1. Is this an official DeepSeek site?
No. It is an independent notes site written from real runs by a user. Nothing here is an official statement, and no page uses DeepSeek branding. See the about page.
2. Why does a plugin I installed make the app hang with no output?
Most likely a missing client.inject package. Measured: a plugin naming six client packages the host lacked produced seventy seconds of zero output, a live process, and no error. There is no version-gate refusal to go looking for. See the plugin verification table.
3. Why did the version gate not stop me installing an incompatible plugin?
Because it does not exist. Measured on 0.1.2-alpha.5: a plugin requiring >=0.2.0-rc.2 installed fine, composed fine in --dump-config, and was refused by nothing. Of 87 first-party packages, zero declare engines.dsh. See the version gate entry.
4. My token numbers are much lower than yours. Why?
Probably reading only part of the three figures. Measured on one session: taking the last usage per turn gave 28,827 while summing per step gave 126,551. Also, inputTokens is cache-miss input only; cache hits are separate. See the measurement method page.
5. Is a cache hit cheaper even when total tokens go up?
Yes. Measured: run two used 51 percent more total tokens than run one at a sixth of the cost, because 47,872 of its tokens were cache hits at $0.003 per million against 16,210 cache-miss tokens at $0.15. See the cache-hit entry.
6. Should I optimise tokens or money?
Money, and within money the output line. Across six measured tasks output was 59 to 69 percent of cost, because output is priced 200 times a cache-hit input token. Cutting output and step count saves more than cutting input. See the cost baseline.
7. Can I trust the English pages for exact wording?
For commands and numbers, yes. For prose, no.Every English page is a generated translation with no native review. Where a detail is ambiguous, the Chinese page governs. See the translation status page.