.forgejo/workflows/benchmark-scheduled.yml

@@ -22,7 +22,7 @@ env:
 
 jobs:
     benchmark-regression:
-        if: github.event_name == 'schedule' && github.event.schedule == '0 2 * * *' || github.event_name == 'workflow_dispatch' && github.event.inputs.run_full_suite == 'false'
+        if: forgejo.event_name == 'schedule' && forgejo.event.schedule == '0 2 * * *' || forgejo.event_name == 'workflow_dispatch' && forgejo.event.inputs.run_full_suite == 'false'
         runs-on: docker
         timeout-minutes: 120
         container:
@@ -67,7 +67,7 @@ jobs:
             - name: Run benchmark regression via nox
               env:
                   NOX_DEFAULT_VENV_BACKEND: uv
-                  ASV_BASE_SHA: ${{ github.event.inputs.base_sha || 'master' }}
+                  ASV_BASE_SHA: ${{ forgejo.event.inputs.base_sha || 'master' }}
               run: |
                   mkdir -p build
                   nox -s benchmark_regression 2>&1 | tee build/nox-benchmark-regression-output.log
@@ -107,7 +107,7 @@ jobs:
                   retention-days: 90
 
     benchmark-full:
-        if: github.event_name == 'schedule' && github.event.schedule == '0 3 * * 0' || github.event_name == 'workflow_dispatch' && github.event.inputs.run_full_suite == 'true'
+        if: forgejo.event_name == 'schedule' && forgejo.event.schedule == '0 3 * * 0' || forgejo.event_name == 'workflow_dispatch' && forgejo.event.inputs.run_full_suite == 'true'
         runs-on: docker
         timeout-minutes: 180
         container:

.forgejo/workflows/master.yml

@@ -51,8 +51,26 @@ jobs:
 
             - name: Run asv continuous via nox
               env:
-                  ASV_BASE_SHA:  ${{ steps.hash.outputs.ASV_BASE_SHA }}
+                  ASV_BASE_SHA: ${{ steps.hash.outputs.ASV_BASE_SHA }}
+                  ASV_S3_BUCKET: ${{ secrets.ASV_S3_BUCKET }}
+                  AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
+                  AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
               run: |
+                  mkdir -p build/asv/results
+
+                  # Check whether S3 baseline data exists before running benchmarks
+                  HAS_BASELINE=false
+                  if [ -n "${ASV_S3_BUCKET}" ] && [ -n "${AWS_ACCESS_KEY_ID}" ]; then
+                      python -m pip install -q awscli
+                      aws s3 ls "s3://${ASV_S3_BUCKET}/asv/results/" >/dev/null 2>&1 && HAS_BASELINE=true || true
+                  fi
+
+                  if [ "${HAS_BASELINE}" = "false" ]; then
+                      echo "Benchmark regression skipped: no S3 baseline results available to compare against."
+                      mkdir -p build/asv/html
+                      exit 0
+                  fi
+
                   nox -s benchmark_regression
 
             - name: Archive the results

CHANGELOG.md

@@ -85,16 +85,6 @@ Changed `wf10_batch.robot` to be less likely to create files, and
 
 - **A2A module rename BDD test suite** (#8615): Comprehensive Behave tests validating that the ACP→A2A module rename is complete — verifying all 22 A2A symbols are properly exported, no legacy ACP references remain in `.py` files under `cleveragents.a2a/`, and the module docstring uses current A2A naming. The step definitions include self-contained symbol lookups to avoid cross-scenario dependency failures.
 
-- Fixed `ReactiveEventBus.emit()` exception handler to log the full exception
-  message (`str(exc)`) and enable traceback forwarding (`exc_info=True`).
-  Previously the handler logged only the exception type name (e.g.
-  "ValueError") with no diagnostic detail, making production debugging
-  impossible. The handler now includes the error message text and full
-  traceback in the structlog warning entry. Removed `@tdd_expected_fail` tag
-  from the TDD test so both scenarios run as normal regression guards. (#988)
-
-### Added
-
 - **`pr-review-worker` review-started notification** (#11028): The `first_review`
   and `re_review` modes now post a "review started" notification comment to the
   PR at the beginning of the review, giving PR authors immediate visibility
@@ -104,6 +94,15 @@ Changed `wf10_batch.robot` to be less likely to create files, and
 - **Plan Rollback Command** (#8557): Implemented `agents plan rollback <plan-id> [<checkpoint-id>]` for checkpoint-based plan state restoration in Epic #8493. The command restores a plan's sandbox to the state captured at a given checkpoint, discarding all decisions made after that checkpoint. The checkpoint can be specified as an optional positional second argument or via the `--to-checkpoint` named option. Supports `--yes/-y` flag to skip confirmation prompts and `--format/-f` for output format selection (rich/plain/json/yaml). Included with comprehensive BDD test coverage (>= 97%) and spec-aligned output formatting showing rollback summary, changes reverted, impact analysis, and post-rollback state panels.
 
 ### Fixed
+
+- Fixed `ReactiveEventBus.emit()` exception handler to log the full exception
+  message (`str(exc)`) and enable traceback forwarding (`exc_info=True`).
+  Previously the handler logged only the exception type name (e.g.
+  "ValueError") with no diagnostic detail, making production debugging
+  impossible. The handler now includes the error message text and full
+  traceback in the structlog warning entry. Removed `@tdd_expected_fail` tag
+  from the TDD test so both scenarios run as normal regression guards. (#988)
+
 - **Guard cleanup_stale against execute/processing and execute/complete plans** (#11121):
   ``_create_sandbox_for_plan()`` in ``src/cleveragents/cli/commands/plan.py`` now
   skips ``GitWorktreeSandbox.cleanup_stale()`` when the plan is in