get_block_context(case_number, block_id, instructions)
@mcp.tool()
async def save_block_content(
case_number: str,
block_id: str,
content: str,
) -> str:
"""שמירת בלוק שנכתב ע"י Claude Code ב-DB."""
return await drafting.save_block_content(case_number, block_id, content)
@mcp.tool()
async def validate_decision(case_number: str) -> str:
"""בדיקת QA — 6 בדיקות איכות על ההחלטה. אם בדיקה קריטית נכשלת — ייצוא חסום."""