Is there a way to bind the same *local* KV store to 2 different apps when developing locally?
Is there a way to bind the same local KV store to 2 different apps when developing locally?
HUse
--persist-to to point them both to the same directory. As long as they have the same ID, they should pull from the same place
ZAwesome thanks.
JHas anybody run into issues (or is it a common issue) with R2 bindings running locally via wrangler, where binary data (eg. a png) is corrupted when downloaded (
env.R2.get(...)). And appears the encoding is borked somewhere along the way. I can see that the file is not corrupted on the disk (within the .wrangler folder) but when I download the file, via the worker, it "corrupts". I the screenshot attached, the left is the original file, and the right is after downloading from R2. It's worth mentioning that if I upload a text file (eg. xml) - it works fine.
JRunning the same code on an actual Cloudflare Worker works fine.
BI started seeing authz errors today when trying to import data to a newly created db.
is now giving me this:
I just updated wrangler to 3.57.0. I'll report if someone thinks it might be a bug. Thanks
wrangler d1 execute <DBNAME> --remote --file=./creation_insertion_stmts.sqlis now giving me this:
I just updated wrangler to 3.57.0. I'll report if someone thinks it might be a bug. Thanks
Knot authorized means you tried using a pragma/function that isn't allowlisted
BThank you, I do have that
PRAGMA foreign_keys=OFF;KD1’s foreign key enforcement is equivalent to SQLite’s PRAGMA foreign_keys = on directive. Because D1 runs every query inside an implicit transaction, user queries cannot change this during a query or migration.
KKYou can use
defer_foreign_keys thoughBthank you, looks like I need to start leaving off the
https://developers.cloudflare.com/d1/build-with-d1/import-data/#convert-sqlite-database-files
I missed the change.
BEGIN TRANSACTION; and COMMIT; as well. I'll review that allowlist. Thanks again, I've been able to import everything remotely now.https://developers.cloudflare.com/d1/build-with-d1/import-data/#convert-sqlite-database-files
I missed the change.
Cloudflare Docs
D1 allows you to import existing SQLite tables and their data directly, enabling you to migrate existing data into D1 quickly and easily. This can be …
MI used to use
in my project, but since today (it's been a few days since I haven't toucher it though) I get an error for that:
and I can't see the arguments that replace that feature.
what should I use now to replace that?
in my project, but since today (it's been a few days since I haven't toucher it though) I get an error for that:
and I can't see the arguments that replace that feature.
what should I use now to replace that?
KThey haven't been removed, they're still there.
Mhmmmm, not sure what causes that error message "✘ [ERROR] Unknown arguments: dry-run, dryRun, outdir, deploy" .... repeating I get:
not sure how "main" should be used, or is a script reference missing?
not sure how "main" should be used, or is a script reference missing?
KMeans it can't find a Wrangler.toml in that folder, usually
MI don't see deploy in that list...., but it still works I guess....
Mthere's a wrangler.toml (lowercase 'W')
MI'm confused:
Mwoa...
HThat's a tricky bugger right there. We recommend installing
wrangler within a project, then calling it from there, so that you consitently use the same versionMis it recommended calling directly, or via npx?
(I know virtually zero about npm and npx)
(I know virtually zero about npm and npx)
Mscripts in jsons seem to use npx
Min .ts sorry
HCalling directly is what I do, though afaik
npm doesn't actually support that for arbitrary commands, so npx would probably be the next best thing.HI use
pnpm for arbitrary command execution using the locally installed package: pnpm wrangler deploy [whatever]MI have multiple folders (a worker, a pages app, functions) - so maybe I need to upgrade wrangler in all of them when updating?
MOK, for now I'm calling wrangler directly and it's solved that....now to fix broken Leptos app that won't deploy 
EHello, I'm thinking of using an API token because wrangler's oauth doesn't support multiple accounts.
How can I create an API token with privileges equivalent to wrangler login?
That is, an API token that has these permissions:
account:read
user:read
zone:read
workers:write
workers_kv:write
workers_routes:write
workers_scripts:write
workers_tail:read
d1:write
pages:write
ssl_certs:write
constellation:write
ai:write
queues:write
offline_access
How can I create an API token with privileges equivalent to wrangler login?
That is, an API token that has these permissions:
account:read
user:read
zone:read
workers:write
workers_kv:write
workers_routes:write
workers_scripts:write
workers_tail:read
d1:write
pages:write
ssl_certs:write
constellation:write
ai:write
queues:write
offline_access
Ldo you guys use the
satisfies in your workers?Li see it's present in some parts of the docs and not present in others
Lin other parts they use the types on the parameters instead
Jshort answer: a combo of both provides the best DX.
long answer: https://github.com/cloudflare/cloudflare-docs/pull/14007
long answer: https://github.com/cloudflare/cloudflare-docs/pull/14007
Lthe one you are using misses stuff
LYou could use
request: Request, env: EnvJYou don't need those with
satisfies ExportedHandler<Env> - the arguments are already typed
Lin some cases you also have extra stuff like here message batch
Lalso this is not needed?
JThat could be refactored to use
ExportedHandler - return type annotation too, yes
Lreturn type annotation?
Lpromise void u mean?
JAll you need is the return type like
: Promise<Response> for better DX, and then satisfies ExportedHandler<Env>;JYeah,
queue handlers don't need to return anything so: Promise<void> works wellLbut
satisfies operatore introduced in TypeScript 4.9 shouldn't just check that the function matches expect class?