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 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 keep the strongest result with local logs and diffs.
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