scan_stream() scans character chunks as they arrive from a streaming model
API. Each scan uses the current chunk plus a configurable overlap from the
previous text so rules can catch phrases split across chunk boundaries.
Usage
scan_stream(
chunks,
policy = "enterprise_default",
reviewer = NULL,
checks = "rules",
chunk_size = 1000L,
overlap = 200L,
on_block = c("stop", "return"),
redaction = NULL,
scanners = scanner_options(),
show_tokens = FALSE
)Arguments
- chunks
Character vector of streamed text chunks, or one long string.
- policy
A
shieldr_policyor built-in policy name.- reviewer
Optional reviewer function or object with
$chat().- checks
One of
"rules","nlp","llm", or"both".- chunk_size
Maximum size used to split a single long string.
- overlap
Number of trailing characters from prior output to include when scanning the next chunk.
- on_block
One of
"stop"or"return".- redaction
Optional redaction strategy from
redaction_strategy().- scanners
Optional scanner configuration from
scanner_options().- show_tokens
Whether to attach token counts when
ellmeris available.
Details
This helper is intentionally transport-agnostic: pass the text chunks you
receive from an SDK, callback, or websocket handler. It returns per-window
reports and a combined action. If on_block = "stop", the function aborts
as soon as a window resolves to block; use on_block = "return" when you
want a full report object instead.
chunk_size is used only when chunks is a single long string. Character
vectors with more than one element are treated as already chunked.
Examples
scan_stream(
c("I will now ", "delete the records."),
on_block = "return"
)
#> $action
#> [1] "block"
#>
#> $text
#> [1] "I will now delete the records."
#>
#> $reports
#> $reports[[1]]
#> llmshieldr report
#> action: block
#> risk_score: 1.000
#> findings: 1
#>
#> $reports[[2]]
#> llmshieldr report
#> action: block
#> risk_score: 1.000
#> findings: 1
#>
#>
#> attr(,"class")
#> [1] "shieldr_stream_result"