Unified · Split
| @@ -1,7 +1,7 @@ | ||
| 1 | 1 | { |
| 2 | 2 | "name": "pstack", |
| 3 | 3 | "displayName": "pstack", |
| 4 | − "version": "0.11.6", | |
| 4 | + "version": "0.11.7", | |
| 5 | 5 | "description": "if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.", |
| 6 | 6 | "author": { |
| 7 | 7 | "name": "Lauren Tan" |
| @@ -45,7 +45,7 @@ The right decomposition depends on the question. Use your judgment. Narrow quest · 44 unmodified lines | ||
| 45 | 45 | Spawn all explorers in a single message: |
| 46 | 46 | |
| 47 | 47 | - `subagent_type`: `generalPurpose` |
| 48 | −- `model`: resolve the configured `how explorer` role per `~/.cursor/rules/pstack-models.mdc`. Pass a real slug as `model`. Omit `model` for `inherit-parent`/`auto`. If the role line is absent, default to `gpt-5.6-sol-max`. | |
| 48 | +- `model`: resolve the configured `how explorer` role per `~/.cursor/rules/pstack-models.mdc`. Pass a real slug as `model`. Omit `model` for `inherit-parent`/`auto`. If the role line is absent, default to `grok-4.5-fast-xhigh`. | |
| 49 | 49 | - `readonly`: `true` |
| 50 | 50 | |
| 51 | 51 | Each explorer gets the same base prompt from `references/explorer-prompt.md` plus a specific exploration angle naming its slice. Each explorer should: |
| @@ -48,10 +48,10 @@ perf-issue: gpt-5.6-sol-max · 47 unmodified lines | ||
| 48 | 48 | hillclimb: gpt-5.6-sol-max |
| 49 | 49 | judgment and prose: claude-fable-5-thinking-max |
| 50 | 50 | hardest tasks: claude-fable-5-thinking-max |
| 51 | −how explorer: gpt-5.6-sol-max | |
| 51 | +how explorer: grok-4.5-fast-xhigh | |
| 52 | 52 | how explainer: claude-fable-5-thinking-max |
| 53 | 53 | how critics: claude-fable-5-thinking-max, gpt-5.6-sol-max, grok-4.5-fast-xhigh |
| 54 | −why investigators: gpt-5.6-sol-max | |
| 54 | +why investigators: grok-4.5-fast-xhigh | |
| 55 | 55 | why synthesizer: claude-fable-5-thinking-max |
| 56 | 56 | reflect tooling: gpt-5.6-sol-max |
| 57 | 57 | reflect judgment, divergent, synthesizer: claude-fable-5-thinking-max |
| @@ -117,7 +117,7 @@ Launch all matching investigators in a single message so they run concurrently. · 116 unmodified lines | ||
| 117 | 117 | |
| 118 | 118 | Subagent config (each): |
| 119 | 119 | - `subagent_type`: `generalPurpose` |
| 120 | −- `model`: resolve the configured `why investigators` role per `~/.cursor/rules/pstack-models.mdc`. Pass a real slug as `model`. Omit `model` for `inherit-parent`/`auto`. If the role line is absent, default to `gpt-5.6-sol-max`. | |
| 120 | +- `model`: resolve the configured `why investigators` role per `~/.cursor/rules/pstack-models.mdc`. Pass a real slug as `model`. Omit `model` for `inherit-parent`/`auto`. If the role line is absent, default to `grok-4.5-fast-xhigh`. | |
| 121 | 121 | - `readonly`: `false` (agent mode). **Do not use readonly/Ask mode.** It strips MCP access, which disables MCP-backed investigators entirely. The source control investigator would be safe in readonly, but keep modes uniform. Investigators still shouldn't write anything. That's a posture, not a sandbox. |
| 122 | 122 | |
| 123 | 123 | Each investigator gets: |