Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
56 commits
Select commit Hold shift + click to select a range
23a2a2c
Send who requested the build in the metrics payload
migueldalberto Sep 24, 2026
478cc0c
asap7/chi_async_bridge: XiangShan's asynchronous CHI bridge
oharboe Oct 1, 2026
e767be4
Check QoR as a checkout of the recorded commit
migueldalberto Oct 2, 2026
de6ca1c
Merge remote-tracking branch 'origin/master' into upload-build-requester
migueldalberto Oct 2, 2026
cc371f3
AUTO_MEMORIES: only convert a memory that is its own module
oharboe Oct 4, 2026
c106d26
AUTO_MEMORIES: a firtool memory module is a memory; read its ports, r…
oharboe Oct 4, 2026
723df49
AUTO_MEMORIES: refuse an RD_CLK_ENABLE that is not one bit per read port
oharboe Oct 4, 2026
8a82183
memories: run the memory passes on the modules that hold memory cells
oharboe Oct 4, 2026
13a2cf8
memories: select every memory cell type, stop if one is left out
oharboe Oct 4, 2026
01db8dc
feat(docker): build yosys into a reusable tools image
maliberty Oct 5, 2026
b0d1bf8
asap7: document why STA-1212 is suppressed
dsengupta0628 Oct 5, 2026
53f9445
memories: select the memory modules with %m, not by name
oharboe Oct 5, 2026
9833c2f
Publish a metrics payload even when no design produced metrics
migueldalberto Oct 5, 2026
d8069b1
asap7/chi_async_bridge: say the port budgets are this file's, not the…
oharboe Oct 6, 2026
762750f
asap7/chi_async_bridge: budget the port-to-port paths
oharboe Oct 6, 2026
b3cc97b
asap7/chi_async_bridge: the NoC clock is not half the core's frequency
oharboe Oct 6, 2026
af424a0
asap7/chi_async_bridge: read SYNC from VERILOG_TOP_PARAMS, as DEPTH is
oharboe Oct 6, 2026
4ae1925
asap7/chi_async_bridge: say the synchroniser check guards synthesis only
oharboe Oct 6, 2026
1923012
asap7/chi_async_bridge: the licenses the SystemVerilog comes under
oharboe Oct 6, 2026
c4b171c
asap7/chi_async_bridge: link hierarchically, the bridge's modules kept
oharboe Oct 6, 2026
bd2b703
asap7/chi_async_bridge: README says what it tests that no other desig…
oharboe Oct 6, 2026
e3f84f8
asap7/chi_async_bridge: core clock 290 ps, so repair does not stop at…
oharboe Oct 6, 2026
827d4d0
test: force a QoR regression to check the Jenkins QoR stage
vvbandeira Oct 6, 2026
78a3b6f
test: rerun with the updated jenkins-ci branch
vvbandeira Oct 6, 2026
e315077
Default the reported build time to UTC
migueldalberto Oct 6, 2026
409687c
genElapsedTime: report CPU time and CPU/elapsed ratio
maliberty Oct 6, 2026
5377393
formal_check: run kepler-formal through run_command.py
maliberty Oct 6, 2026
239852e
fix(docker): address review feedback on tools image
maliberty Oct 6, 2026
dfc688e
Merge pull request #4642 from The-OpenROAD-Project-staging/elapsed-cpu
maliberty Oct 7, 2026
9b26ff8
Merge pull request #4625 from The-OpenROAD-Project-staging/docker-bui…
vvbandeira Oct 7, 2026
bf66d20
fix(docker): remove unused net-imap default gem
noahwithoutark22 Oct 7, 2026
3e353f1
fix(docker): chain net-imap removal into the install layer
noahwithoutark22 Oct 7, 2026
4a6c608
Track endpoint slack across flow steps
maliberty Oct 7, 2026
b0cb3ed
load.tcl: apply WIRE_LOAD_MODEL in load_design
maliberty Oct 8, 2026
7b9e765
Time the 6_final endpoint slack with extracted parasitics
maliberty Oct 8, 2026
12544aa
Merge pull request #4648 from The-OpenROAD-Project-staging/load-wire-…
maliberty Oct 8, 2026
e54722b
Merge pull request #4647 from The-OpenROAD-Project-staging/endpoint-s…
maliberty Oct 8, 2026
1a82e9c
Merge pull request #4618 from oharboe/auto-memories-firtool-modules
maliberty Oct 8, 2026
12eb8bd
Merge pull request #4622 from oharboe/extract-memories-scoped
maliberty Oct 8, 2026
a6accfe
ci: remove the jenkins/public_tests_all.Jenkinsfile symlink
vvbandeira Oct 8, 2026
f395e4b
Merge pull request #4654 from vvbandeira/jenkinsfile-no-symlink
vvbandeira Oct 8, 2026
2848820
Merge pull request #4644 from noahwithoutark22/fix/4376-remove-stale-…
maliberty Oct 8, 2026
517d105
Merge pull request #4600 from oharboe/asap7-chi-async-bridge
maliberty Oct 8, 2026
ef42174
Merge pull request #4629 from The-OpenROAD-Project-staging/asap7-docu…
maliberty Oct 8, 2026
ce18bba
test: merge qor-check-ci-mode for the jenkins-ci stack test
vvbandeira Oct 9, 2026
aecff21
test: merge upload-no-metrics-builds for the jenkins-ci stack test
vvbandeira Oct 9, 2026
aac2b88
test: merge upload-build-requester for the jenkins-ci stack test
vvbandeira Oct 9, 2026
ddd2b6d
test: run three gcd designs on the jenkins-ci stack, two broken
vvbandeira Oct 9, 2026
e78ea11
test: run nangate45/gcd broken so no design writes metrics
vvbandeira Oct 9, 2026
fc0c63a
test: keep the earlier test commit as a parent so this update fast-fo…
vvbandeira Oct 9, 2026
ab4a7d5
test: keep the run 1 commit as a parent so this update fast-forwards
vvbandeira Oct 9, 2026
b18925d
test: load the jenkins-ci library from orfs-qor-one-stage
vvbandeira Oct 9, 2026
2426c6a
test: keep the re-test commit as a parent so this update fast-forwards
vvbandeira Oct 9, 2026
2eb6616
test: load the jenkins-ci library from orfs-qor-one-stage
vvbandeira Oct 9, 2026
f5936bb
test: keep the no-metrics run as a parent so this update fast-forwards
vvbandeira Oct 9, 2026
f016d7f
test: load the jenkins-ci library from orfs-error-steps
vvbandeira Oct 9, 2026
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions Jenkinsfile
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
@Library('utils@main') _
@Library('utils@orfs-error-steps') _

node {
pipelineORFS(maxTimeout: 180)
pipelineORFS(maxTimeout: 180, filter: 'nangate45/gcd,sky130hd/gcd,ihp-sg13g2/gcd')
}
22 changes: 22 additions & 0 deletions build_openroad.sh
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@ function usage() {

Usage: $0 [-h|--help] [-o|--local] [-l|--latest]
[--or_branch BRANCH_NAME] [--or_repo REPO_URL] [--no_init]
[-s|--skip_openroad] [--openroad_only]
[-n|--nice] [-t|--threads N]
[--yosys-args-overwrite] [--yosys-args STRING]
[--with-verific PATH]
Expand All @@ -57,6 +58,9 @@ Options:

-s, --skip_openroad Skip building and all git operations on OpenROAD.

--openroad_only Build only OpenROAD; skip Yosys, Verific and
kepler-formal. Requires --local.

--or_branch BRANCH_NAME Use the head of branch BRANCH for tools/OpenROAD.

--or_repo REPO_URL Use a fork at REPO-URL (https/ssh) for tools/OpenROAD.
Expand Down Expand Up @@ -165,6 +169,9 @@ while (( "$#" )); do
-s|--skip_openroad)
SKIP_OPENROAD=1
;;
--openroad_only)
OPENROAD_ONLY=1
;;
--or_branch)
OPENROAD_APP_BRANCH="$2"
shift
Expand Down Expand Up @@ -233,6 +240,17 @@ while (( "$#" )); do
shift
done

if [ ! -z "${OPENROAD_ONLY+x}" ]; then
if [ -z "${LOCAL_BUILD+x}" ]; then
echo "[ERROR FLW-0033] --openroad_only requires --local." >&2
exit 1
fi
if [ ! -z "${SKIP_OPENROAD+x}" ]; then
echo "[ERROR FLW-0033] --openroad_only and --skip_openroad are mutually exclusive." >&2
exit 1
fi
fi

if [[ "$PROC" == "-1" ]]; then
if [[ "$OSTYPE" == "linux-gnu"* ]]; then
PROC=$(nproc --all)
Expand Down Expand Up @@ -373,6 +391,10 @@ __local_build()
${NICE} ./tools/OpenROAD/etc/Build.sh "${OPENROAD_APP_ARGS[@]}"
fi

if [ ! -z "${OPENROAD_ONLY+x}" ]; then
return
fi

YOSYS_ABC_PATH=tools/yosys/abc
if [[ -d "${YOSYS_ABC_PATH}/.git" ]]; then
# update indexes to make sure git diff-index uses correct data
Expand Down
56 changes: 46 additions & 10 deletions docker/Dockerfile.builder
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,9 @@
# instead use etc/DockerHelper.sh

ARG fromImage=openroad/flow-ubuntu22.04-dev:latest
# Image holding the prebuilt tools/install of every tool except OpenROAD
# (a build of the orfs-tools target). By default they are built here.
ARG toolsImage=orfs-tools

FROM $fromImage AS orfs-base

Expand All @@ -22,7 +25,11 @@ RUN sh /tmp/setup_compiler_wrappers.sh && rm /tmp/setup_compiler_wrappers.sh
# Prepend wrapper directory to PATH so they override system compilers
ENV PATH="/usr/local/bin/wrapped-cc:$PATH"

COPY --link tools tools
FROM orfs-builder-base AS orfs-tools-builder

# Exclude install so a local build's output (e.g. tools/install/OpenROAD)
# cannot leak into the image; the build below starts from an empty install.
COPY --link --exclude=OpenROAD --exclude=AutoTuner --exclude=install tools tools
ARG numThreads=$(nproc)
ARG verificPath=""

Expand All @@ -36,30 +43,59 @@ else
fi
./build_openroad.sh --no_init \
--local \
--skip_openroad \
--threads ${numThreads} \
${verificArgs}
if [ ! -x tools/install/OpenROAD/bin/openroad ]; then
echo "Error: tools/install/OpenROAD/bin/openroad is missing or not executable." >&2
exit 1
fi
if [ -n "${verificPath}" ]; then
rm -rf "${verificPath}"
fi
EOF

# Collect LICENSE files from tool source trees into the install directory so
# they are available in the final image. tools/OpenROAD/src/sta is excluded
# because it is covered by a separate commercial license agreement.
# they are available in the final image.
RUN find /OpenROAD-flow-scripts/tools \( -name "*LICENSE*" -o -name "*LICENSES*" \) \
| grep -v '/OpenROAD/src/sta/' \
| grep -v '/AutoTuner/' \
| grep -v '^/OpenROAD-flow-scripts/tools/install/' \
| while IFS= read -r f; do \
rel="${f#/OpenROAD-flow-scripts/tools/}"; \
mkdir -p "/OpenROAD-flow-scripts/tools/install/licenses/$(dirname "$rel")"; \
cp -r "$f" "/OpenROAD-flow-scripts/tools/install/licenses/$rel"; \
done

# Yosys, kepler-formal and their licenses, without sources or build trees.
FROM orfs-base AS orfs-tools

COPY --link --from=orfs-tools-builder /OpenROAD-flow-scripts/tools/install tools/install

FROM $toolsImage AS tools

FROM orfs-builder-base AS orfs-openroad-builder

COPY --link --from=tools /OpenROAD-flow-scripts/tools/install tools/install
COPY --link tools/OpenROAD tools/OpenROAD
ARG numThreads=$(nproc)

RUN <<EOF
set -e
./build_openroad.sh --no_init \
--local \
--openroad_only \
--threads ${numThreads}
if [ ! -x tools/install/OpenROAD/bin/openroad ]; then
echo "Error: tools/install/OpenROAD/bin/openroad is missing or not executable." >&2
exit 1
fi
EOF

# tools/OpenROAD/src/sta is excluded because it is covered by a separate
# commercial license agreement.
RUN find /OpenROAD-flow-scripts/tools/OpenROAD \( -name "*LICENSE*" -o -name "*LICENSES*" \) \
| grep -v '/OpenROAD/src/sta/' \
| while IFS= read -r f; do \
rel="${f#/OpenROAD-flow-scripts/tools/}"; \
mkdir -p "/OpenROAD-flow-scripts/tools/install/licenses/$(dirname "$rel")"; \
cp -r "$f" "/OpenROAD-flow-scripts/tools/install/licenses/$rel"; \
done

FROM orfs-base

# The order for copying the directories is based on the frequency of changes (ascending order),
Expand All @@ -74,7 +110,7 @@ COPY --link flow/scripts flow/scripts
COPY --link flow/designs flow/designs
COPY --link tools/AutoTuner tools/AutoTuner

COPY --link --from=orfs-builder-base /OpenROAD-flow-scripts/tools/install tools/install
COPY --link --from=orfs-openroad-builder /OpenROAD-flow-scripts/tools/install tools/install
COPY --link \
--exclude=.git* --exclude=tools/ --exclude=docs/ --exclude=docker/ \
--exclude=flow/designs --exclude=flow/platforms --exclude=flow/scripts \
Expand Down
7 changes: 6 additions & 1 deletion docker/Dockerfile.dev
Original file line number Diff line number Diff line change
Expand Up @@ -23,9 +23,14 @@ RUN sh /tmp/setup_compiler_wrappers.sh && rm /tmp/setup_compiler_wrappers.sh

ENV PATH="/usr/local/bin/wrapped-cc:$PATH"

# The last rm drops the unused net-imap default gem bundled with Ubuntu 22.04's
# Ruby 3.0 (flagged by CVE scanners, never used by the flow). It is chained here
# so the files don't persist in an earlier layer. No-op if not present.
RUN ./DependencyInstaller.sh -base $options $constantBuildDir -save-deps-prefixes=/etc/openroad_deps_prefixes.txt \
&& ./DependencyInstaller.sh -common $options $constantBuildDir -save-deps-prefixes=/etc/openroad_deps_prefixes.txt \
&& rm -rf /tmp/installer /tmp/* /var/tmp/* /var/lib/apt/lists/*
&& rm -rf /tmp/installer /tmp/* /var/tmp/* /var/lib/apt/lists/* \
&& rm -rf /usr/lib/ruby/gems/*/gems/net-imap-0.1.1 \
/usr/lib/ruby/gems/*/specifications/default/net-imap-0.1.1.gemspec

ARG fromImage

Expand Down
162 changes: 162 additions & 0 deletions docs/contrib/EndpointSlackTracking.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,162 @@
# Tracking Endpoint Slack Across Flow Steps

When working on an optimization (resizing, buffering, CTS, repair timing,
...) it is useful to see how the slack of each timing endpoint moves from
one flow step to the next, not just how WNS/TNS change. ORFS can record the
setup and hold slack of every endpoint at the end of every flow step
(`1_synth`, `2_1_floorplan`, ..., `3_3_place_gp`, ..., `6_final`) and compare
any two steps, including a scatter plot of slack (x: earlier step, y: later
step).

## Recording

Set `REPORT_ENDPOINT_SLACK=1`:

``` shell
cd flow
make DESIGN_CONFIG=designs/nangate45/gcd/config.mk REPORT_ENDPOINT_SLACK=1
```

Every step then writes `$(REPORTS_DIR)/<step>_endpoint_slack.json`, e.g.
`3_3_place_gp_endpoint_slack.json`. The snapshot is taken by
`write_endpoint_slack` in `flow/scripts/util.tcl`, called from
`orfs_write_db` so the step name is the name of the `.odb` the step writes.
It works in the single-process `flow/scripts/flow.tcl` flow as well. Steps
that just copy their input (`orfs_copy_db`, e.g. `5_3_fillcell` without fill
cells) re-time the design if it is loaded, or else copy the previous step's
snapshot. Intermediate `.odb` files written through `orfs_write_db` (e.g. CTS
`save_progress`) also get a snapshot; `*-failed` ones don't.

So that all steps are timed the same way, parasitics are estimated before
reporting as in `open.tcl`, based on the step number:

| Steps | Parasitics |
| --- | --- |
| 1, 2 | none (cells are not placed) |
| 3, 4 | `estimate_parasitics -placement` |
| 5, `6_1_fill` | `estimate_parasitics -global_routing` if global routes exist |
| `6_final` | `rcx`: the extracted `6_final.spef`, as in `6_finish.rpt` (`global_routing` on platforms without `RCX_RULES`) |

The parasitics model is recorded in each snapshot and shown by
`endpointSlack.py`. Slack changes between steps with different models (e.g.
`2_4_floorplan_pdn` to `3_1_place_gp_skip_io`, `4_1_cts` to `5_1_grt`, or
`6_1_fill` to `6_final`) include the change of model. Detailed routing is
only extracted in `6_final`, so `5_2_route` to `6_1_fill` show global routing
estimates.

Each file contains `design`, `step`, `parasitics`, `time_unit` (seconds per
time unit of the values) and `endpoints`: a map from every endpoint pin
(`sta::endpoints`) to `[setup slack, hold slack]`, `null` where the endpoint
is unconstrained. The slack is the pin's worst slack over all path groups
and clocks (`get_property $pin slack_max|slack_min`). On asap7/swerv_wrapper
(about 30k endpoints) a snapshot is about 1 MB and takes about 10 s, mostly
the timing update.

## Analysis

`flow/util/endpointSlack.py` only uses the Python standard library.

``` shell
R=reports/nangate45/gcd/base

# Steps in execution order with parasitics, WNS, TNS and violation counts
python3 util/endpointSlack.py list $R

# Compare consecutive steps across the whole run; --html also writes a
# scatter for every step vs. its successor and an index.html to a directory
python3 util/endpointSlack.py track $R --html track

# Compare two steps; -o writes an interactive HTML scatter
python3 util/endpointSlack.py compare \
$R/3_5_place_dp_endpoint_slack.json $R/4_1_cts_endpoint_slack.json \
--unit ps -o compare.html

# Flatten all snapshots into one CSV (one row per endpoint per step)
python3 util/endpointSlack.py export $R -o slack.csv
```

For setup and hold, `compare` reports:

- endpoints in both steps, and how many improved, degraded, stayed the
same, became violating (`newly failing`) or stopped violating
(`newly passing`), with statistics of the slack change (B - A).
Improved, degraded and unchanged exclude endpoints with positive slack in
both steps, which are not being optimized;
- endpoints only in A or only in B, i.e. added or removed from the netlist;
- endpoints in both netlists but constrained in only one of them;
- how well the two steps agree on the critical endpoints (see below).

Unconstrained endpoints, such as the outputs of CTS dummy load cells, are
ignored.

### Agreement metrics

Correlation over all endpoints is dominated by endpoints with large positive
slack and is close to 1 even when the critical endpoints change a lot (0.9997
for setup on asap7/swerv_wrapper from `3_5_place_dp` to `4_1_cts`). The
metrics are therefore measured on a critical set: the worst K endpoints of A
or of B (`--critical K`, default 1000), excluding endpoints with positive
slack in both steps, which are not being optimized. When fewer than K
endpoints violate, the critical set is the endpoints violating in either
step; when nothing violates (often hold) it is empty and the metrics are
reported as `-`.

| Metric | Meaning |
| --- | --- |
| `spearman` | Spearman rank correlation of A and B slack (ties get average ranks): is the order of the critical endpoints preserved? |
| `top agreement` | Fraction of the critical set that is in the worst K of both steps. |
| `bias`, `MAE`, `RMSE`, `max\|delta\|` | Mean, mean absolute, root mean square and maximum absolute slack change B - A, i.e. distance from the y = x line. |
| `violator recall` | Of the endpoints violating in B, the fraction already violating in A (over all endpoints). |
| `violator precision` | Of the endpoints violating in A, the fraction still violating in B (over all endpoints). |

They are printed by `compare` and `track`, shown in the HTML stats, and
the `track` index has Spearman, top agreement and MAE columns for every step
transition.

Times are shown in `--unit` (default ns) with a fixed number of digits after
the decimal point (3 for ns, 1 for ps, or `--digits`), in a fixed-width font
in the HTML.
Slack changes smaller than half the last displayed digit (0.5 ps with the
default ns and 3 digits), or `--tolerance` in `--unit`, count as unchanged
for the improved/degraded counts, the tables of most degraded and improved
endpoints and the `track` row colors. Otherwise numerical noise, e.g. a few
femtoseconds between `5_1_grt` and `5_2_route`, shows up as changes that
display as 0.

`--worst N` restricts the endpoints in both to the union of the worst N
endpoints of A and of B, to focus on the critical part of the design.

The HTML is self-contained (no network access needed). It has:

- WNS, TNS and violation counts of both steps;
- a scatter of endpoint slack with a y = x line, where above the line means
the endpoint improved. It is drawn on a canvas so it handles hundreds of
thousands of endpoints. Drag to zoom, double-click to reset, hover for
the endpoint name;
- a setup/hold toggle;
- tables of the most degraded and most improved endpoints, excluding
endpoints with positive slack in both steps, and of the endpoints only in
one step.

`track --html DIR` writes the same page for every step and its successor
(`<step>__<next step>.html`, with previous/next links) and `DIR/index.html`,
a table of every transition with WNS/TNS and the improved, degraded, newly
failing and newly passing counts for setup and hold. Endpoints with positive
slack in both steps are not considered. Transitions where no considered
endpoint changed (e.g. `2_2_floorplan_macro` to `2_3_floorplan_tapcell`) are
greyed out, and transitions where every considered endpoint improved, for
setup and hold, are green.

For other analyses, import the module (e.g. from a notebook):
`load_snapshot()`, `load_dir()`, `summary()`, `compare()`, `movement()`,
`metrics()` and `spearman()`
return plain Python dicts and lists.

## Testing

`flow/test/test_endpointSlack.py` covers loading and comparison with
synthetic snapshots and runs in the util CI job:

``` shell
python3 flow/test/test_endpointSlack.py
```
24 changes: 20 additions & 4 deletions docs/contrib/Metrics.md
Original file line number Diff line number Diff line change
Expand Up @@ -47,12 +47,28 @@ check did not run. Read the `[WARN]` lines to see which. Pass `--strict` to
`checkQorMetrics.py` to get distinct exit codes instead (2 inconclusive,
3 unreachable).

Two environment variables shape the comparison:
The check runs as the commit `metadata.json` records. The dashboard searches
its default baseline pipelines in order and takes a `master` build that has the
design: the one at the commit's merge base with `master`, otherwise the latest
one before the commit. A commit on `master` is its own merge base, so a run of
a `master` commit, such as a downloaded CI artifact, is compared against that
commit's own build. A commit not yet pushed has no merge base on GitHub, so it
is compared against the latest `master` build before it. Without a commit the
run is compared against the latest `master` build.

These environment variables shape the comparison:

- `DASHBOARD_API_KEY` grants access to private platforms. Without it, a
private design reports as inconclusive, not as an authentication error.
- `DASHBOARD_JOB_NAME` names the Jenkins pipeline whose `master` builds are the
baseline. The default is `OpenROAD-flow-scripts-Public`.
private design has no baseline and reports as inconclusive, not as an
authentication error.
- `DASHBOARD_JOB_NAME` checks the run as a build of that CI pipeline instead,
with the pipeline's rules for the branch checked out in this repository: the
previous build on a trunk branch such as `master`, the merge base on any
other branch. A CI job, whose checkout has no branch, also sets
`DASHBOARD_BRANCH` and `DASHBOARD_COMMIT` (or passes `--branch` and
`--commit`).
- `DASHBOARD_API_URL` (`--api-url`) points the check at another deployment and
takes precedence over `--beta`.

If you only changed synthesis, you can gate a synthesis-only run, without
running the rest of the flow. Only the `synth__` and `constraints__` metrics
Expand Down
2 changes: 2 additions & 0 deletions docs/toc.yml
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,8 @@ entries:
title: Guide to Integrate a New Platform into the OpenROAD Flow
- file: contrib/CI.md
title: CI Guide
- file: contrib/EndpointSlackTracking.md
title: Tracking Endpoint Slack Across Flow Steps

- file: contrib/CODE_OF_CONDUCT.md
title: Code of Conduct
Expand Down
Loading
Loading