feat: make us-cpa questions retrieval-first
This commit is contained in:
@@ -177,19 +177,17 @@ Behavior:
|
||||
Current `question` implementation:
|
||||
|
||||
- loads the cached tax-year corpus
|
||||
- searches a small IRS-first topical rule set
|
||||
- returns one canonical analysis object
|
||||
- searches the downloaded IRS corpus for relevant authorities and excerpts
|
||||
- returns one canonical analysis object with:
|
||||
- authorities
|
||||
- excerpts
|
||||
- confidence / risk
|
||||
- primary-law escalation only when the IRS corpus is still insufficient
|
||||
- renders that analysis as:
|
||||
- conversational output
|
||||
- memo output
|
||||
- marks questions outside the current topical rule set as requiring primary-law escalation
|
||||
|
||||
Current implemented topics:
|
||||
|
||||
- standard deduction
|
||||
- Schedule C / sole proprietorship reporting trigger
|
||||
- Schedule D / capital gains reporting trigger
|
||||
- Schedule E / rental income reporting trigger
|
||||
In OpenClaw, the model should answer the user from the returned IRS excerpts when `primaryLawRequired` is `false`, rather than merely repeating the CLI summary.
|
||||
|
||||
## Form Rendering
|
||||
|
||||
|
||||
Reference in New Issue
Block a user