nftpixels 4d66a84ac5 fix(intercept): match tool_input rules against decoded values ...

tool_input rules were only matched against the raw JSON of the tool call.
JSON escapes newlines and tabs, so a multi-line command reaches the rules as
`cd /tmp\nrm -rf /var/www`. There is no word boundary between the `n` of `\n`
and `rm`, so the built-in `\brm\b` / `\bmkfs\b` / `\bDROP ...` rules never
fire on a dangerous command that starts a new line (heredocs, small scripts).
Quotes (`\"`) and, for Go-encoded input, & < > (`&` etc.) have the same
problem.

Decode the input once per Match and also try each string value. The raw
JSON is still checked first, so existing rules written against the JSON
form keep matching; the change can only add matches.

2026-11-14 11:16:27 +13:00

..

jev

fix: align Jev integration with official System One protocol

2026-11-03 15:53:24 +08:00

intercept.go

fix(intercept): match tool_input rules against decoded values

2026-11-14 11:16:27 +13:00

judge_retry_test.go

fix(intercept): default judge failure retries to three

2026-10-20 11:25:04 +08:00

judge_retry.go

fix: add configurable model approval retries

2026-10-15 14:45:08 +08:00

prompt_test.go

fix(intercept): 模型裁决被代码块包裹时不再静默放行 (#126)

2026-09-15 20:40:41 +08:00

prompt.go

fix: improve static script review and default to model judgement

2026-10-13 14:08:00 +08:00

python_modules.go

fix: improve static script review and default to model judgement

2026-10-13 14:08:00 +08:00

python_shell_environment_test.go

fix: improve static script review and default to model judgement

2026-10-13 14:08:00 +08:00

python_shell_environment.go

fix: improve static script review and default to model judgement

2026-10-13 14:08:00 +08:00

review_context_test.go

fix: improve static script review and default to model judgement

2026-10-13 14:08:00 +08:00

review_context.go

fix: address Jev judge review feedback

2026-10-31 18:16:49 +08:00

rule_match_test.go

fix(intercept): match tool_input rules against decoded values

2026-11-14 11:16:27 +13:00

script_resolution_test.go

fix: improve static script review and default to model judgement

2026-10-13 14:08:00 +08:00

scripts_test.go

fix: improve static script review and default to model judgement

2026-10-13 14:08:00 +08:00

scripts.go

fix: improve static script review and default to model judgement

2026-10-13 14:08:00 +08:00

shell_constants.go

fix: improve static script review and default to model judgement

2026-10-13 14:08:00 +08:00

shell_static.go

fix: improve static script review and default to model judgement

2026-10-13 14:08:00 +08:00

static_sed_test.go

fix: improve static script review and default to model judgement

2026-10-13 14:08:00 +08:00

static_sed.go

fix: improve static script review and default to model judgement

2026-10-13 14:08:00 +08:00

trace_test.go

feat(intercept): 模型审查补充任务上下文与裁决说明 (#124)

2026-09-15 20:08:12 +08:00

trace.go

精简动作审查输入并支持审批来源定位 (#125)

2026-09-15 23:51:37 +08:00