* test(#2940): prove gsd-update discards codex config after the GSD marker
Failing-first regression for #2940. mergeCodexConfig Case 2 (marker present)
preserves content before the marker but discards everything from the marker to
EOF, so user/Codex-CLI settings ([model], [mcp_servers.*], [profiles.*]) added
after a fresh install are wiped on every update. Rows 1-2 assert trailing user
content survives; rows 3-7 cover idempotency, the #2406 leaked-section
non-regression, the [agents] namespace, both regions, and the zero-trailing
boundary.
* fix(#2940): preserve codex config.toml content after the GSD marker on update
mergeCodexConfig Case 2 (marker present) preserved content before the marker but
discarded everything from the marker to EOF, so user/Codex-CLI settings added
after a fresh install ([model], [mcp_servers.*], [profiles.*]) were wiped on
every gsd-update.
Route the trailing region through the existing stripLeakedGsdCodexSections,
which removes GSD's own managed/leaked sections (the bare [agents] table GSD
regenerates, legacy [agents.gsd-*], [[agents]]) while preserving genuine user
TOML. The marker comment line (and the optional codex_hooks ownership line) is
stripped from the trailing region first so it is not duplicated alongside the
regenerated block. #2406's de-dup still holds (leaked sections after the marker
are still stripped), and re-merge is idempotent.
* fix(#2940): use CRLF-safe regex in regression test (lint:ci no-crlf-fragile-split)
The Row 7 blank-line assertion used a bare \n which trips local/no-crlf-fragile-split
under Windows git-autocrlf. Use \r?\n.
* fix(#2940): correct Row 5 to valid single-[agents] TOML shape
The isolated adversarial review found Row 5 (bareAgentsAfterMarkerHandled)
constructed TWO [agents] tables (the GSD-managed one + a user trailing one),
which is invalid TOML — a duplicate table definition. extractCodexUserAgentsScalars
reads only the first [agents] and stripLeakedGsdCodexSections removes ALL bare
[agents] tables, so the user's max_threads would be silently dropped.
The valid, realistic shape is the user folding max_threads INTO the managed
[agents] block (which the existing spliceCodexAgentsScalars path preserves) plus
a separate trailing [model]. Reword Row 5 to that shape. A duplicate-[agents]
input is invalid TOML Codex itself rejects, so it is out of scope for this fix.
* chore(#2940): add changeset fragment
* chore(#2940): backfill changeset PR number 3067
---------
Co-authored-by: sim <sim@local>
c9dd4aa951