diff --git a/docs/campaign-summary-chart.md b/docs/campaign-summary-chart.md
index 142cbb721..4d5f533df 100644
--- a/docs/campaign-summary-chart.md
+++ b/docs/campaign-summary-chart.md
@@ -46,6 +46,13 @@ two-point default, because it records the whole campaign rather than one
pairing. When neither exists, the report states why no figure was drawn
instead of showing an empty chart.
+For runs with `--require-trial-check`, chart generation also requires the
+evaluator to publish a comparison in `improvement_pct`. If the checks or the
+paired measurements are incomplete, the report labels the medians as raw
+measurements and omits both the default and campaign figures. The historical
+`summary-chart.json` stays intact. Rebuilding a report removes a previously
+generated `summary-chart.svg` when the current evaluation cannot support it.
+
## Use the command line for a campaign figure
```bash
diff --git a/docs/contributing.md b/docs/contributing.md
index fea0281b7..27319aaf8 100644
--- a/docs/contributing.md
+++ b/docs/contributing.md
@@ -263,3 +263,7 @@ template's copy, validation and catalog-registration steps. Missing hardware
verification remains explicit. Workbench experiments use the
[quickstart](quickstart.md) and [evidence template](../evidence/_template/);
the four CI lanes retain their current roles.
+
+For feedback-coupled models, stochastic audio and streaming/graph experiments,
+use the [Omni experiment contract](../src/inferrsi/data/skill_library/workflows/rsi-evidence/references/omni-experiments.md) to select
+reference, preflight and executable per-trial qualification checks.
diff --git a/docs/operations.md b/docs/operations.md
index 9614db4f2..be908e976 100644
--- a/docs/operations.md
+++ b/docs/operations.md
@@ -221,7 +221,7 @@ unvalidated candidates.
- **Inputs:** one JSON specification (chain of accumulating steps, or a set of independent trials); an output path.
- **Scope:** recorded values only. The renderer computes gains, validates the specification and writes a figure; it measures nothing.
-- **Output:** an SVG figure, plus a Markdown table with the same values when `--markdown` is given. `report` and `run` also write `summary-chart.svg` into the run directory and inline it in the HTML report.
+- **Output:** an SVG figure, plus a Markdown table with the same values when `--markdown` is given. `report` and `run` also write `summary-chart.svg` into the run directory and inline it in the HTML report. When selected trial checks leave the current comparison incomplete, the report omits the figure (including a campaign specification) and removes any previously generated SVG; raw measurements and the campaign JSON remain available.
- **Side effects:** writes the requested files; nothing is executed and no network or GPU is touched.
- **Failure behavior:** exit code 2 with the offending field name when the specification is incomplete, ambiguous or inconsistent; a report without a paired measurement states why it has no figure.
- **Example:** [campaign summary chart](campaign-summary-chart.md)
diff --git a/docs/quickstart.md b/docs/quickstart.md
index 8eee9cbfe..24d2fda79 100644
--- a/docs/quickstart.md
+++ b/docs/quickstart.md
@@ -93,6 +93,7 @@ plan/run: all doctor flags, plus
--candidate-repo --scenario --mode --agent --executor local
--baseline-command --candidate-command --validation-command
--metric-key --metric-unit --comparison-scope --direction
+ --require-trial-check (repeatable dotted boolean qualification key)
--repetitions --min-improvement-pct --max-minutes
--workload-id --model --model-revision --output-dir --dry-run
status/report: --run-id --output-dir
@@ -176,3 +177,7 @@ or `--tier peer`. Export one source explicitly, for example
`--repo-type` names the source owner; vllm_omni queries do not automatically
include its dependencies or peers. See the
[three-tier guide](../src/inferrsi/data/knowledge_packs/README.md) for all sources.
+
+For per-trial completeness, lifecycle and graph qualification, see the
+[Omni experiment contract](../src/inferrsi/data/skill_library/workflows/rsi-evidence/references/omni-experiments.md). These optional checks
+are frozen in RunSpec and do not replace the quality command.
diff --git a/docs/skill-coverage.md b/docs/skill-coverage.md
index 94f2dabc6..c327fb337 100644
--- a/docs/skill-coverage.md
+++ b/docs/skill-coverage.md
@@ -4,7 +4,7 @@ Generated from the registry, the skill sidecars and the two maintained
matrices. **Do not edit by hand**; regenerate after any registry, skill,
matrix or frozen-plan change.
-- Input digest: `sha256:ec4e4b8fbed28d0883fc54ba7bfaf6a76ee0a5f1f28774448f3b49ebed8addb9`
+- Input digest: `sha256:f3358ad6ec7526a64d17fa293e937aaa648efa88b7efb485deb98f9f08d07fae`
- Regenerate: `python tools/build_skill_coverage.py`
- Verify without writing: `python tools/build_skill_coverage.py --check`
@@ -154,7 +154,7 @@ optimization is fully covered or that any procedure has measured benefit.
| [competitor-scan](../src/inferrsi/data/skill_library/workflows/competitor-scan/SKILL.md) | common | Structure a lightweight competitive scan without inventing benchmark numbers or campaign verdicts. | Qualitative positioning of a new RSI repository against other projects before acceptance ... | failure_modes, input_contract, produced_artifact, refusal_point
3 advice | N/A: SKILL.md §§ Frame, Rules and Deliverable produce a qualitative competitive comparison with evidence limits, not a hardware-resource decision or implementation mechanism. | — | candidate · not_run · 0 readset(s) | no-Reference-Matrix-row, no-eval |
| [draft-acceptance-issue](../src/inferrsi/data/skill_library/workflows/draft-acceptance-issue/SKILL.md) | common | Draft a campaign acceptance issue with checklist, RunSpec, evidence paths, and placeholders for baseline/candidate SHAs. | Opening a new acceptance campaign in an RSI-style repository, before any baseline or ... | failure_modes, input_contract, produced_artifact, refusal_point
3 advice | N/A: SKILL.md §§ Steps and Output prepare an acceptance issue, RunSpec, frozen gates and evidence paths; device identifiers are campaign metadata rather than a hardware-resource mechanism. | — | candidate · not_run · 0 readset(s) | no-Reference-Matrix-row, no-eval |
| [npu-skill-factory](../src/inferrsi/data/skill_library/workflows/npu-skill-factory/SKILL.md) | common | Design and operation of the InferRSI NPU skill factory: artifact lifecycle, skill evaluation contract, corpus ... | InferRSI skill lifecycle management | failure_modes, input_contract, produced_artifact, refusal_point
3 advice | N/A: SKILL.md §§ Choose the evidence product, Artifact lifecycle, and What this skill does not do define skill-distillation/evaluation methodology; NPU task tiers are evaluation prerequisites, not a hardware-resource mechanism. | 2 · Methodology and corpus references (Dong1017/OmniRSI @ `codex/skill-eval-bootstrap` (82218b4))
2 · Methodology and corpus references (InferMatrixLab/InferRSI PR #9 @ 4ad551a9)
2 · Methodology and corpus references (VectorSpaceLab/AREX-Skill @ ac3fe1af)
2 · Methodology and corpus references (microsoft/SkillOpt @ 343db22) | candidate · not_run · 14 readset(s) | no-eval |
-| [rsi-evidence](../src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md) | common | Guide agents to publish and cite RSI evidence using plan/results/patch/validator paths and PASS/FAIL/INCONCLUSIVE ... | Documenting or reviewing an optimization campaign whose verdict will be cited downstream | failure_modes, input_contract, produced_artifact, refusal_point
4 advice | 1 Accelerator · Verify | — | candidate · not_run · 1 readset(s) | no-Reference-Matrix-row, no-eval |
+| [rsi-evidence](../src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md) | common | Guide agents to publish and cite RSI evidence using plan/results/patch/validator paths and PASS/FAIL/INCONCLUSIVE ... | Documenting or reviewing an optimization campaign whose verdict will be cited downstream | failure_modes, input_contract, produced_artifact, refusal_point
5 advice | 1 Accelerator · Verify | — | candidate · not_run · 1 readset(s) | no-Reference-Matrix-row, no-eval |
## Documents outside the registry
diff --git a/src/inferrsi/arguments.py b/src/inferrsi/arguments.py
index 46b5e9336..ea7f4907b 100644
--- a/src/inferrsi/arguments.py
+++ b/src/inferrsi/arguments.py
@@ -86,6 +86,10 @@ def parser() -> argparse.ArgumentParser:
default="metrics.latency_ms",
help="Flat or dotted key in benchmark JSON",
)
+ child.add_argument(
+ "--require-trial-check", action="append", default=[], metavar="DOTTED_KEY",
+ help="Require a literal true qualification field in every benchmark JSON; repeatable",
+ )
child.add_argument("--metric-unit", default="ms")
child.add_argument("--comparison-scope", default="external_command")
child.add_argument("--direction", choices=("minimize", "maximize"), default="minimize")
@@ -291,6 +295,7 @@ def command(value: str | None) -> tuple[str, ...] | None:
candidate_command=command(args.candidate_command),
validation_command=command(args.validation_command),
metric_key=args.metric_key,
+ required_trial_checks=tuple(args.require_trial_check),
metric_unit=args.metric_unit,
comparison_scope=args.comparison_scope,
direction=args.direction,
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/README.md b/src/inferrsi/data/repo_packs/inferrsi/knowledge/README.md
index 6606497ad..41ea29e6d 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/README.md
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/README.md
@@ -15,7 +15,7 @@ These are knowledge abstracts (`--kind knowledge`), with namespaced package
IDs distinct from explicitly selected `checkout_ref` skills. Ascend/CUDA
procedures use their corresponding backend; shared methods use `common`.
-Source snapshot: [2c766dbc95605e61b907ce71418ab941287b427a](https://github.com/InferMatrixLab/InferRSI/tree/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library).
+Source snapshot: [1e87be46b8d080d439bb516ed9fa9092f8306f62](https://github.com/InferMatrixLab/InferRSI/tree/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library).
```bash
inferrsi knowledge search 'profiling' --repo-type inferrsi --limit 50
@@ -29,7 +29,7 @@ contain the current input paths and bytes (Git checkout filters are respected).
```bash
python tools/build_skill_index.py --source-revision
-python tools/build_skill_index.py --source-revision 2c766dbc95605e61b907ce71418ab941287b427a --check
+python tools/build_skill_index.py --source-revision 1e87be46b8d080d439bb516ed9fa9092f8306f62 --check
```
`--check` detects missing, stale and unexpected generated records without writing.
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-aclgraph-capture-replay.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-aclgraph-capture-replay.json
index 7bb783ee1..49a1b33ec 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-aclgraph-capture-replay.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-aclgraph-capture-replay.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-device-health.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-device-health.json
index c6504249c..5475a6192 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-device-health.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-device-health.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-distributed-parallel.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-distributed-parallel.json
index 31202f693..f44a0c6fc 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-distributed-parallel.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-distributed-parallel.json
@@ -27,8 +27,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-graph-mode.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-graph-mode.json
index 4c2c71c5a..759b002fc 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-graph-mode.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-graph-mode.json
@@ -26,8 +26,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-model-adaptation.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-model-adaptation.json
index cc4d29945..6590af696 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-model-adaptation.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-model-adaptation.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-profiling.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-profiling.json
index 60e9249b8..f7a87ffc6 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-profiling.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-profiling.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-tuning.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-tuning.json
index dd4548a4e..a71afd0d2 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-tuning.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-tuning.json
@@ -24,8 +24,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-optimization-casebook.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-optimization-casebook.json
index 791575c92..17aa4ec22 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-optimization-casebook.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-optimization-casebook.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/ascend/ascend-optimization-casebook/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/ascend/ascend-optimization-casebook/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-optimization-casebook/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-optimization-casebook/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-performance-analysis.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-performance-analysis.json
index 3741812f8..2a7cbd1c5 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-performance-analysis.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-performance-analysis.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/ascend/ascend-performance-analysis/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/ascend/ascend-performance-analysis/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-performance-analysis/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-performance-analysis/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-video-diffusion-optimization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-video-diffusion-optimization.json
index 695873ad7..6f02a2d11 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-video-diffusion-optimization.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-video-diffusion-optimization.json
@@ -26,8 +26,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/ascend/ascend-video-diffusion-optimization/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/ascend/ascend-video-diffusion-optimization/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascend-video-diffusion-optimization/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascend-video-diffusion-optimization/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascendc-tiling-design.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascendc-tiling-design.json
index 004d93f5b..9d5729069 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascendc-tiling-design.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascendc-tiling-design.json
@@ -24,8 +24,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/ascend/ascendc-tiling-design/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/ascend/ascendc-tiling-design/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/ascendc-tiling-design/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/ascendc-tiling-design/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/cann-attribution-overlap.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/cann-attribution-overlap.json
index 88832eecd..3603ab46d 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/cann-attribution-overlap.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/cann-attribution-overlap.json
@@ -24,8 +24,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/ascend/cann-attribution-overlap/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/ascend/cann-attribution-overlap/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/cann-attribution-overlap/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/cann-attribution-overlap/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torch-npu.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torch-npu.json
index 15f3b9134..b3aaf6019 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torch-npu.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torch-npu.json
@@ -20,8 +20,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/frameworks/torch-npu/torch-npu/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/frameworks/torch-npu/torch-npu/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/frameworks/torch-npu/torch-npu/SKILL.md",
"src/inferrsi/data/skill_library/frameworks/torch-npu/torch-npu/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-device-memory-lifecycle.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-device-memory-lifecycle.json
index c3c2409dd..732ac06dc 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-device-memory-lifecycle.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-device-memory-lifecycle.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/ascend/torchnpu-device-memory-lifecycle/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/ascend/torchnpu-device-memory-lifecycle/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/torchnpu-device-memory-lifecycle/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/torchnpu-device-memory-lifecycle/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-pinned-host-memory-lifecycle.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-pinned-host-memory-lifecycle.json
index 56f694329..09f8a23eb 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-pinned-host-memory-lifecycle.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/torchnpu-pinned-host-memory-lifecycle.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/ascend/torchnpu-pinned-host-memory-lifecycle/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/ascend/torchnpu-pinned-host-memory-lifecycle/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/ascend/torchnpu-pinned-host-memory-lifecycle/SKILL.md",
"src/inferrsi/data/skill_library/hardware/ascend/torchnpu-pinned-host-memory-lifecycle/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/vllm-ascend.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/vllm-ascend.json
index 575baee09..94c56179f 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/vllm-ascend.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/vllm-ascend.json
@@ -39,8 +39,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/vllm-ascend/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/vllm-ascend/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/vllm-ascend/SKILL.md",
"src/inferrsi/data/skill_library/repositories/vllm-ascend/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-serving-preemption.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-serving-preemption.json
index ee535de6f..f87b9e7e9 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-serving-preemption.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-serving-preemption.json
@@ -16,8 +16,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/assess-serving-preemption/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/assess-serving-preemption/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/assess-serving-preemption/SKILL.md",
"src/inferrsi/data/skill_library/methods/assess-serving-preemption/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-split-backward-schedule.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-split-backward-schedule.json
index 0c6065b49..72f7896f3 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-split-backward-schedule.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/assess-split-backward-schedule.json
@@ -16,8 +16,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/assess-split-backward-schedule/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/assess-split-backward-schedule/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/assess-split-backward-schedule/SKILL.md",
"src/inferrsi/data/skill_library/methods/assess-split-backward-schedule/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-fixed-workload-claim.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-fixed-workload-claim.json
index 02911f435..9a09007f3 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-fixed-workload-claim.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-fixed-workload-claim.json
@@ -20,8 +20,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/audit-fixed-workload-claim/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/audit-fixed-workload-claim/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/audit-fixed-workload-claim/SKILL.md",
"src/inferrsi/data/skill_library/methods/audit-fixed-workload-claim/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-metal-fasth3-semantics.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-metal-fasth3-semantics.json
index 968772f87..fee30b7bd 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-metal-fasth3-semantics.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-metal-fasth3-semantics.json
@@ -29,8 +29,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/h3-metal/audit-h3-metal-fasth3-semantics/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/h3-metal/audit-h3-metal-fasth3-semantics/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/h3-metal/audit-h3-metal-fasth3-semantics/LICENSE",
"src/inferrsi/data/skill_library/repositories/h3-metal/audit-h3-metal-fasth3-semantics/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-runtime-residency.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-runtime-residency.json
index f0659a0f5..ff4856eb9 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-runtime-residency.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-h3-runtime-residency.json
@@ -30,8 +30,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/h3-c/audit-h3-runtime-residency/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/h3-c/audit-h3-runtime-residency/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/h3-c/audit-h3-runtime-residency/LICENSE",
"src/inferrsi/data/skill_library/repositories/h3-c/audit-h3-runtime-residency/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-llama-runtime-state.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-llama-runtime-state.json
index 9719f7568..d9049e0b2 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-llama-runtime-state.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-llama-runtime-state.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/llama-cpp/audit-llama-runtime-state/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/llama-cpp/audit-llama-runtime-state/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/llama-cpp/audit-llama-runtime-state/SKILL.md",
"src/inferrsi/data/skill_library/repositories/llama-cpp/audit-llama-runtime-state/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-recurrent-kv-finalization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-recurrent-kv-finalization.json
index 6fb906b7c..d210e22c7 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-recurrent-kv-finalization.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-recurrent-kv-finalization.json
@@ -26,8 +26,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/vllm-rlt/audit-recurrent-kv-finalization/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/vllm-rlt/audit-recurrent-kv-finalization/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/vllm-rlt/audit-recurrent-kv-finalization/LICENSE",
"src/inferrsi/data/skill_library/repositories/vllm-rlt/audit-recurrent-kv-finalization/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sd-cpp-residency.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sd-cpp-residency.json
index fbd8bd60d..0be1ec772 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sd-cpp-residency.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sd-cpp-residency.json
@@ -25,8 +25,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/stable-diffusion-cpp/audit-sd-cpp-residency/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/stable-diffusion-cpp/audit-sd-cpp-residency/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/stable-diffusion-cpp/audit-sd-cpp-residency/LICENSE",
"src/inferrsi/data/skill_library/repositories/stable-diffusion-cpp/audit-sd-cpp-residency/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sglang-diffusion-lifetimes.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sglang-diffusion-lifetimes.json
index 420d4e4ac..dfab8adc4 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sglang-diffusion-lifetimes.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-sglang-diffusion-lifetimes.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/sglang/audit-sglang-diffusion-lifetimes/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/sglang/audit-sglang-diffusion-lifetimes/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/sglang/audit-sglang-diffusion-lifetimes/LICENSE",
"src/inferrsi/data/skill_library/repositories/sglang/audit-sglang-diffusion-lifetimes/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-vllm-kv-lifetimes.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-vllm-kv-lifetimes.json
index 24c5c6b95..cab1bdde7 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-vllm-kv-lifetimes.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/audit-vllm-kv-lifetimes.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/vllm/audit-vllm-kv-lifetimes/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/vllm/audit-vllm-kv-lifetimes/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/vllm/audit-vllm-kv-lifetimes/SKILL.md",
"src/inferrsi/data/skill_library/repositories/vllm/audit-vllm-kv-lifetimes/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/bound-windowed-attention-replay.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/bound-windowed-attention-replay.json
index a2ffa8d8d..940fc1229 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/bound-windowed-attention-replay.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/bound-windowed-attention-replay.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/deepinfer/bound-windowed-attention-replay/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/deepinfer/bound-windowed-attention-replay/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/deepinfer/bound-windowed-attention-replay/SKILL.md",
"src/inferrsi/data/skill_library/repositories/deepinfer/bound-windowed-attention-replay/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/budget-speculative-verification.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/budget-speculative-verification.json
index 93a89d93d..999eba3b1 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/budget-speculative-verification.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/budget-speculative-verification.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/deepinfer/budget-speculative-verification/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/deepinfer/budget-speculative-verification/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/deepinfer/budget-speculative-verification/SKILL.md",
"src/inferrsi/data/skill_library/repositories/deepinfer/budget-speculative-verification/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/calibrate-serving-simulation.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/calibrate-serving-simulation.json
index e471124f0..95db942cc 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/calibrate-serving-simulation.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/calibrate-serving-simulation.json
@@ -16,8 +16,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/calibrate-serving-simulation/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/calibrate-serving-simulation/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/calibrate-serving-simulation/SKILL.md",
"src/inferrsi/data/skill_library/methods/calibrate-serving-simulation/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cgroup-resource-controls.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cgroup-resource-controls.json
index 9e26ff24d..f3e54d518 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cgroup-resource-controls.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cgroup-resource-controls.json
@@ -25,8 +25,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/host/cgroup-resource-controls/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/host/cgroup-resource-controls/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/host/cgroup-resource-controls/SKILL.md",
"src/inferrsi/data/skill_library/hardware/host/cgroup-resource-controls/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/checkpoint-recovery-consistency.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/checkpoint-recovery-consistency.json
index ecaedf415..9c2e8444b 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/checkpoint-recovery-consistency.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/checkpoint-recovery-consistency.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/checkpoint-recovery-consistency/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/checkpoint-recovery-consistency/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/checkpoint-recovery-consistency/SKILL.md",
"src/inferrsi/data/skill_library/methods/checkpoint-recovery-consistency/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/choose-parallel-training-plan.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/choose-parallel-training-plan.json
index 7537a657e..f59de37dc 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/choose-parallel-training-plan.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/choose-parallel-training-plan.json
@@ -16,8 +16,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/SKILL.md",
"src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cite-check-downstream-pr.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cite-check-downstream-pr.json
index 25f3adfa8..972257d8f 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cite-check-downstream-pr.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/cite-check-downstream-pr.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/workflows/cite-check-downstream-pr/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/workflows/cite-check-downstream-pr/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/skill-index.json",
"src/inferrsi/data/skill_library/workflows/cite-check-downstream-pr/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/claim-contract.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/claim-contract.json
index 194b5f12c..2e1bad2bf 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/claim-contract.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/claim-contract.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/workflows/claim-contract/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/workflows/claim-contract/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/skill-index.json",
"src/inferrsi/data/skill_library/workflows/claim-contract/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/comfy-ui.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/comfy-ui.json
index a64da20cb..535de5aa2 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/comfy-ui.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/comfy-ui.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/comfy-ui/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/comfy-ui/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/comfy-ui/LICENSE",
"src/inferrsi/data/skill_library/repositories/comfy-ui/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/competitor-scan.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/competitor-scan.json
index 41b6231f1..0aede0ac3 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/competitor-scan.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/competitor-scan.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/workflows/competitor-scan/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/workflows/competitor-scan/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/skill-index.json",
"src/inferrsi/data/skill_library/workflows/competitor-scan/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dcp-async-save-performance.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dcp-async-save-performance.json
index ff8e066a2..59fde0772 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dcp-async-save-performance.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dcp-async-save-performance.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/frameworks/pytorch/dcp-async-save-performance/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/frameworks/pytorch/dcp-async-save-performance/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/frameworks/pytorch/dcp-async-save-performance/SKILL.md",
"src/inferrsi/data/skill_library/frameworks/pytorch/dcp-async-save-performance/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dense-performance-evidence.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dense-performance-evidence.json
index 2aa811834..fd974be51 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dense-performance-evidence.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dense-performance-evidence.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/dense-performance-evidence/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/dense-performance-evidence/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/dense-performance-evidence/SKILL.md",
"src/inferrsi/data/skill_library/methods/dense-performance-evidence/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diagnose-vllm-admission-pressure.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diagnose-vllm-admission-pressure.json
index b756891af..a58908e46 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diagnose-vllm-admission-pressure.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diagnose-vllm-admission-pressure.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/vllm/diagnose-vllm-admission-pressure/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/vllm/diagnose-vllm-admission-pressure/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/vllm/diagnose-vllm-admission-pressure/SKILL.md",
"src/inferrsi/data/skill_library/repositories/vllm/diagnose-vllm-admission-pressure/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diffusers-invocation-state.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diffusers-invocation-state.json
index 3849a3662..b6a6d3306 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diffusers-invocation-state.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/diffusers-invocation-state.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/frameworks/diffusers/diffusers-invocation-state/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/frameworks/diffusers/diffusers-invocation-state/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/frameworks/diffusers/diffusers-invocation-state/SKILL.md",
"src/inferrsi/data/skill_library/frameworks/diffusers/diffusers-invocation-state/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/draft-acceptance-issue.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/draft-acceptance-issue.json
index 0548b5c7b..843d09712 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/draft-acceptance-issue.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/draft-acceptance-issue.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/workflows/draft-acceptance-issue/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/workflows/draft-acceptance-issue/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/skill-index.json",
"src/inferrsi/data/skill_library/workflows/draft-acceptance-issue/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dwarfstar.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dwarfstar.json
index 5ba8d5e03..27ab7e056 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dwarfstar.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/dwarfstar.json
@@ -25,8 +25,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/dwarfstar/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/dwarfstar/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/dwarfstar/LICENSE",
"src/inferrsi/data/skill_library/repositories/dwarfstar/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/evaluate-elastic-serving-placement.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/evaluate-elastic-serving-placement.json
index c9ba4128c..5a9adf9f8 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/evaluate-elastic-serving-placement.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/evaluate-elastic-serving-placement.json
@@ -16,8 +16,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/SKILL.md",
"src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/generation-cache-lifecycle.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/generation-cache-lifecycle.json
index 6097f698a..15aefe895 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/generation-cache-lifecycle.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/generation-cache-lifecycle.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/mlx-lm/generation-cache-lifecycle/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/mlx-lm/generation-cache-lifecycle/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/mlx-lm/generation-cache-lifecycle/SKILL.md",
"src/inferrsi/data/skill_library/repositories/mlx-lm/generation-cache-lifecycle/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-memory-management.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-memory-management.json
index 2a2d71694..8c4c04ff3 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-memory-management.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-memory-management.json
@@ -30,8 +30,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/host/host-memory-management/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/host/host-memory-management/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/host/host-memory-management/SKILL.md",
"src/inferrsi/data/skill_library/hardware/host/host-memory-management/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-overhead-optimization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-overhead-optimization.json
index bb64d8f49..e39d04a62 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-overhead-optimization.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/host-overhead-optimization.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/host/host-overhead-optimization/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/host/host-overhead-optimization/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/host/host-overhead-optimization/SKILL.md",
"src/inferrsi/data/skill_library/hardware/host/host-overhead-optimization/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/husky.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/husky.json
index d87cfbc05..a8098d4fc 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/husky.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/husky.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/husky/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/husky/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/husky/SKILL.md",
"src/inferrsi/data/skill_library/repositories/husky/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-benchmark-design.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-benchmark-design.json
index c4db748ee..03dbe9942 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-benchmark-design.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-benchmark-design.json
@@ -35,8 +35,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md",
"src/inferrsi/data/skill_library/methods/inference-benchmark-design/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-optimization-casebook.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-optimization-casebook.json
index 70ade38dd..a9c3d12fb 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-optimization-casebook.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/inference-optimization-casebook.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/inference-optimization-casebook/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/inference-optimization-casebook/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/inference-optimization-casebook/SKILL.md",
"src/inferrsi/data/skill_library/methods/inference-optimization-casebook/cases/admission-drain-occupancy.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kernel-writing-guide.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kernel-writing-guide.json
index 9a465b2a4..49c81997d 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kernel-writing-guide.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kernel-writing-guide.json
@@ -39,8 +39,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/kernel-writing-guide/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/kernel-writing-guide/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/kernel-writing-guide/SKILL.md",
"src/inferrsi/data/skill_library/methods/kernel-writing-guide/cases/causal-conv1d-dispatch-state.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kv-tier-management.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kv-tier-management.json
index 49e26c7c5..12b6973dd 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kv-tier-management.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/kv-tier-management.json
@@ -24,8 +24,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/lmcache/kv-tier-management/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/lmcache/kv-tier-management/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/lmcache/kv-tier-management/SKILL.md",
"src/inferrsi/data/skill_library/repositories/lmcache/kv-tier-management/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lazy-evaluation-stream-lifetimes.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lazy-evaluation-stream-lifetimes.json
index 89a05a4cb..a174e6989 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lazy-evaluation-stream-lifetimes.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lazy-evaluation-stream-lifetimes.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/frameworks/mlx/lazy-evaluation-stream-lifetimes/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/frameworks/mlx/lazy-evaluation-stream-lifetimes/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/frameworks/mlx/lazy-evaluation-stream-lifetimes/SKILL.md",
"src/inferrsi/data/skill_library/frameworks/mlx/lazy-evaluation-stream-lifetimes/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lily.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lily.json
index ad48f3f8c..3d7797f97 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lily.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lily.json
@@ -25,8 +25,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/lily/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/lily/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/lily/LICENSE",
"src/inferrsi/data/skill_library/repositories/lily/NOTICE.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lithos-metal.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lithos-metal.json
index 796de0f20..a950e5f4f 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lithos-metal.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/lithos-metal.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/lithos-metal/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/lithos-metal/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/lithos-metal/LICENSE",
"src/inferrsi/data/skill_library/repositories/lithos-metal/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/local-dream.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/local-dream.json
index fdcb41f58..6a0909e46 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/local-dream.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/local-dream.json
@@ -29,8 +29,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/local-dream/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/local-dream/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/local-dream/SKILL.md",
"src/inferrsi/data/skill_library/repositories/local-dream/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mistral-rs.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mistral-rs.json
index c77c3ad61..64e0cd9c5 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mistral-rs.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mistral-rs.json
@@ -26,8 +26,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/mistral-rs/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/mistral-rs/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/mistral-rs/LICENSE",
"src/inferrsi/data/skill_library/repositories/mistral-rs/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlc-llm.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlc-llm.json
index 2246e6844..bf8da38e0 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlc-llm.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlc-llm.json
@@ -27,8 +27,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/mlc-llm/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/mlc-llm/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/mlc-llm/LICENSE",
"src/inferrsi/data/skill_library/repositories/mlc-llm/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlx-swift-lm.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlx-swift-lm.json
index 4002c229b..fe52ef0bf 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlx-swift-lm.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/mlx-swift-lm.json
@@ -27,8 +27,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/mlx-swift-lm/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/mlx-swift-lm/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/mlx-swift-lm/LICENSE",
"src/inferrsi/data/skill_library/repositories/mlx-swift-lm/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/npu-skill-factory.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/npu-skill-factory.json
index a1389e3a2..657681f03 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/npu-skill-factory.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/npu-skill-factory.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/workflows/npu-skill-factory/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/workflows/npu-skill-factory/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/skill-index.json",
"src/inferrsi/data/skill_library/workflows/npu-skill-factory/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/optimization-search-policy.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/optimization-search-policy.json
index df9ec0bb2..775cfac19 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/optimization-search-policy.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/optimization-search-policy.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/optimization-search-policy/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/optimization-search-policy/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/optimization-search-policy/SKILL.md",
"src/inferrsi/data/skill_library/methods/optimization-search-policy/cases/sarathi-chunk-budget.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/os-process-placement.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/os-process-placement.json
index a0c321a90..c14191627 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/os-process-placement.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/os-process-placement.json
@@ -24,8 +24,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/host/os-process-placement/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/host/os-process-placement/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/host/os-process-placement/SKILL.md",
"src/inferrsi/data/skill_library/hardware/host/os-process-placement/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/performance-ceiling-analysis.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/performance-ceiling-analysis.json
index 7d10ede98..2d265a596 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/performance-ceiling-analysis.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/performance-ceiling-analysis.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/SKILL.md",
"src/inferrsi/data/skill_library/methods/performance-ceiling-analysis/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/plan-activation-residency.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/plan-activation-residency.json
index 52274f0af..1f1ea1ac1 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/plan-activation-residency.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/plan-activation-residency.json
@@ -16,8 +16,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/plan-activation-residency/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/plan-activation-residency/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/plan-activation-residency/SKILL.md",
"src/inferrsi/data/skill_library/methods/plan-activation-residency/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/project-maya.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/project-maya.json
index 6116cbd80..738b64c3e 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/project-maya.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/project-maya.json
@@ -25,8 +25,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/project-maya/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/project-maya/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/project-maya/LICENSE",
"src/inferrsi/data/skill_library/repositories/project-maya/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/pytorch.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/pytorch.json
index f8c006822..62d48da31 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/pytorch.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/pytorch.json
@@ -24,8 +24,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/LICENSE",
"src/inferrsi/data/skill_library/frameworks/pytorch/pytorch/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/repository-evolution-analysis.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/repository-evolution-analysis.json
index a7536f233..83b31c60b 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/repository-evolution-analysis.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/repository-evolution-analysis.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/repository-evolution-analysis/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/repository-evolution-analysis/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/repository-evolution-analysis/SKILL.md",
"src/inferrsi/data/skill_library/methods/repository-evolution-analysis/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/rsi-evidence.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/rsi-evidence.json
index 7c0d118a4..9a89e64c6 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/rsi-evidence.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/rsi-evidence.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/skill-index.json",
"src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md",
@@ -34,9 +34,10 @@
"src/inferrsi/data/skill_library/workflows/rsi-evidence/references/loopx-goal-governance/README.md",
"src/inferrsi/data/skill_library/workflows/rsi-evidence/references/loopx-goal-governance/decision-cases.md",
"src/inferrsi/data/skill_library/workflows/rsi-evidence/references/loopx-goal-governance/mechanisms.md",
- "src/inferrsi/data/skill_library/workflows/rsi-evidence/references/loopx-goal-governance/source-ledger.json"
+ "src/inferrsi/data/skill_library/workflows/rsi-evidence/references/loopx-goal-governance/source-ledger.json",
+ "src/inferrsi/data/skill_library/workflows/rsi-evidence/references/omni-experiments.md"
],
- "content_sha256": "08f76e12f6f8e8893f03bcdc8152a96c0c99442e7faecbc2a67a18c632fcb243"
+ "content_sha256": "5ce5b4903a3d7a4c3d20957be004c49c204d331ce76cc57274378f1ab97b4361"
}
],
"index_type": "packaged-skill",
@@ -46,15 +47,16 @@
"checkout_ref": "checkout:rsi-evidence",
"source_files": {
"src/inferrsi/data/skill_library/skill-index.json": "7904275c3383380db179287171e1430617aaa9ac4f439291eff8a71426987fbb",
- "src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md": "08f76e12f6f8e8893f03bcdc8152a96c0c99442e7faecbc2a67a18c632fcb243",
- "src/inferrsi/data/skill_library/workflows/rsi-evidence/metadata.json": "caf3ef265df71b3cbec31b6c4affb6ebe9278fba0626b23bc124825d2761e49a",
+ "src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md": "5ce5b4903a3d7a4c3d20957be004c49c204d331ce76cc57274378f1ab97b4361",
+ "src/inferrsi/data/skill_library/workflows/rsi-evidence/metadata.json": "7adfbf39def6ac64987d537c11ad3a3d2e6c06649178b77d82285add8971a115",
"src/inferrsi/data/skill_library/workflows/rsi-evidence/references/loopx-goal-governance/LICENSE": "cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30",
"src/inferrsi/data/skill_library/workflows/rsi-evidence/references/loopx-goal-governance/LICENSE-MIT.md": "1df1cf519b9e5d8acbbc72820299d7aa95afa1acbfc1f43a15109ad1d59975f3",
"src/inferrsi/data/skill_library/workflows/rsi-evidence/references/loopx-goal-governance/NOTICE.md": "3c3c36a40e1d65f3a6b20ec3a97319cb753e857f1d120f302cd828e107120f6d",
"src/inferrsi/data/skill_library/workflows/rsi-evidence/references/loopx-goal-governance/README.md": "c5802bb4d71fbf95e40a6a5282c0afcba594ab5b34d40bec97874928d8376a00",
"src/inferrsi/data/skill_library/workflows/rsi-evidence/references/loopx-goal-governance/decision-cases.md": "c2c1d3d75c4fcb515dd36ff84d8dc940c25d54c5757a29a80d1af88eb8b66115",
"src/inferrsi/data/skill_library/workflows/rsi-evidence/references/loopx-goal-governance/mechanisms.md": "4fa09099d362a8088fdb0e6a767f72aae6218b92fe5fd75b6fb78c2bb2a318fb",
- "src/inferrsi/data/skill_library/workflows/rsi-evidence/references/loopx-goal-governance/source-ledger.json": "60294951d702db924119300d89f4ed01d970a7036e214aa0d04c78f6842f92d9"
+ "src/inferrsi/data/skill_library/workflows/rsi-evidence/references/loopx-goal-governance/source-ledger.json": "60294951d702db924119300d89f4ed01d970a7036e214aa0d04c78f6842f92d9",
+ "src/inferrsi/data/skill_library/workflows/rsi-evidence/references/omni-experiments.md": "8fafc1e05ef21ab60158fc626c73ca1b8c615ada59f90fd23199496daa46ac48"
},
"skill_metadata": {
"name": "rsi-evidence",
@@ -97,7 +99,8 @@
"Link evidence paths in the report; a metric quoted only in a comment cannot be re-checked later.",
"Fingerprint tracked source even when the output directory overlaps it, and exclude only the current run's generated files.",
"Treat a missing upstream-cache release proof as INCONCLUSIVE rather than a PASS with a caveat.",
- "Read baseline and candidate SHAs from the acceptance issue for that campaign, never from a skill default."
+ "Read baseline and candidate SHAs from the acceptance issue for that campaign, never from a skill default.",
+ "Freeze optional required_trial_checks for complete requests, effective graph controls and clean worker exits; require literal true per trial and retain supporting receipts."
],
"limitations": [
"Documents evidence discipline; it performs no measurement and certifies no campaign.",
@@ -123,7 +126,8 @@
"Link evidence paths in the report; a metric quoted only in a comment cannot be re-checked later.",
"Fingerprint tracked source even when the output directory overlaps it, and exclude only the current run's generated files.",
"Treat a missing upstream-cache release proof as INCONCLUSIVE rather than a PASS with a caveat.",
- "Read baseline and candidate SHAs from the acceptance issue for that campaign, never from a skill default."
+ "Read baseline and candidate SHAs from the acceptance issue for that campaign, never from a skill default.",
+ "Freeze optional required_trial_checks for complete requests, effective graph controls and clean worker exits; require literal true per trial and retain supporting receipts."
],
"limitations": [
"This generated abstract points to the complete packaged skill; external evidence and upstream repositories remain source links.",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/skill-evolution-playbook.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/skill-evolution-playbook.json
index 55dbaaf16..eb90cc805 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/skill-evolution-playbook.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/skill-evolution-playbook.json
@@ -21,8 +21,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/skill-evolution-playbook/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/skill-evolution-playbook/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/skill-evolution-playbook/SKILL.md",
"src/inferrsi/data/skill_library/methods/skill-evolution-playbook/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/splash.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/splash.json
index cada40586..33d7de7c0 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/splash.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/splash.json
@@ -25,8 +25,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/splash/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/splash/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/splash/LICENSE",
"src/inferrsi/data/skill_library/repositories/splash/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/storage-io-measurement.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/storage-io-measurement.json
index c58131fdf..7d446f43b 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/storage-io-measurement.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/storage-io-measurement.json
@@ -24,8 +24,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/host/storage-io-measurement/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/host/storage-io-measurement/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/host/storage-io-measurement/SKILL.md",
"src/inferrsi/data/skill_library/hardware/host/storage-io-measurement/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-input-pipeline.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-input-pipeline.json
index 437eec4ca..9f8fba824 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-input-pipeline.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-input-pipeline.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/training-input-pipeline/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/training-input-pipeline/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/training-input-pipeline/SKILL.md",
"src/inferrsi/data/skill_library/methods/training-input-pipeline/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-resource-budget.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-resource-budget.json
index 25aa9bdcc..2ca8d69aa 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-resource-budget.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/training-resource-budget.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/training-resource-budget/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/training-resource-budget/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/training-resource-budget/SKILL.md",
"src/inferrsi/data/skill_library/methods/training-resource-budget/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/video-diffusion-optimization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/video-diffusion-optimization.json
index a37cb4815..ea9750d13 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/video-diffusion-optimization.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/video-diffusion-optimization.json
@@ -26,8 +26,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/video-diffusion-optimization/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/video-diffusion-optimization/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/video-diffusion-optimization/SKILL.md",
"src/inferrsi/data/skill_library/methods/video-diffusion-optimization/assets/campaign.template.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/vllm-metal.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/vllm-metal.json
index f7260fcdf..631c20305 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/vllm-metal.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/vllm-metal.json
@@ -26,8 +26,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/vllm-metal/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/vllm-metal/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/vllm-metal/LICENSE",
"src/inferrsi/data/skill_library/repositories/vllm-metal/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/weight-loading-optimization.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/weight-loading-optimization.json
index 07fb412c2..0c90cdbaf 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/weight-loading-optimization.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/common/skills/weight-loading-optimization.json
@@ -29,8 +29,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/methods/weight-loading-optimization/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/methods/weight-loading-optimization/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/methods/weight-loading-optimization/SKILL.md",
"src/inferrsi/data/skill_library/methods/weight-loading-optimization/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-afd-p2p-exchanges.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-afd-p2p-exchanges.json
index 7688ccd08..e69bc8b5d 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-afd-p2p-exchanges.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-afd-p2p-exchanges.json
@@ -23,8 +23,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/afd-plugin/audit-afd-p2p-exchanges/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/afd-plugin/audit-afd-p2p-exchanges/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/afd-plugin/audit-afd-p2p-exchanges/SKILL.md",
"src/inferrsi/data/skill_library/repositories/afd-plugin/audit-afd-p2p-exchanges/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-flare-session-lifecycle.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-flare-session-lifecycle.json
index 64d203464..1a7572890 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-flare-session-lifecycle.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/audit-flare-session-lifecycle.json
@@ -29,8 +29,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/repositories/flare-local-inference/audit-flare-session-lifecycle/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/repositories/flare-local-inference/audit-flare-session-lifecycle/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/repositories/flare-local-inference/audit-flare-session-lifecycle/LICENSE",
"src/inferrsi/data/skill_library/repositories/flare-local-inference/audit-flare-session-lifecycle/SKILL.md",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/diagnose-attention-bottlenecks.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/diagnose-attention-bottlenecks.json
index 8a7abd606..cf080ec30 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/diagnose-attention-bottlenecks.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/diagnose-attention-bottlenecks.json
@@ -16,8 +16,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/cuda/diagnose-attention-bottlenecks/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/cuda/diagnose-attention-bottlenecks/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/cuda/diagnose-attention-bottlenecks/SKILL.md",
"src/inferrsi/data/skill_library/hardware/cuda/diagnose-attention-bottlenecks/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/host-overhead-profiling.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/host-overhead-profiling.json
index 11842fcf3..5cb082bec 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/host-overhead-profiling.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/host-overhead-profiling.json
@@ -22,8 +22,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/cuda/host-overhead-profiling/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/cuda/host-overhead-profiling/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/cuda/host-overhead-profiling/SKILL.md",
"src/inferrsi/data/skill_library/hardware/cuda/host-overhead-profiling/metadata.json",
diff --git a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/reason-hopper-kernels.json b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/reason-hopper-kernels.json
index 4d076e79b..d782425be 100644
--- a/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/reason-hopper-kernels.json
+++ b/src/inferrsi/data/repo_packs/inferrsi/knowledge/cuda/skills/reason-hopper-kernels.json
@@ -36,8 +36,8 @@
"sources": [
{
"type": "git",
- "url": "https://github.com/InferMatrixLab/InferRSI/blob/2c766dbc95605e61b907ce71418ab941287b427a/src/inferrsi/data/skill_library/hardware/cuda/reason-hopper-kernels/SKILL.md",
- "commit": "2c766dbc95605e61b907ce71418ab941287b427a",
+ "url": "https://github.com/InferMatrixLab/InferRSI/blob/1e87be46b8d080d439bb516ed9fa9092f8306f62/src/inferrsi/data/skill_library/hardware/cuda/reason-hopper-kernels/SKILL.md",
+ "commit": "1e87be46b8d080d439bb516ed9fa9092f8306f62",
"paths": [
"src/inferrsi/data/skill_library/hardware/cuda/reason-hopper-kernels/SKILL.md",
"src/inferrsi/data/skill_library/hardware/cuda/reason-hopper-kernels/metadata.json",
diff --git a/src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md b/src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md
index 7eac00be0..a1cf8f8f7 100644
--- a/src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md
+++ b/src/inferrsi/data/skill_library/workflows/rsi-evidence/SKILL.md
@@ -80,3 +80,16 @@ external execution guarantees. Read its counterexamples before interpreting
`should_run`, missing state or a replay lookup. This source-derived candidate
adds no execution permission or empirical validation; the evidence, RunSpec and
verdict rules above still apply.
+
+## Omni and streaming experiments
+
+Use the [Omni experiment contract](references/omni-experiments.md)
+for reference/RNG parity, feedback-aware stage boundaries,
+matching streaming decode schedules, internal graph controls and protocol preflight.
+Freeze selected `--require-trial-check` dotted boolean fields
+in RunSpec and require literal true evidence from every baseline/candidate trial.
+Missing, malformed or false fields make qualification INCONCLUSIVE; a successful
+process and metric alone do not prove complete requests or normal worker exits.
+Retain underlying receipts and all failed attempts. After repairing the harness,
+rerun the complete comparison rather than combining arms from different attempts.
+These checks do not replace the accuracy dataset or mixed-request concurrency.
diff --git a/src/inferrsi/data/skill_library/workflows/rsi-evidence/metadata.json b/src/inferrsi/data/skill_library/workflows/rsi-evidence/metadata.json
index 299fd60fb..82a3890c4 100644
--- a/src/inferrsi/data/skill_library/workflows/rsi-evidence/metadata.json
+++ b/src/inferrsi/data/skill_library/workflows/rsi-evidence/metadata.json
@@ -37,7 +37,8 @@
"Link evidence paths in the report; a metric quoted only in a comment cannot be re-checked later.",
"Fingerprint tracked source even when the output directory overlaps it, and exclude only the current run's generated files.",
"Treat a missing upstream-cache release proof as INCONCLUSIVE rather than a PASS with a caveat.",
- "Read baseline and candidate SHAs from the acceptance issue for that campaign, never from a skill default."
+ "Read baseline and candidate SHAs from the acceptance issue for that campaign, never from a skill default.",
+ "Freeze optional required_trial_checks for complete requests, effective graph controls and clean worker exits; require literal true per trial and retain supporting receipts."
],
"limitations": [
"Documents evidence discipline; it performs no measurement and certifies no campaign.",
diff --git a/src/inferrsi/data/skill_library/workflows/rsi-evidence/references/omni-experiments.md b/src/inferrsi/data/skill_library/workflows/rsi-evidence/references/omni-experiments.md
new file mode 100644
index 000000000..40a8e8a72
--- /dev/null
+++ b/src/inferrsi/data/skill_library/workflows/rsi-evidence/references/omni-experiments.md
@@ -0,0 +1,99 @@
+# Qualifying Omni optimization experiments
+
+Use this protocol when a multimodal pipeline has feedback, stochastic audio
+sampling, internal graphs, or stateful streaming. Freeze selected checks and
+quality tolerances in the acceptance issue and `plan/` before searching. This
+adds no default hardware job or model-specific threshold.
+
+## Reference and preflight
+
+- Map per-step feedback before splitting stages: a depth head whose output feeds
+ the next temporal step may need to stay in the same AR stage. Module names do
+ not establish process boundaries.
+- Pin reference code/checkpoint, dependency versions, dtype, attention backend,
+ buffer construction device, and cast/move order. Nonpersistent rotary buffers
+ can differ despite identical weights. Match per-request RNG device, random
+ operation order/shapes and reveal schedule, not just a seed. Locate the first
+ divergent token/frame before relaxing tolerances. Isolate reference packages
+ when serving requires a different supported dependency range.
+- Compare full decode with reference full decode, and streaming with reference
+ streaming under the same codec chunk schedule. Measure the reference's own
+ full/stream difference separately; it cannot excuse additional integration
+ error. Keep transport chunk coalescing from silently changing decoder shapes.
+- Inventory outer and internal graph switches, effective backend, capture,
+ replay and fallback. An outer eager flag may leave component graphs enabled.
+- Preflight the benchmark consumer with metadata-only, empty-final and coalesced
+ payloads. Count first audio only on nonempty samples while preserving completion
+ events. Distinguish text-end, audio-end and request-end; verify flush and abort
+ cleanup. Preserve processor signatures when adding diagnostic wrappers.
+- Validate mixed prompts, seeds and lengths concurrently, cancellation followed
+ by a new request, and the campaign's accuracy dataset. Repeating one prompt
+ or matching a few fixtures does not replace these checks.
+
+## Executable trial qualification
+
+Select adapter-produced boolean fields with repeatable CLI options, for example:
+
+```text
+--require-trial-check evidence.requests_complete
+--require-trial-check evidence.workers_closed
+--require-trial-check evidence.graph_controls_verified
+```
+
+Use the same flags for `inferrsi plan` and `inferrsi run`. They are frozen as
+`required_trial_checks` in `run.lock.json`. Each baseline and candidate benchmark
+command writes its normal metric plus the selected fields to `{result}` (or
+`INFERRSI_RESULT_PATH`), for example:
+
+```json
+{
+ "metrics": {"latency_ms": 100},
+ "evidence": {
+ "requests_complete": true,
+ "workers_closed": true,
+ "graph_controls_verified": true
+ }
+}
+```
+
+These are illustrative adapter-defined keys, not built-in hardware probes. Derive
+fields from actual request counts, worker exit receipts, and effective graph
+controls; keep the underlying receipts in the trial's output directory. Emit
+completion only after checking worker exits. Process exit zero, lack of an error
+message, or executor-forced cleanup does not establish normal worker shutdown.
+Never hardcode `true` to obtain a verdict.
+
+The harness snapshots only selected boolean fields into each `execution.json`.
+Literal `true` is required on every measured trial, on both arms. Missing,
+unreadable, non-boolean or false values make the comparison `INCONCLUSIVE` and
+leave `improvement_pct` unset; raw metrics remain available for diagnosis.
+Qualification describes completeness and comparability, not an accuracy score:
+quality rejection still belongs to the explicit validation command and its frozen
+gates. A completed quality rejection remains `FAIL` when evidence is otherwise
+complete. No selected checks preserves the existing command contract; it does
+not imply lifecycle or graph qualification. Adapter attestations do not replace
+independent validation, source integrity, L3 quality or L4 service evidence.
+
+## Comparable experiments and repair
+
+Use the site's reservation mechanism on shared devices (such as `npu run` where
+provided). Freeze device allocation, workload and software, including CANN,
+torch-npu and vllm-ascend for Ascend. Record contention and graph/backend settings;
+CUDA tooling and MPS are platform-specific. Use portable device labels in shared
+artifacts and keep private machine addresses out of logs.
+
+Retain the common AB/BA loop. Report independent process repetitions separately
+from requests within each process. Warm up before steady-state measurements;
+report startup/capture costs separately when relevant. A new model unsupported
+on upstream main needs a clearly labelled integration-with-optimizations-off
+control, not a fabricated main baseline.
+
+Retain failed and slow attempts. If a consumer or harness bug is repaired, start
+a fresh complete comparison with new frozen commands/source/validator identities;
+do not splice successful samples across attempts or rewrite old evidence. A
+receipt failure does not automatically retry commands or reserve more hardware.
+
+Skipping multimodal memory profiling can help diagnosis but cannot qualify
+deployment capacity. Exercise normal profiling at declared modality limits and
+headroom at target concurrency. Distinguish sampled device memory from allocator
+peaks, component timing from service timing, and request success from clean exit.
diff --git a/src/inferrsi/harness/evaluation.py b/src/inferrsi/harness/evaluation.py
index 62f9cd33e..d2bd21105 100644
--- a/src/inferrsi/harness/evaluation.py
+++ b/src/inferrsi/harness/evaluation.py
@@ -41,12 +41,22 @@ def evaluate(
integrity: dict | None = None,
) -> dict:
failed, incomplete = [], []
+ trials_qualified = True
for label, trials in (("baseline", baseline), ("candidate", candidate)):
if len(trials) != spec.repetitions:
incomplete.append(
f"{label}: expected {spec.repetitions} trials, recorded {len(trials)}"
)
for index, trial in enumerate(trials, 1):
+ checks = trial.get("trial_checks")
+ for key in spec.required_trial_checks:
+ value = checks.get(key) if isinstance(checks, dict) else None
+ if value is not True:
+ trials_qualified = False
+ incomplete.append(
+ f"{label} trial {index}: required check {key} "
+ + ("was false" if value is False else "missing or not boolean")
+ )
if trial.get("status") != "completed":
incomplete.append(
f"{label} trial {index}: {trial.get('status')} trial excluded from "
@@ -70,7 +80,7 @@ def evaluate(
all_metrics = len(baseline) == len(candidate) == spec.repetitions and all(
t.get("status") == "completed" and t.get("metric") is not None for t in baseline + candidate
)
- if all_metrics:
+ if all_metrics and trials_qualified:
improvement = (after["median"] - before["median"]) / before["median"] * 100
if spec.direction == "minimize":
improvement *= -1
@@ -89,6 +99,7 @@ def evaluate(
return {
"verdict": verdict.value,
"reasons": failed + incomplete,
+ "required_trial_checks": list(spec.required_trial_checks),
"metric_key": spec.metric_key,
"metric_unit": spec.metric_unit,
"comparison_scope": spec.comparison_scope,
diff --git a/src/inferrsi/harness/reporting.py b/src/inferrsi/harness/reporting.py
index 500cbfac3..d24aca151 100644
--- a/src/inferrsi/harness/reporting.py
+++ b/src/inferrsi/harness/reporting.py
@@ -5,7 +5,12 @@
from pathlib import Path
from urllib.parse import quote
-from ..summary_chart import SpecError, build_svg, spec_from_evaluation
+from ..summary_chart import (
+ SpecError,
+ build_svg,
+ check_trial_chart_eligibility,
+ spec_from_evaluation,
+)
def write_report(run_dir: Path) -> Path:
@@ -20,13 +25,13 @@ def read(name: str) -> dict:
def dump(value: object) -> str:
return escape(json.dumps(value, ensure_ascii=False, indent=2))
+ figure = _summary_figure(run_dir, evaluation)
links = []
for path in sorted(run_dir.rglob("*")):
if path.is_file() and path.name != "report.html":
relative = path.relative_to(run_dir).as_posix()
links.append(f'{escape(relative)}')
verdict = escape(str(evaluation.get("verdict", "INCONCLUSIVE")))
- figure = _summary_figure(run_dir, evaluation)
report = f"""
@@ -60,10 +65,12 @@ def _summary_figure(run_dir: Path, evaluation: dict) -> str:
A campaign that has accumulated several steps can commit a chain
specification as ``summary-chart.json`` beside the run; that spec wins,
- because it records the whole campaign rather than one pairing.
+ because it records the whole campaign rather than one pairing. Both inputs
+ require the current run's selected trial checks to permit a comparison.
"""
campaign = run_dir / "summary-chart.json"
try:
+ check_trial_chart_eligibility(evaluation)
if campaign.is_file():
spec = json.loads(campaign.read_text(encoding="utf-8"))
if not isinstance(spec, dict):
@@ -72,6 +79,7 @@ def _summary_figure(run_dir: Path, evaluation: dict) -> str:
spec = spec_from_evaluation(evaluation)
svg = build_svg(spec)
except (SpecError, json.JSONDecodeError) as error:
+ (run_dir / "summary-chart.svg").unlink(missing_ok=True)
return f"No gain figure: {escape(str(error))}.
"
(run_dir / "summary-chart.svg").write_text(svg, encoding="utf-8")
# Inline the figure so the report stays one self-contained file.
diff --git a/src/inferrsi/harness/runner.py b/src/inferrsi/harness/runner.py
index 279e9883b..a15c6b2a1 100644
--- a/src/inferrsi/harness/runner.py
+++ b/src/inferrsi/harness/runner.py
@@ -13,7 +13,7 @@
from ..runspec import RunSpec
from .evaluation import evaluate
from .reporting import write_report
-from .scenarios.external import execute_trial
+from .scenarios.external import collect_trial_checks, execute_trial
def run_experiment(
@@ -67,6 +67,9 @@ def execute_checked(
) -> dict:
source_before = snapshot(repos[label], run_dir)
record = execute(command, repos[label], trial_dir, deadline, metric_key)
+ if metric_key is not None and spec.required_trial_checks:
+ record["trial_checks"] = collect_trial_checks(record, spec.required_trial_checks)
+ _write_json(trial_dir / "execution.json", record)
source_after = snapshot(repos[label], run_dir)
check = {
"path": str(trial_dir),
diff --git a/src/inferrsi/harness/scenarios/external.py b/src/inferrsi/harness/scenarios/external.py
index e665293f7..c21242f5b 100644
--- a/src/inferrsi/harness/scenarios/external.py
+++ b/src/inferrsi/harness/scenarios/external.py
@@ -30,3 +30,26 @@ def execute_trial(
record["metric_error"] = str(exc)
_write_json(trial_dir / "execution.json", record)
return record
+
+
+def collect_trial_checks(record: dict, keys: tuple[str, ...]) -> dict[str, bool | None]:
+ """Snapshot only selected boolean attestations, never arbitrary result data.
+
+ Missing/unreadable/non-boolean fields stay unknown. Adapters own the receipts
+ proving these attestations; subprocess success cannot synthesize them.
+ """
+ checks: dict[str, bool | None] = dict.fromkeys(keys)
+ try:
+ payload = json.loads(Path(record["result_path"]).read_text(encoding="utf-8"))
+ except (KeyError, OSError, ValueError, TypeError):
+ return checks
+ for key in keys:
+ value = payload
+ for part in key.split("."):
+ if not isinstance(value, dict) or part not in value:
+ value = None
+ break
+ value = value[part]
+ if isinstance(value, bool):
+ checks[key] = value
+ return checks
diff --git a/src/inferrsi/runspec.py b/src/inferrsi/runspec.py
index 45f2c0b84..161408204 100644
--- a/src/inferrsi/runspec.py
+++ b/src/inferrsi/runspec.py
@@ -33,6 +33,7 @@ class RunSpec:
executor: str = "default"
snapshot_id: str = ""
output_dir: str = "runs"
+ required_trial_checks: tuple[str, ...] = ()
def to_dict(self) -> dict:
return asdict(self)
@@ -40,7 +41,13 @@ def to_dict(self) -> dict:
@classmethod
def from_dict(cls, data: dict) -> "RunSpec":
values = dict(data)
- for name in ("baseline_command", "candidate_command", "validation_command", "device_ids"):
+ for name in (
+ "baseline_command",
+ "candidate_command",
+ "validation_command",
+ "device_ids",
+ "required_trial_checks",
+ ):
if name in values and values[name] is not None:
if not isinstance(values[name], (list, tuple)):
raise ValueError(f"{name} must be an argv/ID sequence, not a string or mapping")
@@ -69,6 +76,17 @@ def validate(self) -> None:
raise ValueError(f"{label} must be a nonempty argv sequence of strings")
if not command[0]:
raise ValueError(f"{label} executable cannot be empty")
+ if (
+ not isinstance(self.required_trial_checks, tuple)
+ or any(
+ not isinstance(key, str)
+ or not key
+ or any(not part or part.strip() != part for part in key.split("."))
+ for key in self.required_trial_checks
+ )
+ or len(set(self.required_trial_checks)) != len(self.required_trial_checks)
+ ):
+ raise ValueError("required_trial_checks must be a tuple of unique dotted JSON keys")
if self.direction not in {"minimize", "maximize"}:
raise ValueError("direction must be minimize or maximize")
if self.mode not in {"config", "code", "semantic"}:
diff --git a/src/inferrsi/summary_chart.py b/src/inferrsi/summary_chart.py
index 1329fe4eb..7d4a7de46 100644
--- a/src/inferrsi/summary_chart.py
+++ b/src/inferrsi/summary_chart.py
@@ -899,6 +899,23 @@ def x_of(gain: float) -> float:
return "\n".join(parts) + "\n"
+def check_trial_chart_eligibility(evaluation: dict) -> None:
+ """Keep the evaluator's selected-check decision authoritative for charts.
+
+ With required checks, the evaluator publishes an improvement only for a
+ complete, qualified pairing. Its raw medians cannot substitute for that
+ decision. Older evaluations without selected checks retain their behavior.
+ """
+ if not isinstance(evaluation, dict):
+ raise SpecError("evaluation must be an object")
+ if evaluation.get("required_trial_checks") and evaluation.get("improvement_pct") is None:
+ raise SpecError(
+ "required trial checks have not established a complete comparison; "
+ "retained medians are raw measurements only. Campaign specifications "
+ "are retained as separate evidence and are not plotted for this run"
+ )
+
+
def spec_from_evaluation(evaluation: dict, *, title: str | None = None) -> dict:
"""Build a one-step chain specification from one recorded evaluation.
@@ -906,8 +923,7 @@ def spec_from_evaluation(evaluation: dict, *, title: str | None = None) -> dict:
recorded pair as a two-point chain: the baseline at 1.00x and the measured
candidate. Nothing is inferred beyond the evaluation's own numbers.
"""
- if not isinstance(evaluation, dict):
- raise SpecError("evaluation must be an object")
+ check_trial_chart_eligibility(evaluation)
before = evaluation.get("baseline") or {}
after = evaluation.get("candidate") or {}
baseline_value = before.get("median")
diff --git a/tests/test_trial_check_reports.py b/tests/test_trial_check_reports.py
new file mode 100644
index 000000000..db7e358d7
--- /dev/null
+++ b/tests/test_trial_check_reports.py
@@ -0,0 +1,81 @@
+"""Reports must obey the evaluator's trial checks before plotting either input."""
+
+import json
+
+import pytest
+
+from inferrsi.harness.evaluation import evaluate
+from inferrsi.harness.reporting import write_report
+from inferrsi.runspec import RunSpec
+from inferrsi.summary_chart import SpecError, spec_from_evaluation
+
+
+def evaluated_pair(checks, side="candidate"):
+ spec = RunSpec(repo=".", repetitions=1, required_trial_checks=("evidence.closed",))
+ arms = {
+ label: [{"status": "completed", "metric": value,
+ "trial_checks": {"evidence.closed": True}}]
+ for label, value in (("baseline", 100), ("candidate", 80))
+ }
+ arms[side][0]["trial_checks"] = checks
+ return evaluate(spec, arms["baseline"], arms["candidate"],
+ {"status": "completed"}, {"verified": True})
+
+
+def persist_report(directory, evaluation):
+ (directory / "evaluation.json").write_text(json.dumps(evaluation), encoding="utf-8")
+ return write_report(directory).read_text(encoding="utf-8")
+
+
+@pytest.mark.parametrize("campaign", [False, True])
+@pytest.mark.parametrize("side", ["baseline", "candidate"])
+@pytest.mark.parametrize("checks", [
+ {}, {"evidence.closed": False}, {"evidence.closed": "true"}, {"evidence.closed": True},
+], ids=["missing", "false", "not-boolean", "qualified"])
+def test_trial_evidence_controls_report_chart(tmp_path, checks, side, campaign):
+ historical = json.dumps(spec_from_evaluation(evaluated_pair({"evidence.closed": True})))
+ specification = tmp_path / "summary-chart.json"
+ if campaign:
+ specification.write_text(historical, encoding="utf-8")
+
+ result = evaluated_pair(checks, side)
+ html = persist_report(tmp_path, result)
+ svg = tmp_path / "summary-chart.svg"
+ if checks.get("evidence.closed") is True:
+ assert result["verdict"] == "PASS"
+ assert "0.80×" in html
+ assert "0.80×" in svg.read_text(encoding="utf-8")
+ else:
+ assert result["verdict"] == "INCONCLUSIVE"
+ assert result["improvement_pct"] is None
+ assert "raw measurements" in html
+ assert "required trial checks" in html
+ assert "