switching memory off switches skills off, and the chat then denies the feature exists
Mantenedores costumam responder em até 1 dia
Ninguém assumiu esta issue ainda.
Avaliação
- Dificuldade
- 4/5
- Tempo estimado
- 3-5 dias
- Facilidade para iniciantes
- 58/100
Direção de pesquisa
Start with importForeignSkillsBeforeFirstMessage in cmd/codeaf/chatv3.go:1169, then read renderSkillCatalog in internal/session/skillcatalog.go:64 and useSkillTool in internal/session/tools_skill.go:71. Trace both memory states through the real chat surface and the /skill picker. Done means memory-off users are told skills are switched off and the setting is named, while memory-on users see and can use the skill shelf.
Escrita pelo modelo de indexação a partir do texto da issue.
Descrição
What happened
A person with eighty-one skills on disk asked the chat "can you use skills ?" and
was told:
If you meant skills in the Claude Code SKILL.md sense, codeaf has no such
mechanism — harnesses and the notebook are what it has instead.
The binary was built from the head that carries the skills wave and its manual
pages. The feature was there. The answer denies it exists.
Why
memory.enabled was off.
~/.codeaf/config.json memory.enabled = off
~/.codeaf/graph.db 59.7 MB, facts table: 0 rows
~/.claude/skills 40 direct-child SKILL.md
~/.agents/skills 41 direct-child SKILL.md
importForeignSkillsBeforeFirstMessage (cmd/codeaf/chatv3.go:1169) returns on
its first line when memory is nil. Nothing is recorded, so
renderSkillCatalog (internal/session/skillcatalog.go:64) reads an empty
shelf and emits zero bytes, and useSkillTool (internal/session/tools_skill.go:71)
withholds the verb. Every one of those is behaving as designed.
The model then has no shelf, no verb, and no sentence about either, so it
reasons from the silence and invents a denial.
The two defects
One. Skills are gated on a setting that names something else, and nothing says
so. A person switches memory off to stop the program remembering things about
them. They also switch off skills, and are not told. That is one decision
producing two outcomes with only one of them disclosed.
Two. "Absent because impossible here" and "absent because it does not exist"
are the same silence. The absent-not-broken law works: it stops a model
planning a reply around a call that can only refuse. It does not stop the model
reasoning from the silence and concluding the capability was never built. The
law needs a companion clause rather than an exception: WHEN A CAPABILITY IS
WITHHELD BY A SETTING, SOMETHING HAS TO SAY SO.
This is not the emptiness law's territory. That law is about a number nobody has
yet: draw nothing rather than $0.00. It was never a licence to hide the
difference between "you have no skills" and "skills are switched off here".
Replication
- A profile with
memory.enabled = offand any number of SKILL.md folders
under a scanned root. - Ask the chat whether it can use skills.
- It denies the feature exists, rather than saying it is switched off.
Acceptance
End to end, through the real surface, in BOTH states.
- With memory off: the answer says skills are switched off on this machine and
names the setting. It does not say codeaf has no such mechanism. - With memory on: the shelf is there and the answer is yes.
- The
/skillpicker with memory off says the same thing rather than drawing an
empty list.
Then whatever mechanism carries it. One candidate: the catalog emits a single
line when the store is absent and the roots are not, which costs a person with
no skills nothing, because that person has no roots either.
Not in scope
#1378 is the manual side: no heading answers the capability question in either
state. Fixing the sentence here does not fix retrieval there, and neither is a
substitute for the other.
- Linguagem predominante
- Go
- Estrelas
- 115
- Forks
- 14
- Merge médio
- 9h 37min
- PRs com merge (30d)
- 755
Preparar o ambiente
Ainda não verificamos os arquivos de configuração deste projeto. Comece pelo README e veja nosso guia da primeira contribuição para os passos gerais.
Primeiros passos
- Leia a issue inteira e depois o guia de contribuição do projeto.
- Comente na issue dizendo que vai assumir — evita que duas pessoas façam o mesmo trabalho.
- Faça um fork do repositório e trabalhe em uma branch.
- Abra um pull request que referencie o número da issue.
Mais de Agent-Field/CodeAF
-
area:chat bug sev:papercut
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 86/100
Agent-Field/CodeAF#1592 ·
Mantenedores costumam responder em até 1 dia
-
area:headless bug sev:critical
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 88/100
Agent-Field/CodeAF#1566 · 1 responsável ·
Mantenedores costumam responder em até 1 dia
-
area:chat feature
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 88/100
Agent-Field/CodeAF#1510 ·
Mantenedores costumam responder em até 1 dia
-
area:tests bug
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 82/100
Agent-Field/CodeAF#1489 ·
Mantenedores costumam responder em até 1 dia
-
area:chat bug good first issue sev:papercut
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 78/100
Agent-Field/CodeAF#1470 ·
Mantenedores costumam responder em até 1 dia
Todas as issues de Agent-Field/CodeAF
Issues semelhantes
-
Remove CAAPFAbertakind/chore kind/cleanup needs-area
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 86/100
rancher/turtles#2848 · 3 comentários ·
Mantenedores costumam responder em até 1 dia
-
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 78/100
Mantenedores costumam responder em até 1 dia
-
good first issue
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 84/100
Mantenedores costumam responder em até 1 dia
-
priority: low 🌱 type: enhancement 💅🏼
Dificuldade 2/5 Meio dia Facilidade para iniciantes 84/100
nebari-dev/llm-serving-pack#199 ·
Mantenedores costumam responder em até 3 dias
-
Dificuldade 1/5 Menos de uma hora Facilidade para iniciantes 90/100
kedacore/keda#8225 · 1 comentário ·
Mantenedores costumam responder em até 1 dia