You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 2ad7dc9
Browse filesBrowse the repository at this point in the historyBrowse files
Both sides appended to the same wpf-extractor job tail: main's #215
[OwnIgnore] block (sample, assertions, SARIF rc-capture step) and this
branch's #218 rotation block (sample, silent + three flagged controls).
Kept both, single merged OK line. Program.cs auto-merged (additive).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LsWw4Ay8KLTHFom1HvRu3U
Copy file name to clipboardExpand all lines: docs/suppression-and-fp-policy.md
+20-14Lines changed: 20 additions & 14 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -45,30 +45,36 @@ fire on unprovable input.
45
45
|---|---|---|
46
46
|`--severity warning`|**works today** (P-013) | Global: downgrades every error-tier finding for that run to advisory. Per-run, not per-finding — an escape hatch for "show me everything, but don't fail the build yet," not a way to silence one specific site. |
47
47
|`--fail-on-finding` set to off |**works today** (P-013) | Global: findings still print/annotate, but the process/step exit code stays 0. The CLI (`own-check.sh`) is off by default — you must pass the flag to make findings fail the shell. The GitHub Action inverts that for safety: its `fail-on-finding` input defaults to `"true"` (fails the step on a finding), so to get the "annotate but don't fail" behavior in CI you must explicitly set `fail-on-finding: "false"`. |
48
-
|`[OwnIgnore("reason")]`|**designed, not implemented** (P-004) | Inline, per-site suppression attribute — the intended fine-grained escape hatch for a specific subscription/field the checker can't see enough context to clear. Referenced across P-001/P-004/P-010/P-014/P-017 as the standing design; there is no code behind it yet. If you need this today, the honest answer is: you don't have it — file the case so it informs the implementation. |
48
+
|`[OwnIgnore("reason")]`|**works today**on `IDisposable` fields (P-004, #209) | Inline, per-site suppression attribute — the fine-grained escape hatch for a specific site the checker can't see enough context to clear. Put `[OwnIgnore("reason")]` on the field; the finding is then **silent-but-counted** — kept out of the exit code and the human findings stream, but tallied in the run summary and carried in SARIF `suppressions` (`kind: "inSource"`, your reason as the `justification`) so nothing is lost and a consumer can audit it. The **reason is mandatory**: a reason-less `[OwnIgnore]` (or an empty `[OwnIgnore("")]`) does **not** suppress — a suppression is a documented decision, never a silent accept. The attribute is matched by simple name, so you can declare your own `OwnIgnoreAttribute`. Currently reads on `IDisposable`**field** declarations (the clearest attribute site); other sites (subscriptions, timers) are follow-up increments. |
49
49
| Project-wide config (`.ownrc`/`own.toml`) |**draft, not implemented** (P-015) | Per-check-category enable/disable + severity + per-path overrides (e.g. relax a category under `tests/`). Stub status — format (TOML vs INI vs JSON) and enforcement point are still open questions in the proposal. |
50
50
|`corpus/oracle-fp-baseline.txt`|**exists, but not a user-facing suppression tool**| An allowlist the *oracle comparator* (`scripts/oracle_compare.py`, a dev/maintainer tool) uses to keep already-triaged false positives out of the `own-only` bucket on re-runs. It doesn't change what `own-check`/the Action reports — it only keeps the oracle's own triage queue from re-showing confirmed noise. |
51
51
52
-
So today, honestly: there is no way to suppress **one specific finding** in
53
-
your own repo. The two escape hatches for that (`[OwnIgnore]`, project config)
54
-
are designed and drafted respectively, not shipped. What you have is a global
55
-
severity dial and the extractor's own honest-skip behavior, which is why the
56
-
precision bar above matters as much as the (currently thin) suppression
57
-
surface — the fewer false positives reach you, the less suppression UX has to
58
-
carry.
52
+
So today: you **can** suppress one specific finding with an inline
53
+
`[OwnIgnore("reason")]` on the field it fires on (shipped, #209) — the finding
54
+
goes silent but stays counted (summary tally + SARIF `suppressions`). The
55
+
project-wide counterpart (`.ownrc`/`own.toml`, P-015) is drafted, not shipped.
56
+
Together with the global severity dial and the extractor's own honest-skip
57
+
behavior, that covers per-site and per-run; the per-*category*, per-*path*
58
+
config is the remaining gap. The precision bar above still matters as much as
59
+
the suppression surface — the fewer false positives reach you, the less
60
+
suppression UX has to carry.
59
61
60
-
## The designed shape (so you know what's coming)
62
+
## The full shape (`[OwnIgnore]` shipped; config still to come)
61
63
62
-
Precedence, once both land (P-015's draft order):
64
+
Precedence (P-015's draft order — the inline attribute half is shipped, #209;
0 commit comments