prompts-gpt 0.3.1 → 0.3.2
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.
- package/README.md +9 -1
- package/dist/cli.js +498 -96
- package/dist/cli.js.map +1 -1
- package/dist/index.js +13 -2
- package/dist/index.js.map +1 -1
- package/dist/orchestrate.d.ts +1 -1
- package/dist/orchestrate.d.ts.map +1 -1
- package/dist/orchestrate.js +51 -18
- package/dist/orchestrate.js.map +1 -1
- package/dist/runtime.d.ts.map +1 -1
- package/dist/runtime.js +4 -1
- package/dist/runtime.js.map +1 -1
- package/dist/sweep.js +14 -3
- package/dist/sweep.js.map +1 -1
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -108,6 +108,9 @@ prompts-gpt sweep --dry-run
|
|
|
108
108
|
# Run and score multiple providers on one prompt
|
|
109
109
|
prompts-gpt orchestrate --mode parallel -f .prompts-gpt/review.md --providers codex,claude,cursor --criteria correctness,completeness
|
|
110
110
|
|
|
111
|
+
# Interactive orchestration mode picker
|
|
112
|
+
prompts-gpt orchestrate
|
|
113
|
+
|
|
111
114
|
# Chain steps with context passing
|
|
112
115
|
cat > pipeline.json <<'EOF'
|
|
113
116
|
[
|
|
@@ -122,6 +125,9 @@ prompts-gpt orchestrate --mode pipeline --steps pipeline.json --dry-run
|
|
|
122
125
|
prompts-gpt orchestrate --mode eval -f .prompts-gpt/review.md --criteria correctness,risk,clarity
|
|
123
126
|
prompts-gpt orchestrate --mode eval --dry-run --eval-criteria correctness,risk,clarity
|
|
124
127
|
|
|
128
|
+
# Inspect available models for the resolved orchestration providers
|
|
129
|
+
prompts-gpt orchestrate --mode eval --list-models
|
|
130
|
+
|
|
125
131
|
# Re-run a prompt when the file changes
|
|
126
132
|
prompts-gpt run -f .prompts-gpt/review.md --watch
|
|
127
133
|
|
|
@@ -178,7 +184,7 @@ All options can be overridden via environment variables. See `prompts-gpt help s
|
|
|
178
184
|
|
|
179
185
|
## Orchestration Patterns
|
|
180
186
|
|
|
181
|
-
- `parallel`: run multiple providers against the same prompt, score outputs, and
|
|
187
|
+
- `parallel`: run multiple providers against the same prompt, score outputs, and report the strongest result with local logs and diffs.
|
|
182
188
|
- `pipeline`: pass context across named steps when research, implementation, and review should be separated.
|
|
183
189
|
- `eval`: run one provider and force a structured quality score for the output.
|
|
184
190
|
- `eval --dry-run`: if `-f` is omitted, the CLI uses the first discovered `.prompts-gpt` prompt so workspace scaffolds can verify orchestration immediately.
|
|
@@ -203,6 +209,8 @@ Dry-runs verify command wiring, prompt resolution, evaluator selection, and crit
|
|
|
203
209
|
npx prompts-gpt orchestrate --mode eval --dry-run --eval-criteria correctness,risk,clarity
|
|
204
210
|
```
|
|
205
211
|
|
|
212
|
+
Full pattern guide (parallel vs pipeline vs eval, visibility handoff, diff/watch): [docs/orchestration-patterns.md](../../docs/orchestration-patterns.md) in the main repo.
|
|
213
|
+
|
|
206
214
|
---
|
|
207
215
|
|
|
208
216
|
## SDK
|