spike(framework): define the Freebuff support contract
Maintainer thường phản hồi trong vòng 1 ngày
Chưa có ai nhận issue này.
Đánh giá
- Độ khó
- 5/5
- Thời gian dự kiến
- Hơn một tuần
- Mức phù hợp với người mới
- 42/100
- Loại issue
- Tính năng
- Độ rõ ràng
- Khá rõ ràng
- Mức độ hoạt động
- Sôi nổi
- Công nghệ
- typescript
- Lĩnh vực
- cli, developer-experience, tooling
Hướng nghiên cứu
Start with cli/src/kernel/tool.ts and the five reference tables: detection.md, tools.md, tool-detect.md, sync-arguments.md, plus plugins/aidd-context/hooks/update_memory.js. Then inspect the existing OpenCode and Kilo profiles and bridges, and verify whether Freebuff has a usable session-start hook surface. Done means Freebuff detection, AGENTS.md wiring, profile delivery, and maintenance behavior are consistently represented and validated.
Do mô hình lập chỉ mục viết ra từ nội dung của issue.
Mô tả
Problem to solve
aidd-context has no representation for Freebuff. It is absent from all five places that enumerate
AI tools, including TOOL_FILES in
update_memory.js. A project that is worked on with
Freebuff therefore cannot keep its AIDD memory current.
On a real project that runs AIDD, with the copy of the hook installed in that project (byte-identical
to upstream/next):
$ node .opencode/hooks/aidd-context/update_memory.js opencode
# exit 0, memory block updated
$ node .opencode/hooks/aidd-context/update_memory.js freebuff
update_memory: unknown tool freebuff (known: claude, codex, cursor, opencode, copilot)
# exit 1, refused
$ node .opencode/hooks/aidd-context/update_memory.js kilo
update_memory: unknown tool kilo (known: claude, codex, cursor, opencode, copilot)
# exit 1, refused
The effect is not cosmetic. Writing a new memory file and syncing:
| synced for | exit | block lists the new file |
|---|---|---|
opencode |
0 | yes |
freebuff |
1 | no |
kilo |
1 | no |
The guard is doing its job — the tool is simply not in the list.
This is not a Freebuff-shaped gap. Kilo is in the same position today: AiToolId in
cli/src/kernel/tool.ts carries six values including kilo, and 12 files under cli/src/ know
the tool, yet kilo appears zero times in plugins/ and update_memory.js kilo exits 1. Two
tools, one cause: the wiring table and the plugin reference tables are maintained separately from
the tool registry, and nothing checks that they agree.
Proposed solution
Add Freebuff as a detected tool wired to AGENTS.md, alongside codex, cursor and opencode.
- Detection signal:
.freebuff/, a project-scoped directory holdingproject-id. It is created
when a project is opened in Freebuff, so it is behavioural rather than inferred — I watched it
appear when I started a session. The vendor writes it fromsetProjectRootin
cli/src/project-files.tswitheveryRepository: IS_FREEBUFF, so it is written in every Git
project, not only in ones without a hosted remote; I confirmed it present in a repo that does
have a GitHub remote. - Wiring target:
AGENTS.md. Freebuff reads projectAGENTS.mdandCLAUDE.md. The vendor
quick-start says "New projects — if you don't already have an AGENTS.md or CLAUDE.md (Codebuff
will also read these files)" — and that page is the right evidence here, because Freebuff is the
same CLI built withFREEBUFF_MODE=true, while the knowledge-file resolution lives in
common/src/constants/knowledge.tsandsdk/src/run-state.ts, neither of which is gated on that
flag. PickingAGENTS.mdalso matches how #914 settled the same question for Kilo. - No new surface:
AGENTS.mdis already the target for three tools, so the existing "tools
sharing a context file wire it once" rule intools.mdcovers this.
Wiring is four table edits (detection.md, tools.md, tool-detect.md, sync-arguments.md) plus
the TOOL_FILES entry. That is necessary and not sufficient — see below.
Content type
- Other
Target tool(s)
- Other — Freebuff, which the dropdowns do not list.
Additional context
-
The five tables are the ones that disagree with each other, and the
sync-arguments.mddefault
is where a fourth writer shows up. Its rule reads "Otherwise derive args from synced context
files;AGENTS.mddefaults tocodex". A third tool already targetsAGENTS.md, so that
default is already arbitrary; a fourth makes it arbitrary in a way a reader will hit. Worth
settling as part of this, not after. -
Wiring is half of it, and the half I cannot deliver is the half that matters.
TOOL_FILESis
the wiring table; it does not maintain anything. Maintenance runs per tool through the CLI
profiles, and all six existing profiles declareacceptsHooks: true— so a tool is not
automatically maintained, and a new one needs its profile wired deliberately:tool hook delivery mechanism claude yes native plugin, pluginRootToken=CLAUDE_PLUGIN_ROOTcopilot yes native plugin, .github/plugins/codex yes writes a hook entry to .codex/config.tomlcursor yes hooksContentFormat: "flat", routed to.cursor/hooks.jsonopencode yes generated bridge ( opencode-hooks-bridge.ts)kilo yes generated bridge ( kilo-hooks-bridge.ts)freebuff no profile — The distinction that matters is
mode: "flat"versus native. Claude, Copilot and Cursor take
hooks.jsonmore or less as-is. OpenCode and Kilo cannot express it natively, so the CLI
generates a bridge module that parseshooks.jsonand replays theSessionStartcommands.
Freebuff would need a profile and one of those two shapes decided for it — which is a question
for whoever validates this, not a guess I should make in a PR. I could not find a session-start
hook surface in the vendor's published source: there is nohooks.jsonconcept, and
SessionStartappears nowhere. The one hook concept that does exist isrun_file_change_hooks,
and its SDK path is an explicit no-op ("File change hooks are not supported in the SDK
environment") — so I cannot claim a bridge is generatable. -
I checked the vendor's source rather than assuming, and its docs disagree with its own code.
Freebuff resolves one knowledge file per directory, first match wins
(selectHighestPriorityKnowledgeFileinsdk/src/run-state.ts, walking
KNOWLEDGE_FILE_NAMES_LOWERCASEover that directory's candidates). That list is
['AGENTS.md', 'CLAUDE.md'](common/src/constants/knowledge.ts);knowledge.mdis no longer a
knowledge file, andisKnowledgeFileadditionally accepts*.knowledge.md. Two comments in
run-state.tsstill describe the oldknowledge.md-first ordering while the code below them no
longer implements it, and the vendor's publisheddocs/tips/knowledge-filesstill tells users
~/.knowledge.mdis "highest priority" — a fileloadUserKnowledgeFilesno longer matches at
all. So the code is right and the docs are stale here.AGENTS.mdis therefore the correct
target, and a project that also carries aknowledge.mdis not a special case. I am reporting
this only as the reason my choice is grounded; the doc fix is theirs to make. -
I have not checked Discussions, only issues. Searched for
freebuffandcodebuffacross
open and closed issues: no hit, so I do not believe this is tracked yet. -
Sequencing with #914 is a judgement call for the maintainers, not mine.
-
I am not asking for a PR to be opened pre-emptively. Per
CONTRIBUTING.mdan issue is validated
first — a Certified Member or Maintainer moves it toTodo— and after that anyone may pick it up,
including me.
Code of Conduct
- I agree to follow this project's Code of Conduct.
- Ngôn ngữ chính
- TypeScript
- Star
- 481
- Fork
- 45
- Merge trung bình
- 1 ngày 13 giờ
- Pull request đã merge (30 ngày)
- 91
Chuẩn bị môi trường
Bắt đầu từ đâu
- Đọc hết issue, rồi đọc hướng dẫn đóng góp của dự án.
- Bình luận trên issue rằng bạn sẽ nhận — tránh hai người làm cùng một việc.
- Fork repository và làm thay đổi trên một nhánh.
- Mở pull request có tham chiếu số hiệu của issue.
Issue khác của ai-driven-dev/framework
-
Độ khó 2/5 1-3 giờ Mức phù hợp với người mới 86/100
ai-driven-dev/framework#1311 ·
Maintainer thường phản hồi trong vòng 1 ngày
-
Độ khó 2/5 1-3 giờ Mức phù hợp với người mới 79/100
ai-driven-dev/framework#1244 ·
Maintainer thường phản hồi trong vòng 1 ngày
-
Độ khó 2/5 1-3 giờ Mức phù hợp với người mới 78/100
ai-driven-dev/framework#1197 ·
Maintainer thường phản hồi trong vòng 1 ngày
-
refactor(aidd-context): apply the new skill template to learnCó thể đã có người làm @blafourcade đã nhận 3 ngày trước. Đang mở
Độ khó 2/5 1-3 giờ Mức phù hợp với người mới 72/100
ai-driven-dev/framework#1186 · 1 người được giao ·
Maintainer thường phản hồi trong vòng 1 ngày
-
Độ khó 2/5 1-3 giờ Mức phù hợp với người mới 83/100
ai-driven-dev/framework#1163 · 1 bình luận ·
Maintainer thường phản hồi trong vòng 1 ngày
Tất cả issue của ai-driven-dev/framework
Issue tương tự
-
db-d1-sqlite: upsert is aliased to updateOne, so payload.kv.set never inserts new keysCó thể đã có người làm @pcbeingused333 đã nhận hôm nay. Đang mởBug db: d1-sqlite Payload OSS
Độ khó 2/5 1-3 giờ Mức phù hợp với người mới 76/100
payloadcms/payload#19766 ·
Maintainer thường phản hồi trong vòng 1 ngày
-
Độ khó 2/5 1-3 giờ Mức phù hợp với người mới 68/100
device-management-toolkit/sample-web-ui#3711 ·
Maintainer thường phản hồi trong vòng 1 ngày
-
bug impact:low Team: SecuritySolution Team:Defend Workflows v9.6.0
Độ khó 2/5 1-3 giờ Mức phù hợp với người mới 72/100
elastic/kibana#306401 · 3 bình luận ·
Maintainer thường phản hồi trong vòng 1 ngày
-
Độ khó 2/5 1-3 giờ Mức phù hợp với người mới 68/100
agentes-chat/agentes-chat#927 ·
Maintainer thường phản hồi trong vòng 1 ngày
-
Closing a pinned tab jumps to the Tabs section instead of the next open pinned tabCó thể đã có người làm @seenimohamed đã nhận hôm nay. Đang mởbug
Độ khó 2/5 1-3 giờ Mức phù hợp với người mới 78/100
ardia-browser/ardia#2769 ·
Maintainer thường phản hồi trong vòng 1 ngày