Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
19 commits
Select commit Hold shift + click to select a range
75ed5aa
chore: record implementation plan
Copilot Oct 19, 2026
fadca6a
feat(evals): add product task effectiveness comparisons
Copilot Oct 19, 2026
ed45e8f
fix(evals): require shipping artifact for baseline
Copilot Oct 19, 2026
9e22d6c
Merge master into copilot/extend-evals-into-product-wide-effectiveness
ScriptedAlchemy Oct 20, 2026
1325f78
Merge branch 'master' into copilot/extend-evals-into-product-wide-eff…
ScriptedAlchemy Oct 20, 2026
cfd7dea
Merge branch 'master' into copilot/extend-evals-into-product-wide-eff…
ScriptedAlchemy Oct 20, 2026
542b86c
Merge branch 'master' into copilot/extend-evals-into-product-wide-eff…
ScriptedAlchemy Oct 21, 2026
224d5fd
Merge branch 'master' into copilot/extend-evals-into-product-wide-eff…
ScriptedAlchemy Oct 21, 2026
b7a633f
fix(evals): verify outcomes and equalize edit capabilities
ScriptedAlchemy Oct 21, 2026
1b29a6d
fix(evals): preserve selected inputs and resource costs
ScriptedAlchemy Oct 21, 2026
1dc8c4b
Merge branch 'master' into copilot/extend-evals-into-product-wide-eff…
ScriptedAlchemy Oct 21, 2026
5803bae
Merge branch 'master' into copilot/extend-evals-into-product-wide-eff…
ScriptedAlchemy Oct 21, 2026
8a40ff2
test(hooks): verify first edits through held worktree publication
ScriptedAlchemy Oct 21, 2026
5d0f61f
test(hosts): identify cache relocation mismatches
ScriptedAlchemy Oct 21, 2026
d143d0e
fix(hooks): expose exact durable edit admission receipts
ScriptedAlchemy Oct 21, 2026
8da41a3
fix(hooks): keep edit filenames out of admission logs
ScriptedAlchemy Oct 21, 2026
99dde4e
test(hooks): check worktree bindings after publication release
ScriptedAlchemy Oct 21, 2026
52fe6e0
Merge branch 'master' into copilot/extend-evals-into-product-wide-eff…
ScriptedAlchemy Oct 21, 2026
185991e
fix(memory): size admission atomically and preserve blocked progress
ScriptedAlchemy Oct 21, 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
3 changes: 3 additions & 0 deletions .github/workflows/hermetic-evals.yml
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@ jobs:
run: |
bash -n evals/hermetic/run.sh
bash -n evals/agent_adoption/run.sh
bash -n evals/agent_adoption/claude_tools.sh
bash -n scripts/build-eval-binary.sh
- name: Run scorer and shell-runner regressions
run: >-
Expand All @@ -46,3 +47,5 @@ jobs:
//evals/agent_adoption:selftest
//scripts:build_eval_binary_test
--test_output=errors
- name: Execute stock-edit oracle regressions
run: python3 evals/agent_adoption/stock_check_selftest.py
Comment thread
ScriptedAlchemy marked this conversation as resolved.
Resolved
37 changes: 37 additions & 0 deletions crates/tracedecay-agent-hosts/src/agents/claude/tests.rs
Original file line number Diff line number Diff line change
Expand Up @@ -148,6 +148,43 @@ fn native_cache_content_drift_and_binary_relocation_require_refresh() {
.unwrap()
);
copy_rendered_bundle_to_native_cache(home.path(), new_bin);
let rendered = rendered_plugin_files(new_bin, &ServeArgs::default()).unwrap();
let relatives = rendered
.iter()
.map(|(relative, _)| (*relative).to_string())
.collect::<Vec<_>>();
for root in [
plugin_deploy_dir(home.path()),
claude_current_cached_plugin_root(home.path()),
] {
for (relative, expected) in &rendered {
let path = root.join(relative);
let actual = std::fs::read(&path).unwrap();
assert!(
actual == expected.as_bytes(),
"relocated bundle differs at {}: actual bytes={}, expected bytes={}, first differing byte={:?}",
path.display(),
actual.len(),
expected.len(),
actual
.iter()
.zip(expected.as_bytes())
.position(|(actual, expected)| actual != expected)
);
}
assert_eq!(
super::super::unexpected_bundle_entrypoints(
&root,
&relatives,
&[".claude-plugin", "agents", "commands", "hooks", "skills"],
)
.unwrap(),
Vec::<String>::new(),
"relocation left auto-discovered entries in {}",
root.display()
);
}
assert!(claude_plugin_registration_is_active(home.path()).unwrap());
assert!(
claude_plugin_is_natively_active(home.path(), Some((new_bin, &ServeArgs::default())))
.unwrap()
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -300,8 +300,7 @@ pub use serving::{
use serving::{
CodeIndexCommittedProgressSampleV1, CodeTextProjectionSlotV1, map_sealed_page_source_error,
sha256_private_file_and_size, text_artifact_admitted_build_budget,
text_artifact_builder_budget, text_artifact_resident_memory_charge,
text_artifact_source_batch_limits,
text_artifact_builder_budget, text_artifact_source_batch_limits,
};
#[cfg(test)]
use tracedecay_query::retrieval::ports::TEXT_ARTIFACT_PAGE_CHUNKS_V1;
Loading
Loading