* fix(#4728): stop presenting the retired Gemini CLI as a supported runtime
#1928 removed the Gemini CLI runtime after Google sunset it on 2026-06-18, and
updated the ENGLISH docs. The locale mirrors and the runtime-loaded workflow
prose were not updated in the same change, and no gate asserts the ABSENCE of a
retired runtime, so both drifted quietly for a year.
The finding that shaped this change: English is already correct. docs/
ARCHITECTURE.md, CONFIGURATION.md, USER-GUIDE.md, how-to/install-on-your-runtime.md
and CLI-TOOLS.md carry zero runtime-axis Gemini references; the only English hits
anywhere are a Gemini 2.5 Pro MODEL line, the GEMINI_API_KEY row, and prose that
correctly documents the retirement. So the docs half of this is translation lag,
not a content decision, and every locale edit here is parity with an existing
English line rather than new wording:
- install-on-your-runtime.md English has NO `### Gemini CLI` section -> deleted
- USER-GUIDE.md :843 "…, Antigravity CLI, Kilo)" -> substituted
- ARCHITECTURE.md English has NO Gemini CLI table row -> row deleted
- ARCHITECTURE.md :24 English holds `Kimi CLI` in that slot -> Kimi CLI
- context-monitor.md :3 "`AfterTool` for Antigravity CLI" -> substituted
- spike-and-sketch.md :93 "(Codex, Antigravity CLI, etc.)" -> substituted
- configure-model-profiles "Codex, OpenCode, Antigravity CLI, or Kilo" -> substituted
- COMMANDS.md English keeps only hyphen + Codex bullets -> colon bullet deleted
- FEATURES.md source docs/features/multi-runtime-support.md:10
lists no Gemini CLI -> name removed
ARCHITECTURE.md:24 is the clearest case for reading English rather than
substituting blind: Antigravity ALREADY appears later in that list, so replacing
Gemini CLI with Antigravity would have named it twice. English holds Kimi CLI
there, so that is what the locales get.
The largest single class was hand-duplicated boilerplate. A "Text mode" paragraph
repeated across 34 runtime-loaded workflow files ends "…required for non-Claude
runtimes (OpenAI Codex, Gemini CLI, etc.)". No lint enforces that sentence and no
script syncs it, so every copy was edited. These files are read by the agent at
runtime, so they steer behavior rather than only informing a reader — which is why
this class matters more than its word count suggests.
The slash-command-form section is restructured in all four languages to match
English, which had already dropped its colon-form bullet. That bullet claimed the
colon form is "Gemini CLI only", which was false on its own terms independent of
the retirement: `/gsd:…` is GSD's canonical AUTHORING token, rewritten per runtime
at install time, and NO runtime registers it — VALID_COMMAND_STYLES is
{slash-hyphen, shell-var} and 18 of 19 runtimes declare slash-hyphen. Substituting
the runtime name would have left the claim false with Antigravity's name in it, so
the claim is gone, matching English.
Two anchor regressions were caught and fixed while doing that. zh-CN lost its
explicit {#slash-command-forms-hyphen-vs-colon} anchor while its TOC still linked
it; the anchor is restored. ko-KR and pt-BR never had an explicit anchor and rely
on the slug generated from the heading text, so shortening the heading broke their
own TOC links; those links now point at the new slugs. English's heading lost its
anchor while its TOC still links the old one — that latent English bug is
deliberately NOT copied.
Preserved, because `gemini` is not one thing here and a blanket sweep breaks the
product: ~/.gemini/antigravity{,-ide,-cli} and ~/.gemini as their parent;
~/.gemini/config (#3738); GEMINI.md; hookEvents "gemini"; GEMINI_API_KEY in all
four locales; every gemini-* model id and the Gemini 2.5 Pro references in
ko-KR/pt-BR/zh-CN (ja-JP genuinely lacks that line — the locales have diverged, so
a uniform patch would be wrong); the hook-event dialect notes, which are
RE-ATTRIBUTED rather than deleted because Antigravity inherits that dialect;
reapply-patches.md:93's legacy-install note; host-integration-capability-matrix.md
:27 and :342, which correctly record the sunset and Antigravity's contract;
whats-new-1.7.0.md and FEATURES.md:3506, which document the retirement itself; and
the generated launcher preamble, which belongs to epic #4632 — zero
_GSD_SHIM_NAME lines appear in this diff.
Coverage: a #4728 block in tests/gemini-runtime-removed.test.cjs asserts the
retired name is gone from STRUCTURAL POSITIONS (a level-3 heading, a table row's
first cell, a runtime-example parenthetical) rather than asserting the string is
absent, which would be wrong. It pairs those with positive PRESERVE assertions
over the same files — Antigravity's heading, ~/.gemini/antigravity, GEMINI_API_KEY,
AfterTool — so a patch that deletes too much fails as loudly as one that deletes
too little. The model-axis test pins both the presence in three locales and the
absence in ja-JP, so a later uniform patch that "helpfully" adds it back fails.
The new docs/ reads tripped lint-docs-guard-registration for the first time in
this file, so the test is registered in scripts/docs-guard-registry.cjs.
Not covered here, by design: nothing above would catch a Gemini-as-runtime
reference appearing in a NEW file tomorrow. That is the repo-wide drift guard,
#4729, which must land last — written now it would red on the very references this
change removes.
Fixes #4728
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(#4728): fix four review blockers, including a vacuous test and my own duplicate
A full matrix run on 31f12d7943 FAILED with 3 real failures, and an isolated
adversarial review returned BLOCK on four blockers. All of it was correct.
1. I committed the exact error I claimed to have avoided. The commit message
boasted that ARCHITECTURE.md:24 proved the value of reading English rather
than substituting blind, because Antigravity already appeared later in that
list. Five hundred lines further down the SAME four files, my
`Gemini:` -> `Antigravity:` substitution produced TWO consecutive
`- Antigravity:` bullets, because an Antigravity bullet was already there.
English (ARCHITECTURE.md:827) merges them into one. Now merged in all four
locales, reusing each locale's existing words.
2. `--gemini` survived in the runtime-detection CLI flag list in all four
locale ARCHITECTURE.md files. English:817 holds `--kimi` in that slot and
already lists `--antigravity` later, so this is another place where
substituting Antigravity would have duplicated it. Now `--kimi`.
3. Two runtime-loaded workflow files still enumerated Gemini one line ABOVE the
line I had already corrected -- the "Adaptive (Recommended)" option in
settings.md:192 and new-project/steps/auto-mode-config.md:95.
4. THE NEW TEST WAS VACUOUS for two of its five files. It matched only
`non-Claude runtimes (` and `(e.g. `, and neither regex could reach the two
lines the change actually fixed: health.md:52 reads `non-Claude (Codex, ...)`
without the word "runtimes", and execute-phase.md:1028 has no parenthetical
at all. The reviewer proved it by re-introducing Gemini at both lines and
watching the assertion stay GREEN. That same blind spot is what hid finding 3.
Replaced with a case-sensitive `/\bGemini\b/` walk over every
`gsd-core/workflows/**/*.md`, which works because every LEGITIMATE gemini
reference in that tree is spelled differently and cannot match: Antigravity's
paths are lowercase with a slash (`~/.gemini/antigravity`), Google's model ids
are lowercase and hyphenated (`gemini-3.1-pro-preview`), and the env vars are
uppercase (`GEMINI_CONFIG_DIR`, `GEMINI_SESSION_ID`). A bare capitalised
`Gemini` there means the retired RUNTIME is being named. The walk asserts it
found at least 50 files so an empty walk cannot pass vacuously, and it now
covers the nested `new-project/steps/` directory where finding 3 lived.
Two allowlist entries, both by line CONTENT and both justified:
reapply-patches.md's `Legacy: ... pre-#1928` note, and settings-advanced.md's
`Known provider` menu. The second was escalated by the agent rather than
decided: Section 8 of that file says model policy is defined "independently"
of the runtime, so `(Claude / OpenAI / Gemini / Qwen)` is the PROVIDER axis --
the same axis as the lowercase model ids -- and must keep working.
Proven to fail, not just asserted: the predicate reports 0 offenders on the
real tree and exactly 2 on a /tmp copy with Gemini re-injected at
health.md:52 and execute-phase.md:1028.
Also from the review: a `| Gemini |` COLUMN survived in the locale FEATURES.md
comparison tables (English has none) -- removed from all three, with header,
separator and every body row kept aligned; two ENGLISH runtime-axis sites were
missed by my own parity standard (how-to/execute-a-phase.md:88 and
how-to/verify-and-ship.md:89, the latter doubly stale since #4716 retired the
Gemini reviewer lane); docs/USER-GUIDE.md:12 linked a dead anchor, which I had
found and deliberately left -- record-and-proceed on a known defect is exactly
what the rules forbid, so it is fixed; docs/COMMANDS.md:12 and all four mirrors
still claimed "the hyphen and colon forms are runtime-specific spellings" with
no colon form documented anywhere, so that false sentence is deleted; and ko-KR
had the installer rather than the user doing the targeting.
The other two matrix failures were the compact-content benchmark baseline, which
drifted because this PR changes byte counts, refreshed via the script's own
`--write` path rather than by hand; and this commit's emitted-drift-ack trailers.
Method note on the acks: the failing run measured growth against
origin/next@1110c3b4ee, which is the STALE LOCAL `next` ref -- gsd-test merges
into the local base branch, and this machine's `next` is seven commits behind
origin/next, which is checked out in the main worktree and so cannot be
fast-forwarded from here. The 32 trailers below are computed against the REAL
base (origin/next @ ca8d9d4459) by comparing each tracked file's blob size, which
is one more file than that run reported -- the extra is settings.md, grown again
by fix 3. docs-update.md and map-codebase.md are deliberately NOT acked: they
SHRANK, since there the fix deleted ", Gemini CLI" rather than substituting, and
acking a file no delta consumed is itself an error.
Refs #4728
Emitted-Drift-Ack-Growth: add-tests.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: add-todo.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: ai-integration-phase.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: check-todos.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: cleanup.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: complete-milestone.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: do.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: eval-review.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: execute-phase.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: execute-plan.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: health.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: import.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: inbox.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: manager.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: new-milestone.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: new-workspace.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: note.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: onboard.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: plant-seed.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: profile-user.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: quick.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: remove-workspace.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: secure-phase.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: settings.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: ship.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: smart-entry.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: ui-phase.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: ui-review.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: undo.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: update.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: validate-phase.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Emitted-Drift-Ack-Growth: verify-work.md — retiring the Gemini CLI runtime name; Antigravity is one byte longer
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* chore(#4728): add the changeset fragment
The PR body claimed one was present and it was not — caught by
scripts/changeset/lint.cjs reporting fail_missing_fragment, not by the
checklist, which is exactly why the lint exists.
Type Fixed: the diff is prose, and a docs-only fix uses Fixed since there is
no Documentation type.
Refs #4728
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
---------
Co-authored-by: sim <sim@local>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
8.4 KiB
Como configurar perfis de modelo
Escolha a estratégia de nível de modelo adequada para o seu projeto e ajuste agentes individuais ou tipos de fase inteiros sem precisar escrever um bloco de substituição extenso. Este guia começa pelo controle mais simples e avança até o roteamento dinâmico.
Os quatro perfis (mais adaptive e inherit)
Defina model_profile em .planning/config.json ou via /gsd-config --profile <name>:
| Perfil | Planejador | Executor | Pesquisadores | Verificador | Usar quando |
|---|---|---|---|---|---|
quality |
Opus | Opus | Opus | Sonnet | Trabalho de qualidade para produção onde o custo é secundário |
balanced |
Opus | Sonnet | Sonnet | Sonnet | Desenvolvimento normal — o padrão |
budget |
Sonnet | Sonnet | Haiku | Haiku | Prototipagem rápida, contextos com restrições de custo |
adaptive |
Opus | Sonnet | Sonnet | Sonnet | Resolve da mesma forma que os outros níveis em perfis cientes de runtime; use ao alternar entre runtimes com frequência |
inherit |
(modelo da sessão) | (modelo da sessão) | (modelo da sessão) | (modelo da sessão) | Provedores não-Anthropic (OpenRouter, modelos locais) — todos os agentes seguem o modelo atual da sessão |
A tabela acima mostra um subconjunto representativo. Todos os 33 agentes incluídos possuem atribuições de nível explícitas por perfil em gsd-core/bin/shared/model-catalog.json. Para a tabela completa, consulte Perfis de Modelo na referência de configuração.
Troca rápida via comando:
/gsd-config --profile balanced # Desenvolvimento normal
/gsd-config --profile budget # Prototipagem ou fases de alto custo
/gsd-config --profile quality # Lançamento em produção
/gsd-config --profile inherit # OpenRouter, modelos locais
Ou edite .planning/config.json diretamente:
{
"model_profile": "balanced"
}
Substituições por agente (model_overrides)
Se um único agente precisa de um nível diferente sem alterar o perfil inteiro, use model_overrides:
{
"model_profile": "balanced",
"model_overrides": {
"gsd-executor": "opus",
"gsd-codebase-mapper": "haiku"
}
}
Valores válidos: opus, sonnet, haiku, inherit ou qualquer ID de modelo totalmente qualificado (ex.: "openai/o3", "google/gemini-2.5-pro").
model_overrides pode ser definido por projeto em .planning/config.json ou globalmente em ~/.gsd/defaults.json. Entradas por projeto têm precedência em conflitos; entradas globais sem conflito são preservadas.
Importante para Codex e OpenCode: Esses runtimes incorporam o modelo resolvido na configuração estática de cada agente no momento da instalação. Após editar model_overrides, execute novamente o instalador para que a alteração entre em vigor:
npx @opengsd/gsd-core@latest --codex --global # ou --opencode, --kilo, etc.
Modelos por tipo de fase (models)
Se você quer dizer "Opus para planejamento, Sonnet para todo o resto" sem precisar aprender todos os 33 nomes de agentes, use o bloco models. Ele mapeia seis tipos de fase para aliases de nível:
{
"model_profile": "balanced",
"models": {
"planning": "opus",
"discuss": "opus",
"research": "sonnet",
"execution": "opus",
"verification": "sonnet",
"completion": "sonnet"
}
}
Tipos de fase e seus agentes:
| Tipo de fase | Agentes cobertos |
|---|---|
planning |
gsd-planner, gsd-roadmapper, gsd-pattern-mapper |
research |
gsd-phase-researcher, gsd-project-researcher, gsd-research-synthesizer, gsd-codebase-mapper, gsd-ui-researcher |
execution |
gsd-executor, gsd-debugger, gsd-doc-writer |
verification |
gsd-verifier, gsd-plan-checker, gsd-integration-checker, gsd-nyquist-auditor, gsd-ui-checker, gsd-ui-auditor, gsd-doc-verifier, gsd-code-reviewer |
discuss |
gsd-assumptions-analyzer |
completion |
Reservado — nenhum subagente hoje; aceito pelo esquema para compatibilidade futura |
O bloco models aceita apenas aliases de nível (opus, sonnet, haiku, inherit). Para um ID de modelo totalmente qualificado, use model_overrides por agente.
Combinando models com uma exceção por agente:
{
"model_profile": "balanced",
"models": {
"research": "sonnet"
},
"model_overrides": {
"gsd-codebase-mapper": "haiku"
}
}
Todos os cinco agentes de pesquisa resolvem para sonnet exceto gsd-codebase-mapper, que está fixado em haiku.
Roteamento dinâmico — comece barato, escale em caso de falha
Se você quiser pagar pelos níveis mais baratos por padrão e só escalar quando um agente falhar em um controle de qualidade, habilite dynamic_routing:
{
"dynamic_routing": {
"enabled": true,
"tier_models": {
"light": "haiku",
"standard": "sonnet",
"heavy": "opus"
},
"escalate_on_failure": true,
"max_escalations": 1
}
}
Cada agente possui um nível padrão (light, standard ou heavy). Na primeira tentativa, o GSD escolhe tier_models[default_tier]. Se o orquestrador detectar uma falha suave (verificação inconclusiva, verificação de plano sinalizada, etc.), ele reinicia o agente um nível acima. max_escalations limita o total de novas tentativas.
Agentes que já estão em heavy não podem escalar mais.
Desativar a escalada mantendo a resolução dinâmica:
{
"dynamic_routing": {
"enabled": true,
"escalate_on_failure": false
}
}
Cada tentativa usa tier_models[default_tier] independentemente do resultado — útil quando você quer mapeamento explícito de nível para modelo sem o comportamento de escalada.
dynamic_routing está desabilitado por padrão. Omitir o bloco ou definir enabled: false preserva a resolução estática.
Usando o GSD em runtimes não-Anthropic
Se você instalou o GSD para Codex, OpenCode, Antigravity CLI ou Kilo, o instalador já definiu resolve_model_ids: "omit" na sua configuração. Isso instrui o GSD a pular a resolução de IDs de modelo Anthropic e deixar o runtime escolher seu próprio modelo padrão. Nenhuma configuração manual é necessária para o caso básico.
Se você quiser modelos por nível no Codex:
{
"runtime": "codex",
"model_profile": "balanced"
}
O GSD resolve cada alias de nível para o modelo nativo do Codex e o esforço de raciocínio definido no mapa de nível do runtime.
Se você quiser IDs de modelo por agente em qualquer runtime não-Claude:
{
"resolve_model_ids": "omit",
"model_overrides": {
"gsd-planner": "o3",
"gsd-executor": "o4-mini",
"gsd-debugger": "o3"
}
}
Para a referência completa de perfis cientes de runtime e a superfície model_policy (predefinições neutras em relação ao provedor adicionadas na v1.42), consulte Referência de configuração — Perfis de Modelo.
Precedência de resolução (maior para menor)
Quando múltiplas camadas se aplicam, o resolvedor escolhe a entrada de maior prioridade:
1. model_overrides[<agent>] — por agente; IDs completos; exceção direcionada
2. dynamic_routing.tier_models[<tier>] — quando habilitado; escala em falha suave
3. models[<phase_type>] — nível de fase grosseiro
4. model_profile (coluna por agente) — estratégia global de nível
5. Padrão do runtime — quando nada mais se aplica
Escolhendo o controle certo
| O que você quer | Use |
|---|---|
| Uma estratégia de nível para todos os agentes | model_profile |
| Ajuste grosseiro por fase ("Opus para planejamento") | models.<phase_type> |
| Precisão por agente ("forçar Haiku no mapeador de base de código") | model_overrides[<agent>] |
| Um ID de modelo totalmente qualificado para um agente específico | model_overrides[<agent>]: "openai/gpt-5" |
| Começar barato, escalar apenas em falha | dynamic_routing |
| Todos os agentes seguem o modelo da sessão (provedor não-Anthropic) | model_profile: "inherit" |