mirror of
https://github.com/glittercowboy/get-shit-done
synced 2026-04-25 17:25:23 +02:00
d4767ac2e0
* fix: replace /gsd: command format with /gsd- skill format in all suggestions All next-step suggestions shown to users were still using the old colon format (/gsd:xxx) which cannot be copy-pasted as skills. Migrated all occurrences across agents/, commands/, get-shit-done/, docs/, README files, bin/install.js (hardcoded defaults for claude runtime), and get-shit-done/bin/lib/*.cjs (generate-claude-md templates and error messages). Updated tests to assert new hyphen format instead of old colon format. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: migrate remaining /gsd: format to /gsd- in hooks, workflows, and sdk Addresses remaining user-facing occurrences missed in the initial migration: - hooks/: fix 4 user-facing messages (pause-work, update, fast, quick) and 2 comments in gsd-workflow-guard.js - get-shit-done/workflows/: fix 21 Skill() literal calls that Claude executes directly (installer does not transform workflow content) - sdk/prompt-sanitizer.ts: update regex to strip /gsd- format in addition to legacy /gsd: format; update JSDoc comment - tests/: update autonomous-ui-steps, prompt-sanitizer to assert new format Note: commands/gsd/*.md frontmatter (name: gsd:xxx) intentionally unchanged — installer derives skillName from directory path, not the name field. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(plan-phase): preserve --chain flag in auto-advance sync and handle ui-phase gate in chain mode Bug 1: step 15 sync-flag check only guarded against --auto, causing _auto_chain_active to be cleared when plan-phase is invoked without --auto in ARGUMENTS even though a --chain pipeline was active. Added --chain to the guard condition, matching discuss-phase behaviour. Bug 2: UI Design Contract gate (step 5.6) always exited the workflow when UI-SPEC was missing, breaking the discuss --chain pipeline silently. When _auto_chain_active is true, the gate now auto-invokes gsd-ui-phase --auto via Skill() and continues to step 6 without prompting. Manual invocations retain the existing AskUserQuestion flow. * fix: remove <sub>/clear</sub> pattern and duplicate old-format command in discuss-phase.md --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
1.1 KiB
1.1 KiB
Monitor de Contexto
O monitor de contexto ajuda a evitar degradação de qualidade em sessões longas, alertando sobre uso excessivo da janela de contexto.
Para detalhes completos de implementação, veja context-monitor.md em inglês.
Objetivos
- identificar quando a sessão principal está saturando
- recomendar ações de recuperação (
/clear,/gsd-resume-work,/gsd-progress) - manter previsibilidade durante ciclos longos de desenvolvimento
Como funciona
- coleta sinais de uso da janela de contexto
- compara com limiares de alerta
- emite avisos progressivos
- sugere retomada por artefatos persistentes
Estratégia recomendada
- Limpe contexto entre fases grandes
- Execute tarefas pesadas em subagentes
- Mantenha o estado em
.planning/como fonte de verdade
Recuperação quando há degradação
/clear
/gsd-resume-work
# ou
/gsd-progress
Tip
O monitor não substitui boas práticas de escopo. Planos pequenos e verificáveis continuam sendo o principal fator de qualidade.