mirror of
https://github.com/dotnet/skills.git
synced 2026-09-20 09:49:54 +08:00
fix-dotnet-test-analysis-scripts
354 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 leslierichardson95
|
10331dbf09 |
Cut mcp-csharp-debug skill (#938)
Remove the mcp-csharp-debug skill and its eval tests. Per the dotnet-ai skills-eval (#889) and telemetry review, the skill had weak eval impact (+0.27) and thin real-world adoption (3 users, 0 with >=5 invocations), making it a cut candidate rather than a strengthen target. - Delete plugins/dotnet-ai/skills/mcp-csharp-debug/ - Delete tests/dotnet-ai/mcp-csharp-debug/ - Remove CODEOWNERS entries for the skill and its tests - Remove dangling references (frontmatter DO NOT USE FOR, Stop Signals, Related Skills) from mcp-csharp-create, mcp-csharp-test, mcp-csharp-publish - Update skill-validator doc example to a surviving skill Refs dotnet/skills#889 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 6a8ce111-58e5-48a7-9f7f-8de972bdc693 |
||
|
Amaury Levé
|
71414ce000 |
Improve dotnet-test eval coverage and efficiency (#917)
* Improve dotnet-test eval coverage and efficiency Address remaining high-confidence items from #899 by bounding the code-testing pipeline and adding eval coverage for grade-tests and find-untested-sources. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: e430fee9-d3df-4ef5-85a4-745ae4b17046 * Fix dotnet-test eval activation and quality Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 9c5c1a52-4f99-49d6-b503-1bec713a6e98 * Strengthen dotnet-test skill activation Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 9c5c1a52-4f99-49d6-b503-1bec713a6e98 |
||
|
Amaury Levé
|
5fff8f1022 |
Improve dotnet-test-migration skill signal (#929)
* Improve migration skill eval signal Trim unnecessary xUnit-to-MSTest workflow turns and make MSTest v1/v2 migration preserve the detected test platform. Add focused cost and activation-boundary eval coverage for issue #900. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 860bd5ec-3bee-44ec-8fad-1bdcc745b9e1 * Strengthen migration evaluation signal Use the first evaluation's per-trial evidence to remove an inert scenario, cover semantic assertion migration, broaden MSTest risk guidance, and make testsettings migration objective. Also fix the MSTest 4.1/Test SDK compatibility rule and add a fast path to reduce retry-heavy migrations. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 860bd5ec-3bee-44ec-8fad-1bdcc745b9e1 * Fix migration eval review findings Move the sequence grader into its matching stimulus, positively require element-wise comparison, and make runsettings XML checks tolerant of casing and whitespace. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 860bd5ec-3bee-44ec-8fad-1bdcc745b9e1 * Strengthen migration eval execution signal Convert weak advice-only scenarios into verified migrations, require test discovery and complete framework state, and correct misleading migration mappings found in eval replay. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 06f10e04-4c49-40c3-b663-69be4525e4cb --------- Copilot-Session: 860bd5ec-3bee-44ec-8fad-1bdcc745b9e1 Copilot-Session: 06f10e04-4c49-40c3-b663-69be4525e4cb |
||
|
luisquintanilla
|
4516118b23 |
Trim technology-selection skill via gated progressive disclosure
Cuts SKILL.md from 355 to 101 lines and moves per-branch depth into references/ (classic-ml, llm, agentic, rag), read only when writing implementation code. Removes the Step 6 `dotnet build -warnaserror` + `dotnet test` mandate that induced build-fix-rebuild loops -- the root cost driver flagged in #889 (measured: 1.56M tok / 46 turns / 8 builds vs a 220K no-skill baseline on the LLM stimulus). Selected by offline head-to-head Vally runs (runs=3, two model families), not guessed. Versus the current skill: plan-only cost cut ~3-4.5x, eliminates the sk- key leak, best reliability 16/18 on haiku, -37% tokens on the LLM task on GPT, and zero task regression on either family. A cheaper single-file trim was rejected because its judge score dropped to 0/3 and it still leaked sk-. Frontmatter description is unchanged so discovery is held constant (Call% already 100%). Part of #889 (the dotnet-ai portfolio tracker): this implements the TRIM-COST (P1) "address first" item for technology-selection only. The four mcp-csharp-* skills tracked in #889 remain separate work. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: a78b17bd-5e28-4e85-b248-38626ebb5eee |
||
|
Abhitej John
|
30897983e8 | Merge branch 'main' into fix/claude-code-lsp-schema | ||
|
YuliiaKovalova
|
b39a041ed0 |
Strengthen dotnet-template-engine skills per cross-family eval (#898) (#904)
* Strengthen dotnet-template-engine skills per cross-family eval (#898) Cross-family skill eval (issue #898) flagged 5 of 6 skills as STRENGTHEN ("mostly ties - too generic/non-prescriptive") and template-instantiation as KEEP-POLISH. Invocation is already ~100% and token overhead is a penalty, so these edits add decisive, opinionated OUTPUT requirements (not volume). All skills remain in the recommended "detailed" tier. - template-validation: require a one-line verdict header + single findings table, and a concrete fix for every ERROR/WARNING. - template-smart-defaults: require a "Defaults applied" log + the exact single dotnet new command line (only flags actually passed). - template-comparison: require a decisive Recommendation verdict and add opinionated decision shortcuts for canonical template pairs. - template-discovery: lead the answer with a ready-to-run command line. - template-authoring: require a complete template.json + a conventions-preserved confirmation table. - template-instantiation: add a lean "match the workspace, then stop" directive to cut the excess turns/tokens flagged for the Opus gap. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * Address PR review: remove template-specific AOT claims, narrow authoring validation routing - template-smart-defaults: reword the AOT note, rules row, and pitfall so they no longer claim --aot is unavailable on webapi/webapp (dotnet new webapi --aot exists since .NET 8 and template-instantiation references it). Now say --aot is present only where dotnet new <template> --help lists it, without naming specific templates as unsupported. - template-authoring: narrow the frontmatter DO NOT USE to standalone validation (use template-validation) and align the When-to-Use bullet, so it no longer contradicts the body, which validates as a step during authoring. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * Address PR review: keep Defaults-applied Source strictly user|rule The sample row used 'rule (AOT)', which made the Source column look free-form. Set it to 'rule' and moved the AOT context into the Why column, matching the guidance that Source is strictly user or rule. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * Address PR review: tighten discovery description, make comparison AOT row conditional - template-discovery: simplify the redundant 'two or more templates against each other' phrasing to 'comparing templates side by side' and rewrap so each '(use <skill>)' stays with its clause. - template-comparison: reword the example AOT row so it is conditional on what 'dotnet new <template> --help' exposes instead of asserting webapi has no --aot (which contradicted template-instantiation). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * Address PR review: align find/compare routing between frontmatter and body - template-discovery: narrow the frontmatter exclusion to a *detailed* side-by-side comparison (use template-comparison), matching the body which supports light comparison but routes detailed comparisons away. - template-instantiation: split the frontmatter 'finding or comparing' exclusion into finding (template-discovery) vs detailed comparison (template-comparison), and align the When-Not-to-Use bullet accordingly. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * Address PR review: mention validation in template-authoring description The description said only 'Guides creation' while the skill validates the template it authors (intro + Step 2). Restored 'creation and validation' and added a USE FOR entry for validating the template.json you are authoring, while keeping standalone validation routed to template-validation in DO NOT USE. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * Address PR review: mention high-level compare in discovery; clarify defaults log scope - template-discovery: description now says 'find, inspect, and compare (at a high level)' so it isn't under-scoped vs the body (detailed side-by-side still routes to template-comparison via DO NOT USE). - template-smart-defaults: clarify the 'Defaults applied' log has one row per parameter covering both preserved user values (Source=user) and rule-applied defaults (Source=rule). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * Address PR review: symmetric AOT cell + clarify clean verdict - template-comparison: make the webapp AOT cell reference 'dotnet new webapp --help' so it is symmetric with the webapi cell and unambiguous. - template-validation: the 'Ready to publish' verdict now says '0 errors, 0 warnings' and notes optional suggestions may still apply, instead of 'clean'. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * Address PR review: allow line:col location for JSON parse errors Widened the findings-table Location column to 'JSON path or line:col' and added an example parse-error row, so the required table can represent the JSON parse errors that Step 2 asks to report with a line number. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * Improve template-discovery resilience: answer before any dotnet new call Eval investigation (PR #904 results, run 29503063336) showed template-discovery scoring 1.0-2.0 on Opus because sessions died with '(no output)' after a 'persistence'/'mutex' error from concurrent dotnet new calls. When the session survived, the same content scored 4.0-4.3. The failing runs invoked the skill then ran 'dotnet new --help' as the first/last action and the mutex error left the turn empty. Make answer-first an imperative rule: write the recommendation and ready-to-run command from the intent mapping BEFORE running any dotnet new command, and never end the turn on a dotnet new call. This makes the answer survive the mutex error (and gives users a faster answer). Skill stays in the 'detailed' token tier. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * Iterate on eval quality: shadow-verb shortName warning + discovery resilience From PR #904 eval run 29509140219: - template-validation & template-authoring: add a WARNING tier for shortNames that *shadow* a well-known top-level dotnet verb (build/run/test/publish/pack/clean/ restore). These do NOT technically conflict with dotnet new (correctness kept), but 'dotnet new build' is easily confused with 'dotnet build', so it warrants a warning + a distinctive-name suggestion. This is a genuine authoring footgun and also resolves the 'Validate a template.json file' scenario where the agent was penalized for correctly saying shortName 'build' is fine. - template-discovery: require the pre-CLI answer to be complete and standalone (never end on a 'let me confirm from the CLI…' teaser, which the mutex error was truncating), and add a dry-run-failure fallback (describe expected files from template knowledge) so preview requests never return empty. Skill stays 'detailed'. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * Rubber-duck follow-up: revert eval-gaming, fix real defects Independent review + empirical checks (dotnet new build/restore/list --help; EvaluateCommand.cs Task.WhenAll) confirmed: - The mutex '(no output)' deaths come from the validator running Baseline+Isolated +Plugin concurrently, not cross-skill parallelism — eval.yaml can't fix it. - build/restore/test do NOT conflict with dotnet new (only real subcommands like 'list' do), so the shortName-shadow WARNING added last commit was appeasing a factually-wrong rubric (and the 'restore' entry contradicted the validation eval). Changes: - Revert the shortName-shadow WARNING in template-validation and template-authoring (the skills were already correct; do not game an incorrect rubric). - template-discovery: fix a real mapping bug — 'windows auth' mapped to SingleOrg; it is --auth Windows. Split azure ad/entra (SingleOrg) from windows auth (Windows). - template-discovery: tighten the dry-run-failure fallback to give only a representative structure and forbid inventing specific parameter values/choices/ file paths (avoids confident hallucination), keeping the 'answer-first, never end on a teaser' resilience. Skill stays in the detailed token tier. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * Address PR review: fix validation findings-table example (real subcommand + line:col) - Use a real dotnet new subcommand ('list') in the ERROR example instead of 'restore' (which does not conflict), matching the corrected shortName rules. - Make the parse-error location example '12:5' match the 'line:col' column header. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * Address PR review: consistency fixes across three skills - template-authoring: add ExcludeAssets to the conventions-preserved table (the workflow above lists it, so include it to avoid implying partial carry-over). - template-discovery: add SingleOrg to the example --auth choices so options aren't under-reported. - template-validation: broaden the concrete-fix requirement to allow a specific edit instruction (e.g. 'remove the trailing comma'), matching the parse-error example. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * Fix incorrect eval rubrics: shortName 'build'/'restore' are not dotnet new conflicts The 'Validate a template.json' (authoring) and 'Validate template with multiple errors' (validation) scenarios used shortName 'build'/'restore' and asserted they conflict with dotnet new. Verified empirically they do NOT (dotnet new build/ restore --help treat them as template-name lookups; only real subcommands like 'list'/'search' intercept). The skills correctly report this, so the wrong rubrics were penalizing correct behavior and causing regressions. Change both fixtures to shortName 'list' (a real dotnet new subcommand that genuinely conflicts) and update the rubric/assertion wording accordingly, so the eval tests correct behavior. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * template-discovery: faithful dry-run output + built-in package guidance Fresh eval (run 29581297999) confirmed the earlier rubric fix worked (authoring Validate 4.3->5.0). Two repeatable clean-output defects remained in template-discovery (seen in surviving Plugin runs, not just mutex deaths): - Preview: the agent summarized/regrouped the dry-run output and invented files (e.g. ReconnectModal), and didn't explain key files. Now: present the actual dry-run file list faithfully (no summarizing/inventing) and give a one-line purpose for key entry points. - Search: for a built-in template the agent never clearly answered 'which package to install'. Now: name the exact package, or say 'no install needed - ships with the SDK' for built-in templates. Compressed the resilience note to keep the skill in the detailed token tier. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * Reduce eval overfitting: outcome-focused rubrics + de-cued prompts The overfitting judge flagged moderate overfit on smart-defaults (0.45), comparison (0.34), and instantiation (0.28). Per its per-element analysis (assertions were all 'broad'/fine), make the rubrics/prompts outcome-focused: - Drop every 'The agent used the template-* skill' rubric item (tests activation, not outcome — expect_tools already enforces skill usage as a hard gate). - Reword skill-vocabulary items (e.g. 'native AOT needs a recent AOT-capable TFM', 'smart defaults only fill gaps') and skill-method items ('verify against dotnet new --help', 'inspected via --help', 'logged each applied default', 'verified the project was created') into result-focused criteria that any valid approach satisfies. - De-cue the three smart-defaults prompts that mirrored the skill's 'Required Output B' verbatim ('output the exact single dotnet new command line ... only the flags you will actually pass'); they still elicit a concrete command so the negative assertions remain meaningful. - Drop the blazor prompt's 'Inspect both with dotnet new --help' methodology cue. Assertions and expect_tools are unchanged, so activation and correctness are still verified — the eval now measures outcomes instead of parroting. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * template-smart-defaults: defer --help to creation time (trim advice-only cost) Eval run 29586558625 showed the advice-only AOT scenario tie at 4.0 but the skilled run cost 45.7k tokens / 3 turns vs baseline 12.7k / 1 turn — driven entirely by running 'dotnet new worker --help' (feeding ~30k tokens of help output into context) just to advise, which flipped the weighted score negative. Make --help confirmation a creation-time step: for advice-only requests, answer from the rules and note names are confirmed at creation, rather than spending a --help call to advise on well-known parameters. The quality wins come from the decisive output (defaults log + exact command), not from --help, so quality holds while cost drops. Addresses the #898 TRIM-COST concern. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * Address PR review: workspace-framework precedence + sync eval.vally.yaml - Precedence conflict (instantiation 'mirror workspace framework' vs smart-defaults 'latest AOT-capable when --framework unset'): treat the workspace framework discovered in Step 2 as an explicit --framework value that smart-defaults must not override; deviate only when incompatible with a requested feature (then flag it). Added a matching note to the smart-defaults AOT rule (a framework pinned by the workspace/global.json counts as set). - Synced eval.vally.yaml (cross-family harness) with the eval.yaml changes that had drifted: outcome-focused rubrics + de-cued prompts for smart-defaults/comparison/ instantiation, and the shortName build/restore -> list fixture+rubric fix for authoring/validation (including the referenced fixture template.json files). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 * Assert required skill outputs with broad checks (address review) Reviewer flagged that the outcome-focused rubric rewrite left several scenarios without any assertion of the skill's required outputs. Add broad (non-overfitting) assertions in eval.yaml and eval.vally.yaml: - smart-defaults (all 4 scenarios): assert a 'dotnet new' command line is present (output B) and a markdown table is present (the 'Defaults applied' log, output A). - comparison (webapi/webapp, blazor): assert a recommendation is present. - validation (multiple errors): assert a verdict summary (Not ready / N errors) and a findings table are present. - authoring (validate): assert the agent flagged that shortName 'list' conflicts. These are broad presence checks (any valid phrasing passes), so they verify the required output without re-introducing the overfitting the rubric rewrite removed. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 0dadc452-fb69-49aa-9631-1b86647d83b9 --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
4df4da469a |
Upgrade agentic workflows and fix stale PR cleanup (#916)
* chore: upgrade gh-aw runtime * fix: paginate stale pull request cleanup Upgrade the generated agentic workflow assets and ensure stale PR discovery includes every result page and draft pull requests. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 968a22c2-327f-4d26-8f86-1c59bcd323ea * Improve dotnet-test eval coverage and efficiency Address remaining high-confidence items from #899 by bounding the code-testing pipeline and adding eval coverage for grade-tests and find-untested-sources. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: e430fee9-d3df-4ef5-85a4-745ae4b17046 * fix: address agentic workflow review Pin the Copilot setup checkout action and include the cutoff date in stale PR search results. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 968a22c2-327f-4d26-8f86-1c59bcd323ea * Improve test migration skill guidance Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 5e19d263-02a6-45b1-9cfb-424fa4d10863 * fix: add fixture namespace imports Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: a464e6e4-3e45-41fe-b17d-887c8cb8a448 * test: assert GetOrderById grade Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: a464e6e4-3e45-41fe-b17d-887c8cb8a448 --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Jan Krivanek
|
1b99afac59 |
Fix dotnet-msbuild skill eval regressions and coverage gaps (#896) (#910)
* Fix dotnet-msbuild skill eval regressions and coverage gaps (#896) Addresses the cross-family evaluation findings in #896. P0: - eval-performance: add diagnostic-first framing + explicit stop-conditions and gate prescriptive fixes on measurement, to stop over-application regressions. - msbuild-antipatterns: rewrite description with an action-verb lead and concrete trigger phrases to fix low invocation (FIX-DISCOVERY). P1: - Add cross-family eval.vally.yaml for extension-points, item-management, property-patterns, and target-authoring (previously excluded from the matrix). - check-bin-obj-clash: trim 465 -> 315 lines, removing the redundant text-log fallback steps, duplicate example workflow, and verbose tips (TRIM-COST). P2: - build-parallelism: add an opinionated 'start here' critical-path checklist. - binlog-generation: add one-build-one-binlog rule and a verify step. Keeps the plugin under the 15,000-char rendered skill-menu budget (14,981 -> 14,873). * Address PR review: portable grep whitespace + per-project eval count; shell-labeled binlog verify commands (#896) - check-bin-obj-clash: use [[:space:]] instead of non-portable \s in ERE; replace 'grep -c' note with an accurate per-project uniq -c count. - binlog-generation: label verify commands by shell and add the Windows cmd (dir /b) equivalent instead of mislabeling ls as cmd. * Address PR review round 2: full PowerShell -m command; match quoted project path in per-project eval count (#896) - build-parallelism: spell out 'dotnet build -m -bl:{{}}' for PowerShell so the -m flag isn't dropped. - check-bin-obj-clash: match the full quoted project path (not just filename) so same-named projects in different dirs stay distinct and paths with spaces work. |
||
|
Amaury Levé
|
0ca7f8921d |
Fix migrate-static-to-wrapper DateTimeKind regression (#899) (#906)
The replacement mapping instructed models to convert TimeProvider's DateTimeOffset back to DateTime via .DateTime, which yields Kind=Unspecified and silently changes behavior vs the original DateTime.UtcNow (Utc) / DateTime.Now (Local). The eval rubric penalizes exactly this behavioral change, a likely cause of the frontier-model regression flagged in the dotnet-test scorecard. Use .UtcDateTime / .LocalDateTime to preserve Kind, and add a guardrail plus validation/pitfall notes about matching the target member type and not forcing DateTime through DateTimeOffset. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 69261256-256e-4e4c-9bdc-932d5ca8e5df |
||
|
Viktor Hofer
|
b83443ac1e |
Document SetTargetFramework bin/obj clash on single-targeting ProjectReferences (#853)
* Document SetTargetFramework bin/obj clash on single-targeting ProjectReferences Setting SetTargetFramework metadata on a ProjectReference to a non-multi-targeting project injects a path-neutral TargetFramework global property, forking a redundant project instance that shares the same OutputPath/IntermediateOutputPath as the solution-rooted build. The project is built twice, causing a bin/obj clash under parallel builds. Adds AP-23 to the msbuild-antipatterns catalog and a matching Common Causes and Fixes section plus global-properties note to the check-bin-obj-clash skill. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Clarify SetTargetFramework: same-TFM clash vs legitimate overrides Refine AP-23 and the check-bin-obj-clash guidance to reflect two additional cases: (1) the clash only occurs when the injected TFM equals the single-targeting project's own TFM (path-neutral); injecting a DIFFERENT TFM changes the output path and is a valid override, and (2) for framework-incompatible references (e.g. .NETFramework test project -> single-targeting .NETCoreApp), SkipGetTargetFrameworkProperties=true and ReferenceOutputAssembly=false are also required. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Generalize incompatible-TFM ProjectReference guidance SkipGetTargetFrameworkProperties=true and ReferenceOutputAssembly=false are required whenever the referencing and referenced projects target incompatible frameworks, independent of single- vs multi-targeting and independent of SetTargetFramework. Decouple that rule from the SetTargetFramework override case in both AP-23 and the check-bin-obj-clash skill. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Note TargetFramework leak when SkipGetTargetFrameworkProperties is set When SkipGetTargetFrameworkProperties=true bypasses P2P negotiation, the referencing project's TargetFramework global property can flow into a single-targeting referenced project and build it under the wrong TFM/output path. Guard with either SetTargetFramework (pin) or UndefineProperties=TargetFramework (strip), not both. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add eval coverage for SetTargetFramework bin/obj clash (AP-23) check-bin-obj-clash: extend ClashTest with a single-targeting ToolLib and a ConsumerApp that references it with redundant same-TFM SetTargetFramework, forking a second ToolLib instance that builds to the same bin/obj (verified: ToolLib builds twice). Adds rubric items for identifying and fixing it. msbuild-antipatterns: LibB now references LibA with redundant same-TFM SetTargetFramework; adds a rubric item for detecting AP-23 in the static review scenario. Both eval.yaml and eval.vally.yaml updated. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Viktor Hofer <vihofer@users.noreply.github.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
YuliiaKovalova
|
9c7436b949 |
Add copy-to-output-directory MSBuild skill (IfDifferent / SkipUnchangedFilesOnCopyAlways) (#883)
* Add copy-to-output-directory MSBuild skill Adds a focused dotnet-msbuild skill documenting how to choose a CopyToOutputDirectory / CopyToPublishDirectory mode, including the `IfDifferent` mode and the `$(SkipUnchangedFilesOnCopyAlways)` property introduced in MSBuild 17.13 / .NET SDK 9.0.2xx (dotnet/msbuild#11052). Covers mode semantics (Never/PreserveNewest/Always/IfDifferent), why `Always` is a per-build perf hit, the SkipUnchangedFiles timestamp+size comparison, transitive copy through ProjectReference, and version requirements. Registers the skill in the msbuild, msbuild-code-review, and build-perf agent routing lists. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 881d26ad-87b7-48e3-8ec6-043163944437 * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Address review feedback on copy-to-output-directory skill - Soften the IfDifferent description to avoid overclaiming: it skips when "unchanged per MSBuild's heuristic" (timestamp + size, not a content hash), rather than "identical"/full Always equivalence. - Correct the target-flow wording: the three copy targets run as dependencies of _CopySourceItemsToOutputDirectory (invoked by CopyFilesToOutputDirectory). - Restore the USE FOR / DO NOT USE FOR routing pattern for the skill's frontmatter description, matching sibling skills. - Reclaim skill-menu budget headroom (per maintainer note) by tightening the verbose property-patterns and target-authoring descriptions; dotnet-msbuild rendered menu is now ~14,897/15,000 chars. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 881d26ad-87b7-48e3-8ec6-043163944437 * Fix article: 'an SQLite' per review Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 881d26ad-87b7-48e3-8ec6-043163944437 --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
79a2ada302 |
Fix dotnet-test plugin timeout + skill activation issues (#875)
* Fix dotnet-test plugin timeout + skill activation issues Activation: - filter-syntax eval: both scenarios set expect_activation: false. The skill is a reference skill (disable-model-invocation/user-invocable false) loaded by run-tests/mtp-hot-reload; it can never self-activate — this was an eval mis-spec, not a skill bug. - writing-mstest-tests 'Fix swapped Assert.AreEqual arguments': expect_activation false. The rubric requires diagnosing the root cause unaided, so no invocation is expected (notActivated 11/11 both arms). - test-smell-detection: relax the over-restrictive 'INVOKE ONLY when explicitly asked for the testsmells.org catalog' guidance so nuanced named-smell reviews with justified severity also activate (both-arm notActivated gap). Funded within the 15k skill-menu budget by compressing redundant framework parentheticals to the compact style already used by sibling skills. Timeout: - run-tests 'Filter xUnit v3 tests by class pattern and trait using query filter language': raise 240 -> 360 (observed peak ~178s, closest to its cap). Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * Address /evaluate: revert test-smell regression, remove untestable filter-syntax eval Log-driven iteration on the eval results (run 29019511076): Priority 1 - regression fix: revert the test-smell-detection description broadening. results.json shows it reliably regressed 'Decline request to write new tests from scratch' (perRunScores [-0.19,-0.10,-0.22]; plugin overallJudgment -0.28, quality 5.0 baseline -> 4.3 skilled) while NOT fixing its target 'Distinguish reasoned skips' (isolated 5.0 vs 5.0 tie failing on judge position-bias, CV=114% - not description-fixable). Net-negative, so restore the pristine description. Priority 3 - remove the structurally-untestable filter-syntax eval. filter-syntax is disable-model-invocation/user-invocable:false, so it can never activate and can never show a skilled-vs-baseline delta - both scenarios fail by construction regardless of expect_activation. Peer reference skills (platform-detection, code-testing-extensions) have NO eval.yaml; filter-syntax was the lone exception. Its filter functionality is already covered by run-tests scenarios (which load filter-syntax as an additional_required_skill). Following precedent, remove the eval rather than leave two permanently-red cases. Kept from the prior commit: run-tests query-filter timeout 240->360 (harmless hard-cap headroom) and writing-mstest 'Fix swapped Assert.AreEqual' expect_activation:false (documents the unaided-by-design scenario and prevents a spurious hard activation failure). Not done - plugin-arm sibling deflections: results.json shows every failing plugin-arm scenario has detectedSkills=[] (NO sibling captured the turn), the rendered menu is under the 15k budget (descriptions are shown), and the verdict failures are dominated by high-variance efficiency noise (CV 60-3000%, several with quality improved). Per docs/InvestigatingResults.md there is no captor to deflect and description edits would not help; with zero budget headroom, adding speculative deflections is unjustified. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * run-tests evals: flip expect_tools:[bash] to reject_tools to fix activation Root cause of run-tests plugin+isolated non-activation (skill_not_activated gate): every run-tests scenario is a 'show me the exact command' knowledge question, yet each carried expect_tools: [bash] — which is an ASSERTION that bash was used. That actively forced the model into empirical exploration (dotnet test --help, trial runs, web_fetch) instead of consulting the run-tests skill, and a clean knowledge-only answer would FAIL the assertion. Evidence from run 29253857976: run-tests failed to activate even in the ISOLATED arm (where it is the only skill loaded) on scenarios as easy as base=1.0 — proof the model was bypassing the skill via bash rather than not needing it. The forced bash use also drove the token/tool/ time overhead that produced the negative efficiency scores, and one scenario hit the 360s timeout doing web exploration. Fix: convert all 15 run-tests scenarios from expect_tools: [bash] to reject_tools: [bash, edit, create]. These scenarios only assert on the recommended command text (output_matches) — none run tests (no run_command_and_assert, no file assertions) — and the model can still inspect fixtures via view/glob. Forbidding bash makes them pure-knowledge comparisons, so the model must reason from knowledge and reaches for the run-tests skill (improving activation in both arms), while removing the tool-induced overhead and timeout risk. This is stricter, not weaker, gating and matches docs/InvestigatingResults.md sec.8. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * Revert run-tests reject_tools change — did not affect activation gate The expect_tools->reject_tools flip was based on a wrong assumption: reject_tools is a POST-HOC scoring assertion only (AssertionEvaluator/BaselineStore), it does NOT remove bash from the agent toolset, so the agent kept using bash and skill activation was unchanged (12 activation-fail arms before AND after, runs 29253857976 vs 29256920057). Reverting to keep the PR minimal and avoid adding failing assertions that don't serve the activation goal. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * writing-mstest 'Fix swapped AreEqual': validate activation instead of waiving it Addresses review feedback (r3551729171): setting expect_activation:false on an in-scope prompt (swapped Assert.AreEqual is explicitly in writing-mstest-tests' USE FOR) masks real routing/activation regressions. The waiver existed only because the task was trivially solvable unaided (baseline 5.0/5, zero delta), so the skill never needed to activate. Fix: make the scenario genuinely skill-dependent so activation is expected and validated. The prompt now also asks which analyzer catches this and how to enable it — skill-specific MSTest knowledge (SKILL.md Step 8: MSTEST0017 + MSTest.Analyzers packaging) that a vanilla model does not reliably produce. Added an output_matches 'MSTEST0017' assertion and two rubric items requiring the analyzer id and its enablement, and removed expect_activation:false. This both restores activation validation and gives the skill a real quality advantage over baseline. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * run-tests: strengthen activation triggers to fix systemic non-activation Radical fix for run-tests' systemic activation-gate failures. Root cause from artifact analysis: these are 'show me the exact dotnet test command' prompts, so the model answers directly from its own knowledge without invoking run-tests — even in the ISOLATED arm where run-tests is the only skill loaded (proving it is prompt/description-trigger driven, not just plugin-menu competition). It often answers WRONG on the subtle SDK 8/9 '--' separator vs SDK 10+ direct-args rule (baseline 1.0-1.7) yet still does not reach for the skill. At ~70% per-run activation the strict '.Any(3 runs) in BOTH arms' gate flakes red. Two-pronged fix to raise per-run activation probability: 1. run-tests description: lead with an imperative trigger ('ALWAYS use when the user asks ... wants the precise command, flags, or argument order') and name the model's blind spot ('the right syntax depends on the platform and SDK version and is easy to get wrong from memory'). This signals the model should consult rather than guess, and is more trigger-matched for the plugin arm. Kept under the 1024-char description limit and the 15000-char plugin skill-menu budget (verified: skill-validator check passes). 2. The four currently-flaking scenario prompts now state the user needs the command to be correct for THIS project's specific test platform and SDK version (a natural need that raises the stakes) without naming the skill or leaking the answer — the model must still detect the platform and know the version-specific syntax. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * run-tests Negative test: fix brittle assertion penalizing the better skilled answer After the activation fix, run-tests activates on the Negative VSTest scenario in both arms (activation solved), but it still failed with completion_regression. Root cause: the assertion output_not_contains '--report-trx' is too naive. The skill-informed answer is strictly better — it recommends 'dotnet test --logger trx' AND educates 'use --logger trx, not --report-trx (which is MTP-only)'. That correct, more helpful contrast trips the substring ban, marking the better answer as a task-completion regression versus a bare baseline command. Fix: forbid --report-trx only when it appears as an actual dotnet test command (output_not_matches 'dotnet test[^\r\n]*--report-trx'), not when the answer names it to warn against it. Verified against the real failing outputs: both skilled runs' --report-trx mentions are in explanatory prose and now pass, while an actual 'dotnet test ... --report-trx' recommendation is still rejected. Stricter-but-correct. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * run-tests Negative test: drop expect_tools:[bash] to remove efficiency-only failure After the activation + assertion fixes, the Negative VSTest scenario activates in both arms and passes all assertions, but still failed on a -2.8% weighted score: the baseline is already perfect (5.0/5, correctly uses --logger trx), so the skill can add no quality — and expect_tools:[bash] forced the skilled arm to actually run the tests, inflating tokens (40k->88k) and tool calls (5->8) versus a leaner baseline. That efficiency delta was the entire failure (docs sec.8 baseline-already-good). This is a 'recommend the exact command' negative test: exit_success only checks the agent produced output, and the other assertions validate the recommended command text, so requiring bash execution over-specified the scenario. Dropping expect_tools lets both arms answer from knowledge, removing the forced-execution token/tool overhead while still fully validating that the answer uses --logger trx and never a 'dotnet test ... --report-trx' command. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> |
||
|
Abhitej John
|
ca1b47371f |
Add automated per-plugin versioning (NBGV) with /version-bump + weekly backstop (#813)
* Add automated per-plugin versioning (NBGV) with /version-bump + weekly backstop WHY Tools that surface skills (Copilot CLI, Claude Code, Codex, Cursor) read a plugin's version directly from its checked-in manifest. With no versioning discipline, a plugin's behavior can change while its advertised version stays flat, so clients never learn to re-pull, and there is no human-readable signal of what changed. We want correct, current versions in the repo with minimal manual work and without bloating the marketplace clone. WHAT - Per-plugin semantic versioning via Nerdbank.GitVersioning (NBGV). Each plugin owns a version.json whose pathFilters exclude the generated manifests and the version.json itself, so version height tracks real content changes only. - The computed version is materialized into the checked-in manifests (plugin.json and .codex-plugin/plugin.json) so every consumer reads a current value with no build step on their side. - eng/version/Sync-PluginVersions.ps1 is the single workhorse. It resolves the set of changed plugins from a git diff, computes each version with nbgv (predicting the squash-merge height for PRs), and either reports or stamps. AUTOMATIONS (two, low-touch by design) - /version-bump: an admin/maintainer comments the command on a PR and the affected plugins are stamped on the PR branch. Gated on collaborator permission (admin/write/maintain); forks are rejected before any privileged step. No other PRs are auto-modified. - weekly-version-sync: a Monday backstop (and workflow_dispatch) that stamps any drift on main, opens/updates a single bot PR, and explains the per-plugin reason. This self-heals anything that merged without a bump. We deliberately did NOT auto-edit contributor PRs or add a noisy advisory comment bot; maintainers stay in control and the signal stays clean. SECURITY (multi-model adversarial review: GPT-5.5 + Gemini 3.1 Pro) - Supply chain (High, both models): dotnet tool restore would have honored a nuget.config authored in the PR tree, letting an attacker remap the nbgv package source to a malicious feed and run code in the privileged contents:write context. Mitigated with a trusted eng/version/nuget.config (clear + nuget.org-only + packageSourceMapping), overlaid from main and used via --configfile so PR-supplied configs are ignored. No nuget.config is tracked in the repo today, so this path was genuinely exploitable. - TOCTOU (Medium): /version-bump now checks out the authorized head SHA rather than the mutable branch name; a racing push fails non-fast-forward, which is the safe outcome. - Injection: Set-ManifestVersion uses a MatchEvaluator (not a replacement string) so a "$"-bearing version cannot re-expand, plus a strict major.minor.patch guard that throws on a malformed base, leaving manifests untouched. - A base-only version.json bump (0.1 -> 0.2) is correctly detected and stamped. VERIFIED End-to-end against a real NBGV git harness: content-scoped predict, base-only bump -> x.y.0, docs-only -> [], weekly drift stamping, malformed-base guard, and --configfile restore (exit 0). actionlint passes on both workflows. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address Copilot review feedback - Add missing plugins/dotnet-test-migration/version.json so it participates in versioning (it was the only plugin without one; manifests are at 0.1.0). - CONTRIBUTING: the two manifests are not byte-identical; say the version is duplicated across two manifest files instead. - weekly-version-sync: include version.json in commit attribution so a base-only bump is explained rather than showing 'no attributable commits'. - Get-NbgvInfo: capture nbgv stderr and include it in the thrown error so CI failures are diagnosable, while keeping stdout clean for JSON parsing. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
1270722c95 |
Fix migrate-static-to-wrapper skill activation on evals (#864)
Sharpen the description boundary between migrate-static-to-wrapper and generate-testability-wrappers so prompts that replace call sites when the abstraction is already registered in DI activate the migration skill. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
e558acb8e8 |
dotnet-test: raise timeout for boundary comparison assertions eval scenario (#863)
The 'Use comparison assertions for boundary testing' scenario chronically hit its 240s wall-clock timeout. Raise it to 360s to match the other code-generation scenarios in this eval file, per InvestigatingResults.md timeout guidance. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
8bbf2bfd61 |
dotnet-test: reduce assertion-quality over-structuring on small suites (#865)
Scale report depth to suite size so a tiny test file gets a focused, direct answer instead of a padded multi-section dashboard. Preserves full-template behavior for substantial suites and keeps all rubric-relevant substance (assertion-free/trivial identification, quality verdict, concrete recommendations). Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
77154137e8 |
dotnet-test: make code-testing agent tools Claude Code-compatible + add cross-host portability check (#856)
* dotnet-test: make code-testing agent tools declarations Claude Code-compatible PR #847 added `tools: ["agent", "skill", "read", "search", "edit", "execute"]` to the code-testing-* agents to enable VS Code / Copilot CLI subagent fan-out. Those lowercase aliases map to real tools in VS Code and the Copilot CLI, but Claude Code matches `tools:` against its own vocabulary (Task, Skill, Read, Glob, Grep, Edit, Write, Bash). None of the aliases matched, so when these agents are loaded into Claude Code via --plugin-dir and selected with `claude --agent`, the agent was granted ZERO tools. A tool-less model asked to generate tests emits a textual <tool_call> block and exits after one turn, producing no file changes. Append the Claude Code tool names to each agent's `tools:` list so the same declaration works across all three runtimes (each honors the names it knows and ignores the foreign ones): - Orchestrators (generator, implementer): add Task, Skill, Read, Glob, Grep, Edit, Write, Bash (Task is the Claude Code equivalent of the `agent` fan-out tool). - Workers (researcher, planner, builder, tester, fixer, linter): add Skill, Read, Glob, Grep, Edit, Write, Bash. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * skill-validator: complete built-in tools + add cross-host tool portability check Two related follow-ups to the agent tools fix: 1. Address the skill-check review feedback. The validator's BuiltInTools set was missing three legitimate host tool spellings that are not case-insensitive matches of existing entries, so they were flagged as non-built-in: - "write" — Claude Code file-creation tool (Copilot CLI / VS Code: "create") - "agent" — Copilot CLI / VS Code subagent fan-out tool (Claude Code: "task") - "execute" — Copilot CLI / VS Code run-command tool (Claude Code: "bash") "agent" and "execute" were already flagged before this branch (introduced by the fan-out PR); adding them to BuiltInTools clears the pre-existing warnings. 2. Add a cross-host tool portability check (CheckAgentToolPortability) so an agent that declares a capability for only one host is flagged. Tool names are matched case-sensitively (hosts resolve tools by exact spelling), so an agent that lists e.g. only "edit" (Copilot / VS Code) without "Edit"/"Write" (Claude Code) is reported as working on one host and silently tool-less on the other. Findings are advisory (do not fail CI) and allowlistable via "agent-tool-portability:AGENT:capability". Wired into the agents loop in CheckCommand and covered by unit tests. Also make the one existing single-host agent (optimizing-dotnet-performance) portable by adding its Claude Code tool spellings, so the new check reports a clean tree. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
72af853455 |
Add slnf and slnx solution formats to run-tests skill (#857)
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
ce75c35569 |
dotnet-test: raise timeouts for chronic-timeout eval scenarios (#850)
Several dotnet-test eval scenarios repeatedly hit their wall-clock timeout in the evaluation dashboard (skilled + plugin arms), producing empty output and failing all assertions. Increase per-scenario timeouts for the ones that timed out most often across recent runs: - writing-mstest-tests: 'Write unit tests for a service class', 'Write data-driven tests for a calculator', 'Use string assertions for format validation' 180->360; 'Use comparison assertions for boundary testing' 120->240 - coverage-analysis: 'Coverage plateau diagnosis', 'Project-wide coverage analysis with existing Cobertura data' 300->480 - test-gap-analysis: 'Decline request to write new tests from scratch' 120->300; 'Acknowledge well-tested code with few surviving mutations' 300->420 - run-tests: 'Filter xUnit v3 tests by trait on MTP', 'Filter xUnit v3 tests by class pattern and trait using query filter language' 120->240 Per eng/skill-validator/src/docs/InvestigatingResults.md, timeouts are the highest-priority failure mode; code-generation scenarios often need 360s. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
a677ec43d2 |
Consolidate dotnet-test-frameworks into test-analysis-extensions (#851)
* Consolidate dotnet-test-frameworks into test-analysis-extensions Remove the orphaned dotnet-test-frameworks reference skill, whose content was a duplicate subset of test-analysis-extensions/extensions/dotnet.md. Nothing actually loaded it. Redirect the remaining references and drop its eval tests. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * Make exp-test-maintainability Step 1 self-contained and fix activation Address PR review: exp-test-maintainability (dotnet-experimental plugin) must not point at test-analysis-extensions (dotnet-test plugin) — inline the .NET framework markers instead. Also strengthen the description/When-to-Use triggers so the 'each new case needs a whole new method / suggest a better structure' scenario reliably activates the skill instead of routing to a test-writing skill. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * Revert exp-test-maintainability description broadening; keep self-contained markers The description broadening regressed activation (3/4 -> 0/4 across a variance-dominated single eval run, CV up to 924%). Description is the activation lever, so restore the original wording and keep only the review-comment fix (inlined .NET framework markers in Step 1). Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * Fix scenario 1 eval: use project fixture so the skill activates Scenario 1 pasted a self-contained snippet inline and asked to 'suggest a better structure', which the base model answers directly without loading the skill -> NOT ACTIVATED with no headroom. Convert it to the project-fixture pattern used by the activating scenarios (3 & 4): move the repetitive InputValidatorTests into a Validation.Tests fixture and ask the model to analyze the project. Mirror the change in eval.vally.yaml. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * Fix scenario 2 eval: use project fixture so the skill activates Scenario 2 also pasted a self-contained snippet inline (well-maintained Auth.Tests) and asked to 'review these tests', which the base model handles without loading the skill. Convert to the project-fixture pattern used by the activating scenarios; add fixtures/well-maintained/Auth.Tests. Mirror in eval.vally.yaml. All four scenarios now reference a project on disk. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * Add reject_tools to exp-test-maintainability evals to create headroom All four scenarios scored NOT ACTIVATED / no-headroom (#8 in InvestigatingResults.md): baselines are already 4.0-5.0/5, so loading the skill only adds token/tool overhead with no offsetting quality gain. Match the convention of the sibling analysis skill test-anti-patterns: reject bash/edit/create on every scenario. This skill is analysis-only ('do not modify any files'), so the constraint is a no-op for correct behavior but levels the playing field between baseline and skilled runs — scoring focuses on answer quality (weight 0.40+0.30) instead of tool-induced overhead. Applied to both eval.yaml and eval.vally.yaml. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * Address review: make well-maintained fixture self-contained and deterministic - Import System.Security.Authentication for AuthenticationException - Replace wall-clock assertion (token.ExpiresAt > DateTime.UtcNow) with a deterministic one anchored on a fixed clock (FixedNow), and drive the injected FakeClock from that fixed time. This removes the flakiness and makes the FakeClock injection meaningful — a better exemplar for the 'well-maintained' scenario. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> |
||
|
Petr Pokorny
|
325890d119 |
Bump dotnet-test to 0.2.0 (#852)
* Bump dotnet-test plugin to 0.2.0 Signals the VS Code subagent fan-out fix (#847) to existing installs. Minor bump; no breaking changes. * Sync .codex-plugin manifest to 0.2.0 Keeps plugins/dotnet-test/.codex-plugin/plugin.json in sync with the main plugin.json, matching the convention other plugins follow (e.g. dotnet-ai). Addresses PR review feedback. |
||
|
Abhitej John
|
733cc264e3 |
fix: add .claude-plugin manifest for dotnet-msbuild binlog MCP server (#844)
Claude Code discovers MCP servers via .claude-plugin/plugin.json inside each plugin directory. The existing .codex-plugin/ manifest only works for Codex CLI. Add the Claude Code-specific manifest with inline mcpServers config, and also declare mcpServers in the root marketplace manifest entry for belt-and-suspenders coverage. Fixes #840 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Petr Pokorny
|
06dd46e5f1 |
Enable VS Code subagent fan-out for the dotnet-test code-testing agents (#847)
* Add VS Code subagent metadata to dotnet-test code-testing agents
Enable the code-testing-* Research-Plan-Implement pipeline to fan out as
subagents in VS Code while keeping the GitHub Copilot CLI working.
Frontmatter (VS Code "coordinator/worker" pattern; portable tool aliases that
map in both VS Code and the CLI):
- code-testing-generator: tools: [agent, read, search, edit, execute] + an
agents: list (researcher, planner, implementer, builder, tester, fixer,
linter); softened the three runSubagent({ agent, prompt }) blocks to
tool-agnostic delegation prose.
- code-testing-implementer: tools: [agent, read, search, edit, execute] +
agents: (builder, tester, fixer, linter).
- Leaf agents (researcher/planner/builder/tester/fixer/linter):
tools: [read, search, edit, execute].
Why explicit tools (not ["*"]): VS Code has no all-tools wildcard for ools:
and a subagent's ools: overrides its inherited set, so ["*"] matched nothing
and stripped subagents of file tools (they ran without read/edit/search). The
CLI treats ["*"] as all-tools, so this was VS-Code-specific. The portable
aliases agent/read/search/edit/execute map to real tools in both environments;
agents: is ignored by the CLI.
README: document the VS Code chat.subagents.allowInvocationsFromSubagents
setting (off by default) needed for the nested implementer->builder/tester/
fixer/linter layer to fan out on large scopes; the CLI has no such gate.
Validated end to end: VS Code shows researcher->planner->implementer fanning out
with real file I/O (no "subagents lack file tools" warning); CLI fan-out intact
with skills still loading and tests passing. An all-tools baseline used only
tools within this enumerated set, confirming no CLI capability is restricted.
* Include skill tool in code-testing agent tool allowlists
Address PR review: the explicit `tools:` allowlists omitted the `skill`
tool, but every code-testing-* agent's prompt instructs calling skills
(e.g. `code-testing-extensions` for per-language guidance, `test-gap-analysis`,
`assertion-quality`). Because `tools:` is an override, omitting `skill` can
prevent the agents from loading those skills in environments that gate skill
invocation by the allowlist.
Add `skill` to all eight agents:
- orchestrators (generator, implementer): [agent, skill, read, search, edit, execute]
- workers (researcher/planner/builder/tester/fixer/linter): [skill, read, search, edit, execute]
Re-verified in the Copilot CLI: full fan-out (researcher -> planner ->
implementer/tester), the `code-testing-extensions` skill is invoked, and the
generated tests pass.
|
||
|
Wendy Breiding
|
4975793af0 |
Moving niche skills to dotnet-advanced (#807)
* Add csharp-development skill and update CODEOWNERS and README.md - Introduced a new skill for C# development guidance. - Updated CODEOWNERS to include reviewers for the new skill. - Modified README.md to list the new csharp-development skill. - Added evaluation scenarios for the csharp-development skill. * Refactor C# evaluation scenarios to enhance production code review and validation guidance * Refactor production code review scenarios to improve clarity and focus on async error handling * Update CODEOWNERS to reflect current ownership and streamline reviewer assignments * Remove csharp-development skill documentation and evaluation tests * Remove csharp-development skill from README * Fix formatting in Constants.g.cs by adding missing semicolon * Revert Constants.g.cs to main * Remove csharp-development skill from CODEOWNERS * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Update CODEOWNERS to include additional reviewers for dotnet-ai skills * Move dotnet skills to dotnet-util to keep dotnet plugin focused and targeted. * Add CODEOWNERS, SKILL.md, package-types.md, and publish-workflow.md for NuGet trusted publishing; implement eval.yaml for dotnet-pinvoke and dotnet-util skills * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Update README files to enhance plugin descriptions and remove outdated LSP section * Rename repository title from 'dotnet' to 'dotnet-util' in README.md for clarity. * Refine README.md to clarify included .NET skills and remove redundant descriptions * Add 'dotnet-util' plugin for utility skills in .NET development * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Add 'dotnet-util' plugin for utility skills in .NET development * Add dotnet-util to Codex marketplace manifest * Align dotnet-util marketplace descriptions * Refactor CODEOWNERS and update README for nuget-trusted-publishing; add evaluation scenarios and workflow template for trusted publishing * Add P/Invoke diagnostics and type mapping references; implement NuGet trusted publishing setup - Created diagnostics.md for common pitfalls and failure modes in P/Invoke. - Added type-mapping.md for native-to-.NET type mappings. - Introduced nuget-trusted-publishing skill for setting up OIDC-based NuGet publishing. - Added package-types.md detailing structural requirements for various NuGet package types. - Created publish-workflow.md as a template for GitHub Actions workflows for NuGet publishing. * Add evaluation YAML files for csharp-scripts, dotnet-pinvoke, and nuget-trusted-publishing skills * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Complete nuget-trusted-publishing move: remove from dotnet, add to dotnet-specialized README * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Remove eval.vally.yaml and eval.yaml files for nuget-trusted-publishing skill * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Add NuGet trusted publishing skill and related references - Introduced `nuget-trusted-publishing` skill for setting up OIDC-based trusted publishing on GitHub Actions. - Added detailed documentation in SKILL.md covering prerequisites, process, safety rules, and troubleshooting. - Created `package-types.md` to outline structural requirements for various NuGet package types. - Developed `publish-workflow.md` as a template for GitHub Actions workflows for NuGet publishing. - Removed obsolete `dotnet-specialized` plugin and updated `dotnet` plugin description. - Added evaluation tests for `nuget-trusted-publishing` skill to ensure proper guidance for users. - Implemented evaluation tests for `dotnet-pinvoke` and `csharp-scripts` skills to validate functionality. * Update dotnet plugin description to include high-level .NET development skills * Add NuGet trusted publishing and P/Invoke documentation - Introduced type mapping reference for native-to-.NET types in dotnet-pinvoke. - Added a comprehensive guide for setting up NuGet trusted publishing using OIDC in GitHub Actions. - Created a reference document detailing structural requirements for various NuGet package types. - Provided a template for GitHub Actions workflow for publishing NuGet packages with trusted publishing. - Implemented evaluation scenarios for testing the dotnet-pinvoke and nuget-trusted-publishing skills, including prompts and assertions for expected outputs. * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Add CODEOWNERS entries for setup-local-sdk * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Update dotnet README to list setup-local-sdk skill * Add setup-local-sdk to skills section in README * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> |
||
|
YuliiaKovalova
|
8a52700bce |
Add TFM-aware buildTransitive->build forwarding guidance to msbuild skills (#836)
* Add TFM-aware buildTransitive->build forwarding guidance to msbuild skills buildTransitive/*.props should forward through the corresponding build/*.props (ownership chain buildTransitive -> build -> shared) rather than importing buildMultiTargeting/ directly. When build/ is packed per-TFM (build/<tfm>/), the forwarder must include the TFM segment and derive it from the file own folder, not $(TargetFramework) (NuGet nearest-match can serve a different asset folder), otherwise transitive consumers hit MSB4019. Updates extension-points (new Forwarding chain section), msbuild-antipatterns AP-13, and the msbuild-code-review agent. Lesson learned from microsoft/testfx#9431. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Clarify ambiguous props/targets glob in forwarder review check Address review feedback on dotnet/skills#836: spell out ".props/.targets forwarders" instead of the ambiguous `buildTransitive/*.props|targets`. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Tighten forwarding-chain guidance to reduce skill token overhead Condense the new extension-points Forwarding chain section (+26 -> +11 lines) and the AP-13 note by dropping the redundant non-TFM example and self-evident derivation explanation, keeping the chain rule, MSB4019 cause, and the TFM derivation expression. Lower token footprint addresses the skill-validator weighted-score token penalty without losing substance. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address review nits: AP range and forward-slash path Update the additional anti-patterns range to AP-16 through AP-22 (the reference doc now includes AP-22), and use a forward-slash build/MyPackage.props in the forwarding-chain prose to match the build/<tfm>/ convention used in the section. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Condense AP-13 forwarding note to a cross-reference to reduce token overhead The full TFM-forwarding guidance lives in extension-points; AP-13 only needs a concise pointer. Removes duplication and trims the msbuild-antipatterns skill footprint flagged by the skill-validator token penalty. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Address remaining review nits: targets forwarders, single-source wording, quoted MSBuildThisFileDirectory --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> |
||
|
Huo Yaoyuan
|
4560ea4d4d | Update P/Invoke skill (#798) | ||
|
Amaury Levé
|
691cd472a1 |
Fix writing-mstest-tests activation by deflecting sibling skills (#835)
* Add MSTest deflection to assertion-quality and test-anti-patterns skills The writing-mstest-tests skill failed to activate in the plugin arm for six MSTest-specific scenarios (fix swapped Assert.AreEqual, modernize legacy patterns, type/string assertions, DynamicData with ValueTuples) because sibling skills captured the routing. assertion-quality and test-anti-patterns matched these prompts but lacked explicit deflection to writing-mstest-tests. Add DO NOT USE entries pointing MSTest test writing/fixing/modernizing to writing-mstest-tests. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address review: restore general assertion-fix deflection, align test-anti-patterns - assertion-quality: restore the general 'fixing or rewriting assertions' deflection (dropped in the prior edit) alongside the MSTest deflection, and fix punctuation to use comma-separated DO NOT USE items. - test-anti-patterns: align the 'writing new tests' deflection to also point MSTest test-writing to writing-mstest-tests, matching the body guidance. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
592a53008e |
skill-validator: restore 15K aggregate cap as the real Copilot CLI skill-menu budget (#803)
* skill-validator: restore 15K aggregate cap, document it as the real Copilot CLI skill-menu budget The per-plugin aggregate description cap had been raised 15,000 -> 20,000 -> 22,000 under the belief that 15K was 'a local repo policy, NOT a documented Copilot constraint'. That belief was wrong: the GitHub Copilot CLI renders the model-facing <available_skills> menu under a hard 15,000- char budget (the agent SDK's SKILL_CHAR_BUDGET, default 15e3, confirmed in CLI 1.0.36 and 1.0.61). Skills are listed alphabetically and emitted with their full <description> only until the budget is exhausted; every skill past the cut-off collapses to a bare name with no description and can no longer be reliably model-activated. Raising the validator cap merely masked this silent menu truncation — e.g. dotnet-test's run-tests and test-* skills stopped activating in plugin eval runs because they fell into the name-only overflow. Changes: - SkillProfiler.MaxAggregateDescriptionLength: 22,000 -> 15,000, with the comment rewritten to document the real Copilot CLI budget (and correct the prior 'not a documented constraint' claim). - CheckCommand aggregate now excludes skills marked 'disable-model-invocation: true' — the CLI drops those from the menu, so they do not consume the budget. This makes the cap satisfiable by hiding reference / agent-orchestrated primitives rather than only by trimming. - InvestigatingResults.md: document plugin-arm-only non-activation caused by skill-menu budget overflow, and how to fix it. Note: dotnet-test currently exceeds 15K and must be slimmed below it (via disable-model-invocation on reference/primitive skills plus description trims) before this cap can go green repo-wide. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * skill-validator: use source-generated regex for disable-model-invocation check Address review: replace Regex.IsMatch(pattern-string) with a [GeneratedRegex] partial method (AOT-friendly, no per-call cache lookup), matching FrontmatterParser's style. Runs once per skill during checks. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * skill-validator: parse disable-model-invocation via YAML to avoid block-scalar false positives The regex-based check matched any line in the frontmatter, so a block-scalar description that merely mentioned 'disable-model-invocation: true' on its own line was wrongly treated as disabling model invocation. Parse the frontmatter with the existing YAML deserializer (which correctly handles block scalars) by adding a DisableModelInvocation field to SkillFrontmatter, and drop the regex entirely. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
cbb6121e76 |
dotnet-test: trim skill descriptions to fit skill-menu under 15K (#816)
The plugin's rendered skill-menu was 15,428 chars, over the 15,000 limit. Compressed the verbose per-framework parentheticals in the longest polyglot descriptions and dropped a few redundant clauses, preserving all routing keywords. Aggregate name+description length now ~14.5K. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Gerald Versluis
|
72c0d2c7b7 |
Add setup-local-sdk skill for global.json paths feature (#508)
* Rebase setup-local-sdk skill Replay PR #508 onto current main and address the remaining setup-local-sdk review feedback. The install examples now use fail-fast temporary downloads, the team scripts preserve existing global.json content, and eval assertions cover the critical paths/version/workload behavior. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address setup-local-sdk review comments Add the missing skill license metadata and fix the PowerShell .gitignore regex examples so they correctly detect an existing .dotnet/ entry. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Stabilize setup-local-sdk evals Reduce overfit-prone assertions, make incompatible host handling explicit, configure base SDK resolution before slow workload installs, and tighten exact-version/team-script validation. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address setup-local-sdk follow-up review Include the shared dotnet skill reviewer team in CODEOWNERS, make .gitignore appends newline-safe, and tighten the incompatible-host eval to reward stopping before local install commands. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Tighten exact local SDK eval Measure project-level SDK resolution and exact roll-forward behavior using global.json artifact assertions so the scenario distinguishes PATH-based local installs from SDK paths setup. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address install script review feedback Use the documented lowercase dotnet-install quality value and call out both bash and PowerShell official install script URLs. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Increase team script eval timeout Give the team install script scenario the same realistic long-running timeout as other scenarios that install preview SDK bits. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add Windows local SDK check Document the PowerShell equivalent for detecting an existing local SDK and give exact SDK installs enough time to complete in eval. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Stabilize team script eval Focus the team script scenario on script/config generation, create reproducible setup guidance before long downloads, and avoid brittle transcript assertions. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Make mktemp usage portable Use BSD/macOS-compatible mktemp templates in setup-local-sdk bash snippets and generated team install script. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
YuliiaKovalova
|
67e2a47e87 |
Trim dotnet-msbuild skill-menu under 15K char limit (#809)
The rendered skill-menu for the dotnet-msbuild plugin was 16,679 characters, exceeding the 15,000 limit. Trim two categories of content from the 18 skill descriptions that do not help agents decide when to invoke a skill: - Remove INVOKES: clauses (which MCP tools / fallback shell commands a skill runs internally) — implementation mechanics, not routing signal. - Remove the boilerplate 'Only activate in MSBuild/.NET build context.' repeated verbatim in all 18 skills — redundant, since every description is already MSBuild-specific and each DO NOT USE FOR still excludes non-MSBuild build systems. USE FOR triggers and DO NOT USE FOR cross-references are preserved. Aggregate skill description size drops from 14,551 to 12,536 chars (rendered menu 16,679 -> 14,664). Co-authored-by: Yuliia Kovalova <ykovalova@users.noreply.github.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
35ace775b3 |
Add dotnet-test-migration plugin and move migration skills there (#808)
Move the .NET test framework/platform migration skills (migrate-mstest-v1v2-to-v3, migrate-mstest-v3-to-v4, migrate-vstest-to-mtp, migrate-xunit-to-mstest, migrate-xunit-to-xunit-v3) and the test-migration orchestrator agent out of dotnet-test into a new dedicated dotnet-test-migration plugin, along with their evals. Update all marketplace manifests, READMEs, CODEOWNERS, and .vally.yaml accordingly. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
29bfae5f5b |
run-tests: fix evals (query-filter regex, sibling skills, command observability) (#800)
* run-tests: fix evals (query-filter regex, sibling skills, command observability)
Investigated run-tests eval failures by running the validator locally.
- SKILL.md Step 3: document xUnit v3 --filter-query so the agent stops
answering that complex xUnit v3 filters 'cannot be combined'.
- eval.yaml: fix a broken assertion regex. The query-filter pattern is a
single-quoted YAML scalar using '\\s'/'\\[', which (unlike a double-quoted
scalar) is NOT unescaped, so the regex searched for a literal '\s' and
could never match. Corrected to single backslashes.
- eval.yaml: add additional_required_skills (filter-syntax / platform-detection)
to the filter and detection scenarios, so the isolated arm loads the sibling
reference skills that run-tests explicitly defers to.
- eval.yaml: ask the agent to show the exact command in execute-style prompts.
output_matches only sees the final assistant message; 'run my tests' prompts
make the agent execute and summarize ('tests passed'), so the recommended
command never appears. The assertions still catch wrong commands.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* run-tests: rewrite description for reliable plugin-arm activation
The run-tests skill activated reliably in the isolated eval arm but
unreliably in the plugin arm (all dotnet-test sibling descriptions
loaded), so every scenario's pluginImprovementScore went negative and
dragged min(isolated, plugin) below zero.
Lead the description with natural-language intent triggers that mirror
how the eval prompts phrase requests (run all tests, run a subset via
filters, produce TRX reports, collect crash/hang dumps, run a single
TFM) instead of opening with platform-detection mechanism, and add
explicit DO NOT USE redirects to code-testing-agent / mtp-hot-reload.
Stays under the 1024-char description cap.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* dotnet-test: fix run-tests plugin-arm activation via skill-menu budget
Root cause (verified against the Copilot CLI SDK skill renderer): the
model-facing skill menu has a 15000-char budget. Skills are listed
alphabetically and emitted with full descriptions only until the budget
is exhausted; the rest collapse to bare names with no description and
effectively cannot be model-activated. With 27 dotnet-test skills,
run-tests (alphabetical position ~20) fell into the name-only overflow,
so it never activated in the plugin eval arm even though it activated
reliably in isolation. This is a real user-facing discoverability bug,
not just an eval artifact.
Fix: hide reference/primitive skills that are never meant to be
model-invoked from the menu via 'disable-model-invocation: true', which
the SDK filters out of the budget entirely:
- filter-syntax, platform-detection, dotnet-test-frameworks,
code-testing-extensions, test-analysis-extensions — already
user-invocable:false reference data ('DO NOT USE directly').
- find-untested-sources, find-untested-sources-polyglot — researcher
primitives invoked by-name from the code-testing-researcher agent
(which has a manual fallback); no standalone evals.
These remain invocable by explicit name (agents/users), only auto-
suggestion is suppressed.
This frees enough budget that run-tests (plus migrate-xunit-to-xunit-v3
and mtp-hot-reload) now receive full descriptions; no previously-visible
skill regresses. Also trimmed the run-tests description so its menu block
fits with margin while keeping all activation triggers.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
||
|
Amaury Levé
|
e3f0becd4c |
Fix test-gap-analysis skill activation in plugin eval runs (#801)
* Fix test-gap-analysis skill activation in plugin eval runs In plugin-mode eval runs (all dotnet-test skills loaded), test-gap-analysis lost activation: 'Acknowledge well-tested code' was stolen by assertion-quality and 'logic/null-check gaps' loaded no skill at all. Front-load the concrete 'would my tests catch a bug if the code changed' trigger phrasing the prompts use, and add a DO NOT USE -> test-gap-analysis redirect in assertion-quality for mutation-style reasoning. Both descriptions stay within the 1024-char cap; aggregate unchanged. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Restore Jest/TS activation signal for assertion-quality polyglot scenario The earlier trim of assertion-quality's description dropped the Jest/Vitest and toBeTruthy() signals, breaking plugin-mode activation for the 'Polyglot: Jest/TypeScript' scenario (agent answered directly, loading no skill). Restore those polyglot signals, and make the scenario prompt realistic — the prior prompt enumerated the full check catalog and Jest matcher list inline, acting as an answer key that let the agent self-serve without loading the skill. Verified locally: the scenario now activates assertion-quality in plugin mode across runs; all other assertion-quality scenarios still activate; description stays within the 1024-char cap. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
03f06321a4 |
Cover MSTESTxxxx analyzer diagnostics in writing-mstest-tests skill (#794)
* Cover MSTESTxxxx analyzer diagnostics in writing-mstest-tests skill Add a 'Fix MSTest analyzer diagnostics' workflow step mapping the common MSTESTxxxx rules to their idiomatic fixes, plus MSTestAnalysisMode guidance, instead of creating one skill per rule. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Fix MD012 markdown lint (trailing blank line) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address review feedback: reword analyzer availability and fix table grammar - Don't tie MSTest.Analyzers availability to TestFramework 3.7; note metapackage/SDK/explicit reference. - Fix grammatically broken fix text for the MSTEST0002-0014 layout row. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Clarify the MSTESTxxxx table is non-exhaustive; defer to full reference Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
0c98ce6bd9 |
Direct strategy must still run the Step 7 pre-completion gate (#793)
* Direct strategy must still run the Step 7 pre-completion gate The Direct strategy correctly skips the research/plan/implement sub-agents for small single-file tasks, but the wording let agents also skip the Step 7 pre-completion gate (test-gap-analysis + assertion-quality + scenario coverage) — treating a single-file task that enumerates specific behaviors as 'trivially small'. This is the dominant failure mode observed on behavior-enumerating tasks: the agent writes one test file directly and finishes with no assertion-strength or scenario-coverage check, producing weak assertions (mutation survivors) and missing required edge/negative cases. Clarify in both the generator Step 2 strategy table and the code-testing-agent SKILL.md that Direct trades away only the sub-agents, never the gate, and that a request naming a specific symbol or enumerating scenarios is not 'trivially small' and must run the gate. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address review: align Direct gate trigger with Step 7 threshold; clarify gate in SKILL.md - Step 2 Direct cell no longer introduces a separate 'names a specific symbol' gate trigger that contradicted Step 7. It now defers to Step 7's own threshold (>=5 tests, or any enumerated behaviors/scenarios). - SKILL.md now names what/where the gate is: the generator's Step 7 (test-gap-analysis + assertion-quality). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Amaury Levé <evangelink@users.noreply.github.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
5d717dbdd1 |
Add prompt-scenario coverage check to code-testing-generator gate (#789)
* Add prompt-scenario coverage check to code-testing-generator gate The pre-completion gate already verifies assertion strength (pseudo-mutation and assertion-depth checks), but two recurring failure modes still slip through when the prompt enumerates specific behaviors: - Testing an *adjacent* function/helper instead of the exact feature named in the objective, leaving the requested behavior uncovered. - Covering only a single representative case when the scenario wording implies multiple variations or pins a condition to a specific position or structure. Add a third gate item that maps each enumerated scenario to a dedicated test, requires targeting the exact named function (preferring the canonical existing test file), and requires honoring range/positional qualifiers literally. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address review: genericize example, fix gate-count consistency - Remove benchmark-specific symbol names from the target-the-named-function bullet to avoid overfitting; phrase it generically. - Fix the gate intro that said 'The two skills below' now that there are three numbered items (the third is a prompt self-review, not a skill). - Update Step 8 and Rule 11 so re-running the gate includes the new prompt-scenario coverage check, not just test-gap-analysis + assertion-quality. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Amaury Levé <evangelink@users.noreply.github.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
14d727fee6 |
Fix test-anti-patterns skill activation for 5 evals (#786)
* Fix test-anti-patterns skill activation for 5 evals Sibling skills with overlapping descriptions were stealing activation from test-anti-patterns in plugin eval runs (coverage-analysis, assertion-quality, test-smell-detection). Reword descriptions so test-anti-patterns owns the umbrella 'audit my tests for anti-patterns' severity-ranked report, and add DO NOT USE redirects in the metric-focused siblings. Kept all descriptions within the 1024-char cap. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Use toBeTruthy() call form in assertion-quality example Addresses review feedback: the Jest matcher example read like a property without parentheses. Description stays within the 1024-char cap (1023). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Fix eval validation error and improve activation triggers - assertion-quality eval.yaml/eval.vally.yaml: replace hyphenated 'assertion-quality' (the target skill name) with spaced 'assertion quality' in two scenario prompts, fixing the 'prompt mentions target name' validation error that biased baseline runs. - test-anti-patterns description: add 'what's wrong with my tests' / 'are these tests any good' / 'flaky tests' trigger phrasing to improve organic activation for the flakiness, well-written and polyglot scenarios (which intermittently failed to activate in plugin runs). Stays within the 1024-char description cap (1007). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Use Jest matcher call form in assertion-quality polyglot prompt Addresses review feedback: write toBeDefined()/toBeTruthy()/not.toBeNull()/ toBe()/toThrow() in call form in the prompt so they read as matcher calls, consistent with the skill description examples. Regex assertions and rubric left untouched (they match agent output, which may use either form). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Sharpen test-anti-patterns description for flakiness/polyglot activation The flakiness and Python-pytest scenarios failed to activate even in isolated runs (where it's the only candidate skill), because their prompts enumerate the methodology and the description's keywords were too generic. Front-load the concrete trigger keywords those prompts use: Thread.Sleep, DateTime.Now, time.sleep, order-dependent, reflection coupling, and Python/pytest. Stays within the 1024-char cap. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Make mixed/flakiness eval prompts realistic to fix plugin activation The mixed-severity and flakiness scenarios consistently failed to activate test-anti-patterns in plugin runs (detected=[] — the agent loaded no skill at all and answered directly). Both prompts enumerated the full anti-pattern catalog inline, acting as an answer key that made the agent self-sufficient. Replace the embedded checklists with realistic user asks while keeping the 'for .NET test anti-patterns' trigger, file references, severity-ranked output format, and read-only constraint. Rubric and output_matches assertions are unchanged — they validate the produced report. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
0c2b9710ee |
Fix activation for OutputType=Exe Directory.Build.props scenario (#785)
The 'Set OutputType=Exe only for test projects in Directory.Build.props' eval scenario was failing skill activation: the model answered from its own knowledge and proposed the IsTestProject condition the skill explicitly warns against. Strengthen the migrate-vstest-to-mtp SKILL.md description so the skill router matches this scenario: add the literal trigger phrase and surface the MSBuildProjectName (correct) and IsTestProject (anti-pattern) keywords in the USE FOR clause. Trimmed lower-value text to stay within the 1024-char description limit (1011). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
f389af86c7 |
code-testing-generator: mandatory pre-completion self-review gate (#768)
* code-testing-generator: mandatory pre-completion self-review gate Replaces the prose `Verify tests are implementation-specific'' bullet in Step 7 of the code-testing-generator agent with a mandatory pre-completion self-review gate that invokes two existing plugin skills: 1. `test-gap-analysis'' (pseudo-mutation check) against the source files tested and the produced test files 2. `assertion-quality'' (trivial/tautological assertion check) against the produced test files Both skills already ship in plugins/dotnet-test; this PR only wires them into the generator's workflow as a mandatory gate before declaring a run complete. The two skills' `When to Use'' sections are extended to list `called by code-testing-generator as a pre-completion self-review step'' as a recognised use case so the model does not refuse the invocation. The skill descriptions are unchanged (frontmatter is already at the 1024-char limit). Rule 11 of the generator agent is updated to list the gate alongside final build, final test, and coverage-gap review as mandatory for ALL strategies including Direct. A matching rubric item is added to the ContosoUniversity scenario in the code-testing-agent eval (yaml and vally) so the LLM judge can verify the gate was actually invoked on the trajectory. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Apply suggestions from code review Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
11fd40e04c |
Add worked example files for C++, PowerShell, Ruby, Rust, Kotlin (#775)
* Add missing language worked examples Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address review: fix runnable example bugs (PS type/scope, Rust impl Trait arg, Catch2 macros) - powershell: accept [pscustomobject] in Get-InvoiceTotal; assert \ - rust: use concrete fn pointer type instead of impl Trait as generic arg - cpp: use REQUIRE_THROWS_WITH for message-substring assertions Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
2bdec9b741 |
Expand C++ testing extension: coverage instrumentation, frameworks, CMake/ctest setup (#777)
* Expand C++ testing extension guidance Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address review: group find -o predicates, include AppleClang, note libgtest-dev caveat Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
fc1e54f1a4 |
Harden Python testing guidance: reuse repo test runner/layout, handle heavy deps, never ship failing tests (#776)
* Harden Python testing guidance: reuse repo runner/layout, handle heavy deps, never ship failing tests Python is the weakest benchmark language (grade ~0.31): ~60% of generated tests fail and coverage stays ~2%. Trajectory analysis showed heterogeneous causes — custom runners not discovered (Django), custom layouts (ansible test/units), native-import failures (PyTorch), and over-reach that ships failing tests (Flask/FastAPI), which zeroes the grade via the pass-all gate. - Discover and reuse the repo's own test runner/layout before writing tests. - Add Django runner / DJANGO_SETTINGS_MODULE / subdir-runner guidance. - Verify heavy/native modules import before testing; otherwise scope down or skip. - Add a green-suite-or-remove finalization rule (delete tests that can't pass). - Start with high-certainty pure-function tests to bank coverage. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address review: reword nonexistent Skip section reference Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address review: clarify env-wrapper usage for module vs script/-c, import probes, and green-suite check Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
YuliiaKovalova
|
5aa08ce41b |
Resolve Microsoft.AITools.BinlogMcp from nuget.org (#774)
The Microsoft.AITools.BinlogMcp package is now published on nuget.org as stable 1.0.0, so the binlog MCP server no longer needs the dnceng AzDO dotnet-tools feed or the --prerelease flag. Drop --prerelease and --add-source <azdo> from the binlog server args in both plugin.json and the .codex-plugin/.mcp.json mirror. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
754011b5ee |
Add workspace-integrity guardrail to code-testing agents (#773)
The code-testing-generator/implementer agents could treat an unusual or
scaffolded workspace (e.g. a gutted repo with an injected synthetic module)
as corruption and "repair" it with git checkout/restore/reset/clean or rm,
restoring deleted tracked files and testing the wrong code.
- Replace generator Rule 5 ("Clean git first - stash changes") with an
explicit "Treat the workspace as delivered" rule, and add a "Never mutate
version control" rule. Output must be purely additive test files.
- Add a no-revert/no-clean invariant to the implementer's edit boundaries.
- Add a 'workspace integrity' eval to the code-testing-agent suite
(eval.yaml + eval.vally.yaml). The fixture looks gutted: a metricsd project
whose real core/io modules are committed at HEAD but deleted from the
working tree, leaving only a synthetic 'synthstr' decoy. A git restore would
resurrect the deleted sentinel files; graders fail if they reappear and
require passing pytest tests for the module as delivered.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
||
|
Amaury Levé
|
a98fb44e52 |
code-testing-agent: pin down behavior in generated tests (#767)
Adds a new `Write Tests That Pin Down Behavior'' section to `unit-test-generation.prompt.md'' covering five universal test-craft principles: 1. Mutation thinking - each assertion would fail under a plausible bug 2. Property intersections - test combinations, not only coordinate axes 3. Behavior radius - assert on at least one secondary observable 4. Fixture realism - never set the parameter under test to a degenerate value 5. Quick self-review before declaring a test method done Mirrors the same depth requirements in `code-testing-implementer.agent.md'' Step 4 as a cross-language invariant block alongside the existing `Edit boundaries'' rules. Extends the existing `code-testing-agent'' eval rubrics (yaml and vally) with one or two depth-oriented bullets per scenario: * ContosoUniversity: minimal IsNotNull-only assertions + secondary observable check on controller actions * python-flask-tasks: minimal `is not None''-only assertions + at least one combined-property TaskService validation test * typescript-vitest-cart: minimal `toBeDefined''/`toBeTruthy''-only assertions + at least one intersection test (discount + tax + shipping together) Rationale and prior-art references in PR description. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Daniel Plaisted
|
8a437b1d4f |
Add anti-pattern for forking a project instance via <MSBuild> with path-neutral global properties (#770)
Adds msbuild-antipatterns AP-22 (in references/additional-antipatterns.md): using
the <MSBuild> task to build/publish a project with an extra global property that
does not change the output path forks a distinct instance sharing the same
OutputPath/IntermediateOutputPath as the instance the graph already builds,
causing duplicate builds and parallel-write races on PDBs, *.sourcelink, and
project.assets.json. Covers both shapes:
(a) a project re-invoking itself (publish-on-build), and
(b) project A invoking Build/Publish on another project B it consumes
(e.g. a test/layout project publishing a tool) — the more common trigger.
GOOD fixes: (a) static _IsPublishing + DependsOnTargets with a cycle guard;
(b) let the producer publish in its own build and have the consumer sequence it
with a non-output ProjectReference instead of re-publishing it. Also updates the
SKILL.md pointer (AP-16 through AP-22) and the quick-reference checklist.
Extends check-bin-obj-clash with the matching cause (self or cross-project
<MSBuild> Build/Publish with a path-neutral global property), binlog-based
detection via the evaluations/global-properties/double_writes tools, the two
fixes, and an _IsPublishing row in the global-properties table.
Adds eval coverage: a publish-on-build smell in the msbuild-antipatterns review
fixture (LibA.csproj) plus a matching rubric line in eval.yaml and eval.vally.yaml.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
||
|
Amaury Levé
|
76b4c73a39 |
Add find-untested-sources-polyglot skill (tree-sitter, 9 languages) (#735)
* Add find-untested-sources-polyglot skill (tree-sitter, 9 languages) Sibling of the C# find-untested-sources skill that uses tree-sitter (via tree-sitter-language-pack) to extract declarations + imports across Python, TS/JS, Go, Java, Rust, C#, and Ruby with no build step. Output schema mirrors the C# skill's so prompts can consume either tool. Pairing strategies per language: - Import resolution (Python module path, TS/JS relative ./../index.*, Go pkg/<name>.go, Java FQCN, Rust use::, Ruby require). - Identifier overlap (every >=4-char token in the test source is cross-referenced with the declared-name index). Smoke-tested on: - python-flask-tasks fixture: 8 source / 0 test, 8 untested. - typescript-vitest-cart fixture: 8 source / 0 test, 8 untested (node_modules pruned). - AITestAgent C# repo: 3138 source / 761 test, 1419 tested, 1719 untested, 15 orphan. - gh-skills Go repo: 14 source / 7 test, 8 tested, 6 untested, 0 orphan. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Polyglot: union structure+symbols for declarations (fixes Go types, Python methods) tree-sitter-language-pack's ProcessResult exposes two complementary views: - structure: top-level items (classes, functions, structs, traits) - symbols: flat declared-name list Neither alone is complete: - Go: structure has methods/functions but NOT 'type' declarations; symbols has the types. Without union, a test that references a struct name finds no matching source and the source is incorrectly marked untested. - Python: structure stops at top-level, symbols also lists nested methods. - Rust: structure has structs and impls; symbols has fn names inside impls. Fix: union both lists, then drop kind='module'/'namespace' (these are packaging items that would cause false positives, e.g. Java's tree-sitter output emits the package name 'com' as a Module). Verified across all 9 supported languages with synthetic source+test+orphan fixtures (python, javascript, typescript, tsx, go, java, rust, csharp, ruby): each fixture now reports tested=1, untested=1, orphan=0. Real-repo regression check (AITestAgent C#): tested 1419 -> 1429, untested 1719 -> 1709 (10 sources now correctly paired via types previously missing from the declared-name index). Orphan count unchanged at 15 (no false-positive pairings introduced). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address review feedback on find-untested-sources-polyglot Code fixes (find_untested_sources.py): - Java test-file detection: drop the `name.startswith("test")` clause so data files like `testdata.java` are no longer misclassified as tests. Keep the documented `*Test.java` / `*Tests.java` rule and the path segment heuristic. - C# test-file detection: tokenize the (PascalCase-preserving) stem and treat the file as a test only when the final word is `Test` or `Tests`. This correctly classifies `UserServiceTests.cs` while no longer misclassifying `Contest.cs`, `Latest.cs`, `Manifest.cs`. - Identifier-overlap pairing: iterate the test's referenced identifiers and do O(1) lookups in `by_decl` instead of scanning every declaration in the index. Pairing is now O(#test_identifiers) per test instead of O(#decls × #tests) across the run, which matters on large repos. - JS/TS relative-import normalization: collapse `<seg>/../` segments in a fixed-point loop instead of a single regex pass so chained imports like `../../foo` and `a/b/../../c` resolve fully. Doc fix (SKILL.md): - Clarify that `symbols` is unioned with `structure` rather than being used only as a fallback when `structure` is empty, matching the actual parse_file implementation. - Tighten description to stay within the per-skill (1,024 chars) and plugin aggregate (20,000 chars) limits enforced by skill-validator. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Allow tree-sitter.github.io in known-domains for find-untested-sources-polyglot The polyglot skill's SKILL.md links to https://tree-sitter.github.io/ for the tree-sitter project; add the domain to eng/known-domains.txt so the skill-validator reference scanner stops failing with EXTERNAL-DOMAIN. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address PR #735 review feedback (round 2) - parse_file: log a stderr WARN when tree-sitter parsing throws instead of silently returning a 0-declaration FileInfo, so users can see when results are degraded by parser failures. - Python relative imports: _python_module_to_path now respects PEP 328 leading dots, resolving 'from .utils import x' against the test file's package rather than treating it as an absolute 'utils.py' at repo root. Returns an empty candidate set when no test context is available or when the imported name isn't captured ('from . import x'), to avoid false-positive pairings. - Go import resolution: _build_indexes now produces a by_filename index, and _resolve_test_imports looks up '<pkg>.go' in O(1) per import instead of scanning every source path for each import target. - tested_sources: emit sorted by path for deterministic JSON output across runs (matches the existing sort on untested_sources / orphan_tests). - SKILL.md: JS/TS test-detection row now lists the 'test' path segment to match the implementation. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
d0924d4f17 |
Add find-untested-sources skill (C# parse-only test pairing) (#733)
* find-untested-sources: C# static test-pairing prototype Parse-only Roslyn analysis that maps C# source files to the test files referencing their declared types and lists production sources with no referring test. No Compilation, no MetadataReferences, no binding. - File discovery prunes bin/obj/node_modules/.git and generated *.g.cs. - Test classification by .csproj suffix or test-SDK reference. - Source index records (ShortName, Namespace, FilePath) per parsed file. - Test scan walks IdentifierTokens, disambiguates strictly against the test file's using directives + enclosing namespace. - Suggests a test-file path by mirroring the source under the test project that already <ProjectReference>s the source's project. Runs in ~9s on a ~3,900 .cs-file repo (AITestAgent + msbench fixtures). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address review feedback on find-untested-sources Code fixes (Find-UntestedSources.cs): - ProjectFor: sort .csproj matches and wrap enumeration in try/catch so selection is deterministic when a directory contains multiple project files. - GetNamespaceFor: walk all enclosing namespace declarations and join from outermost to innermost so nested namespace blocks (namespace A { namespace B { ... } }) return "A.B" rather than just "B". - Test scan: stop unconditionally skipping global-namespace declarations. Global types are visible without a using directive, so accept them as visible to any test file. Previously, types without a namespace were never attributed to any test and always reported as untested. - BuildProductionToTestProjectMap: sort the recursive .csproj enumeration and wrap in try/catch so the "first write wins" rule selects the same test project across runs/machines regardless of filesystem ordering. - IsSkippedFile: switch suffix comparisons to OrdinalIgnoreCase and collapse the five if statements into a single loop over an array. Skill metadata (SKILL.md): - Tighten the description so the skill stays under the 1,024-character per-skill limit and the dotnet-test plugin stays under the 20,000-char aggregate limit enforced by skill-validator. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Amaury Levé
|
d9c1e7a801 |
code-testing-agent: mention find-untested-sources for C# discovery (#734)
* code-testing-agent: mention find-untested-sources for C# discovery Adds a conditional pointer (gated on 'when available') to the find-untested-sources skill in two places: - SKILL.md Step 3 (Research Phase): high-level note for C# / .NET multi-file scopes — prefer the helper over manual find/grep/glob walks. - code-testing-researcher.agent.md Section 7 (Discover Preexisting Tests): directive instruction telling the researcher to invoke the helper before manually pairing source <-> test files, and to use its source_to_tests / untested output to fill the research document. Both callouts are phrased as 'when available', so installations without the find-untested-sources skill continue to work via manual discovery. Adds no behavior for non-C# repos. Context: in a 5x136-instance internal experiment on the msbench .NET test bench, adding equivalent pointers to the routed code-testing-agent yielded a 15.67% input-token reduction at neutral pass rate — the model trusted the documented pairing heuristics and skipped its own discovery walk. The helper itself was not invoked in those runs (the Copilot CLI router did not auto-load the sibling skill), so the measured win comes from the doc text causing the model to short-circuit its manual exploration, not from the helper executing. Depends on dotnet/skills#733 (which adds the find-untested-sources skill itself). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * code-testing-agent eval: grade find-untested-sources usage on C# scenario PR #734 adds a doc pointer steering the researcher toward the `find-untested-sources` skill on .NET / C# multi-file tasks. The existing ContosoUniversity scenario is the natural fit: it's the only C# multi-file scenario in this eval, and the new pointer is .NET- scoped. Add one rubric item to that scenario (in both eval.vally.yaml and the legacy eval.yaml) asking the grader to verify the researcher actually leveraged the helper — either by citing its `source_to_tests` / `untested` JSON output in `.testagent/research.md`, or by executing `scripts/Find-UntestedSources.cs` — instead of falling back to manual `find` / `grep` / `glob` walks. Gated on `when available in the workspace` to match the SKILL.md wording, so installs without find-untested-sources are not penalized. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |