## What
Migrate `dedup_test.go`'s 6 manual `origDir, _ := os.Getwd();
os.Chdir(tmp); defer os.Chdir(origDir)` blocks to Go 1.20+
`t.Chdir(tmp)` — auto-restores cwd **and** refuses `t.Parallel`,
pre-empting the latent flake class flagged by **ag-4nif** / **ag-k38x**
(raw forms mutate process-global cwd). No `t.Parallel` in the file;
behavior-preserving.
Each block held two `os.Chdir(` references (the call + the defer
restore), so 6 blocks drop the repo-wide test-isolation count by **12
(163→151)**. I lowered `BASELINE_CHDIR` in
`scripts/check-test-isolation.sh` to **lock the gain** (the ratchet is
only-goes-down).
## Scope / no-collision note
`os.Chdir` only. The 3 redundant `os.Setenv` restores in
`rpi_reliability_test.go` are **already handled by the open PR #772
(ag-k38x)** — I deliberately do **not** touch that file here, to avoid a
merge collision (an earlier draft of this branch did; it was reverted).
**ag-k38x is the canonical tracker; ag-4nif/ag-y4ac are duplicates** —
worth closing as dup-of-ag-k38x during triage.
## Evidence
```
bash scripts/check-test-isolation.sh # PASS (os.Chdir=151/151, os.Setenv=22/22)
cd cli
go build ./... # OK
go vet ./cmd/ao/ # No issues found
go test ./cmd/ao/ -run 'TestRunDedup|TestMergeDedupGroups' -count=1 # 17 pass
gofmt -l # clean
```
Net: −19 / +8 across `dedup_test.go` + the ratchet baseline.
Closes-scenario: ag-4nif#dedup-tchdir
Bounded-context: BC5-Runtime
Evidence: ratchet PASS + go build/vet/test (17 pass) + gofmt clean
## What
Lands the durable mechanism for ag-k38x (codebase-audit P2-1/P2-2): raw
`os.Chdir`/`os.Setenv` in tests mutate process-global cwd/env — a latent
flake landmine once any test opts into `t.Parallel` (cf. **ag-jfzs**,
the memory-sync flake of exactly this class).
The repo has ~163 `os.Chdir` + 22 `os.Setenv` inline sites across 34
files in **non-uniform patterns** (`defer` / `t.Cleanup` / `defer
func(){}()` with reversed order) — a blind sweep would break the suite.
So this ships the **durable gate + the canonical lever**, not a risky
80-site mass-edit:
- **`scripts/check-test-isolation.sh`** — a baseline ratchet (163/22)
wired into the **process-hygiene** job: raw `os.Chdir`/`os.Setenv` in
`*_test.go` may not **grow**; new code must use `t.Chdir`/`t.Setenv` or
the testutil helpers. This pre-empts the flake class from spreading.
- **`testutil_test.go`** — `chdirTemp`/`chdirTo` migrated from
`os.Chdir`+`t.Cleanup` to `t.Chdir` (the shared helpers most tests
delegate to; canonical example).
## Follow-up
The bulk inline-site migration drives the baseline toward zero
incrementally — **ag-k38x stays open** for it (scenario
`#bulk-migration`). Decomposing an ~80-site, non-uniform migration into
*gate-the-growth now + reduce-incrementally* is the responsible path; a
one-shot sed would be the reckless one.
## Verification
Ratchet PASSes at baseline AND catches a synthetic increase; shellcheck
+ `validate-ci-policy-parity` green; `go vet` clean; chdir-helper-caller
tests pass under `-race`.
Closes-scenario: ag-k38x#lint-ratchet
Bounded-context: BC2-Validation
Evidence: scripts/check-test-isolation.sh
Bo