Ettore Di Giacinto ea456e7027 fix(ci): treat .docker/ as a shared build input ...

#11346 changed how ROCm llama.cpp compiles and built nothing. It touched
.docker/llama-cpp-build-target.sh and scripts/build/llama-cpp-build-target_test.sh,
no SHARED_BUILD_INPUTS rule matched either (the second is carved out on
purpose), so the filter selected zero entries and all six backend job
groups reported "skipping". The fix shipped to master unvalidated.

.docker/ holds the per-backend compile and build-target scripts for
llama-cpp, turboquant, bonsai and ik-llama-cpp, plus inputs every
Dockerfile consumes (apt-mirror.sh, install-base-deps.sh). Those files
decide how a backend is compiled, so a change to one can only be
validated by rebuilding it.

Take the same posture the scripts/build/ catch-all already takes, and for
the reason its comment already gives: a shared build input silently
shipping to nothing is the failure this list exists to prevent. A rule
sees only the matrix entry, not which file matched it, so narrowing
.docker/<name>-compile.sh to the backend named by its prefix would mean
threading the filename through matchedSharedRules. Not worth it for files
edited a handful of times a release.

Two regression tests, both verified red against the unfixed filter:
one asserting a .docker/ compile script selects the backend it compiles,
one asserting a shared .docker/ input takes the full matrix.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude Code:claude-opus-5 [Read] [Edit] [Bash]

2026-08-04 21:44:08 +00:00

..

backend-filter_test.mjs

fix(ci): treat .docker/ as a shared build input

2026-08-04 21:44:08 +00:00

backend-filter.mjs

fix(ci): treat .docker/ as a shared build input

2026-08-04 21:44:08 +00:00