* security: isolate every gstack Bun entry point from the audited checkout's .env and bunfig.toml
Bun auto-loads .env, .env.local and .env.<NODE_ENV> from its cwd and runs a
cwd bunfig.toml preload before the program starts. gstack runs inside the repo
it audits, so a committed .env could steer state roots, the claude binary or
spend caps, and a bunfig preload ran arbitrary code in every bin and hook.
Every bun shebang, shell and skill caller, TypeScript spawn and compiled build
now disables both (--no-env-file --config=/dev/null, bunIsolationArgs(),
--no-compile-autoload-dotenv/bunfig), with a ratchet and hostile-fixture
regressions.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: name the directly executed scripts in the isolation ratchet
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: follow the isolation flags in touchfiles, copy lists, recipe assertions and the harness pin
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: keep browse/src/bun-child-config.ts unchanged so the native cookie qualification still binds
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(windows): the empty bunfig outlives its process so the timeline hook's detached repair child can read it
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.159.0 security: gstack's Bun entry points ignore the audited repo's .env and bunfig.toml (S1)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: plan-mode render pattern accepts the isolation flags
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(dx): agent-ready error contract for the DevEx review skills
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(dx): gstack-error-capture runs a CLI with no terminal and prints a redacted record
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(dx): CI-clean fences, runtime-root-safe contract location, path-agnostic launch-check test
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(dx): preregistered behavior case for the agent-ready error contract; README skill rows
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(dx): grader items come from the contract; paid-file count includes the new case
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(dx): outside DX voice uses the agent-ready contract; DX_CAPTURE_* codes join RESULT_CODES with troubleshooting anchors
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(dx): review fixes for gstack-error-capture and the paid grader
- every helper diagnostic passes the record's redaction, fail-closed
- forwarded values are masked before and after sanitizing, plus JSON-escaped forms
- the final secret check reads the record's string fields with byte-based scan limits
- mise/asdf config, trust and env-loading variables need --pass-env; only data locations pass by default
- launch reports whether the target started; --launch-check's probe result is exit_code
- Step 3 captures --help first; help states the containment lifetime limit
- the paid grader validates the bound result with parseReviewResult
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(dx): mask forwarded values before argument validation; protocol strings never match literals; Step 3 captures stay read-only
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.114.0 feat(dx): score every error for an AI agent reader (agent-ready error contract + gstack-error-capture)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
