@sreetej510/pi-shipd-checks 0.4.0 → 0.4.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. package/README.md +10 -11
  2. package/dist/index.js +40 -40
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -47,16 +47,15 @@ repeated requests sequentially after applying each result.
47
47
 
48
48
  ## Configuration
49
49
 
50
- `/checks --config` opens the row-based settings menu with four sections:
50
+ `/checks --config` opens the row-based settings menu with two sections:
51
51
 
52
- - **Reviewer**: model and thinking level used by the behavioral gap finders, validator, and
53
- solver-solution comparison agent.
54
- - **Solver**: model and thinking level for TDD solver agents, plus their timeout, parallel solver
55
- count, and artifact-saving setting.
56
- - **Analyze Tool**: pick separate models + thinking levels for the agent-callable gap-analysis and Test Audit modes. The audit model defaults to the gap-analysis model until explicitly changed. These are stored under `analyzeGap.testAuditProvider`, `analyzeGap.testAuditModelId`, and `analyzeGap.testAuditThinkingLevel`.
57
- - **Fargate**: choose the shared-task resource profile for the current project: `small` (1 vCPU,
58
- 2 GB), `medium` (2 vCPU, 4 GB), or `large` (4 vCPU, 8 GB). Adaptive sizing can select the
59
- next profile from task telemetry after each run.
52
+ - **Solver**: comparison model and thinking level for the final solver-result reviewer, plus the
53
+ TDD solver model, thinking level, timeout, parallel solver count, and artifact-saving setting.
54
+ - **Analyze Tool**: separate models + thinking levels for the agent-callable gap-analysis and Test
55
+ Audit modes. The audit model defaults to the gap-analysis model until explicitly changed. These
56
+ are stored under `analyzeGap.testAuditProvider`, `analyzeGap.testAuditModelId`, and
57
+ `analyzeGap.testAuditThinkingLevel`. Fargate resources are selected automatically and are not
58
+ configured in this menu.
60
59
 
61
60
  AWS credentials stay local. Configure the AWS CLI profile, then set `AWS_PROFILE`/`AWS_REGION` (or add
62
61
  `fargate.awsProfile`/`fargate.region` to `checks-config.json`). The runner discovers the default
@@ -131,8 +130,8 @@ On-Demand fallback. Spot interruptions are retried according to `fargate.maxRetr
131
130
  no telemetry history is retained. Set `projectProfiles` to override resources per repository:
132
131
  `{"C:/path/to/repo":"large"}`.
133
132
 
134
- 5. Restart pi, use `/checks --config` to select the solver model and project resource profile,
135
- then run `/checks --solver-gap-finder`. Projects need `Dockerfile`, `agent_prompt.md`,
133
+ 5. Restart pi, use `/checks --config` to select the solver and comparison models, then run
134
+ `/checks --solver-gap-finder`. Projects need `Dockerfile`, `agent_prompt.md`,
136
135
  `solution.patch`, `test.patch`, and `test.sh`.
137
136
 
138
137
  Use `/analyze:on` and `/analyze:off` to control the tool per project, like HPC. The enabled project