qp-exa-dynamic
适用于 DeepSeek Harness ctx.web 接口的 Exa 网页搜索提供程序，默认启用 Dynamic Highlights，并提供 /exa 命令以在运行时更改 highlights、搜索类型和结果数量；exa_search 工具拥有独立的结果数量上限。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:Geighlord007/qp-exa-dynamic#e46f698450a352094bbd7d70c4a7cf06148ae1e7Qp Exa Dynamic 以 qp-exa-dynamic 发布，当前版本为 0.1.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
English | 简体中文
An Exa-backed WebSearchProvider for the
DeepSeek Harness ctx.web seam, with Exa
Dynamic Highlights on by default and an /exa command that changes highlights, search type and
result count at runtime.
dsh plugin --profile web add qp-exa-dynamic
The first-party @deepseek-ai/dsh-web-search-exa cannot reach Exa Dynamic Highlights, for two
independent reasons:
Its request body is hardcoded. It sends contents.highlights.highlightsPerUrl, and no config
field it accepts reaches a dynamic field.
Dynamic Highlights is a beta API and needs a header. Every request that sets dynamic: true
must also send Exa-Beta: dynamic-highlights-2026-08-28. That provider's headers are
authorization, content-type, accept and user-agent — no Exa-Beta. Without it Exa answers
HTTP 400:
{"error":"'highlights.dynamic' is in beta. Send the 'Exa-Beta: dynamic-highlights-2026-08-28' request header to use it.","tag":"INVALID_REQUEST"}
This provider sends both, and drops highlightsPerUrl entirely — measured against the live API, Exa
ignores that parameter, returning byte-identical payloads for values 1 and 5. It uses
maxCharacters instead, which is the knob that actually works when Dynamic Highlights are off.
Real /search calls, one query, 8 results:
| Configuration | Highlight characters |
|---|---|
| First-party provider's default (no working knob) | 51,152 |
This provider, dynamicHighlights: false + highlightsMaxCharacters: 1500 | 10,973 |
This provider, dynamicHighlights: true (default) | 12,716 |
Dynamic Highlights is not a uniform truncation: it concatenates the retrieved documents into one input, runs a single forward pass, and allocates a shared budget across the result set — so useful pages keep more context and redundant ones get less.
dsh plugin --profile web add qp-exa-dynamic
The package declares a dsh.bundle manifest, so its bundle patch inserts the provider row for you —
no hand-written patch entry is needed.
To select it, override the web row in $DSH_HOME/profiles/web/cordis.patch.yml:
- id: web
name: '@deepseek-ai/dsh-web'
config:
searchProvider: exa
fetchProvider: http
A patch replaces the targeted row's whole
configrather than merging into it, sofetchProvider: httpmust be restated or the fetch provider is dropped.
Then give it a key, either as plugin config:
- id: qp-exa-dynamic
name: qp-exa-dynamic
config:
apiKey: 'your-exa-api-key'
or through the environment. apiKey is declared role('secret'), so it never appears in a
describe() response — but a plain-text config file is still a plain-text config file; prefer the
environment when you can.
On
$DSH_HOME/.env. The plugin readsapiKeyEnv(defaultEXA_API_KEY) through the harness's launch-environment snapshot, which is documented to consult the inherited environment, the invoking directory's.envand the Harness home's.env. That worked in some deployments and not in others — on one Windows install the snapshot came back without the variable even though the file was correct, and the configapiKeyabove was the fix. If your provider reportsregistered but unavailable, the key is not reaching it; setapiKeydirectly.
Restart dsh web after changing the environment. cordis.patch.yml itself is hot-reloaded, so
config edits apply without a restart.
Every field has a safe default; you normally only supply a key.
| Field | Default | Meaning |
|---|---|---|
providerId | exa | Registry id. Change it only to coexist with another Exa provider. |
apiKey | unset | Literal key; falls back to apiKeyEnv. |
apiKeyEnv | EXA_API_KEY | Environment variable consulted when apiKey is unset. |
baseURL | https://api.exa.ai | Exa endpoint; /search is appended. |
searchType | auto | Retrieval type — see below. Runtime-settable with /exa type. |
numResults | 8 | Source cap. Runtime-settable with /exa results. |
dynamicHighlights | true | On by default; adds the required Exa-Beta header. Runtime-settable with /exa. |
highlightsMaxCharacters | unset | Per-page highlight cap, used only when dynamicHighlights is false. |
dynamicHighlights is never combined with highlightsMaxCharacters: Exa sizes and distributes the
shared budget itself when dynamic is on, and its docs warn against combining the two.
/exa commandTyped in the composer. It runs directly against the interface and creates no model message.
| Command | Effect |
|---|---|
/exa | Toggle Dynamic Highlights |
/exa on / /exa off | Set them explicitly |
/exa type | List the retrieval types |
/exa type deep | Set the retrieval type |
/exa results | Report the source cap |
/exa results 3 | Set the source cap |
/exa status | Report every knob, the available types, and the real ceiling |
Plain words, no punctuation: the command declares no argument hint, so the composer inserts no
template to edit around. /exa status lists the retrieval types too, so "which types were there
again" never costs a second command, and a mistyped argument replies with copy-pasteable examples.
Writes land in the qp-exa-dynamic settings namespace's user layer, so they survive a
restart. Clearing that section returns the plugin to its configured defaults.
Measured on one provider instance, one query: switching Dynamic Highlights off took the same search from 12,716 to 57,958 highlight characters — a 4.6x difference, applied on the next search.
exa_search toolThe plugin also registers a second, model-facing tool beside web_search:
exa_search(query: string, maxResults?: integer) // maxResults 1-50
It exists because of a hard structural fact: ctx.web.search() caps its result at the caller's
request.maxResults, and dsh-tool-web sends its own searchMaxResults on every call — so no
provider can ever exceed that cap, and raising it means forking an agent preset. This tool owns its
own request.maxResults, so the result count becomes a per-call model argument instead of a
deployment-level ceiling.
That makes the preset fork optional. Two ways past the default 8 sources:
| Want | Use | Needs the preset fork? |
|---|---|---|
| 20 sources for one question | exa_search(query, maxResults: 20) — just ask in words | no |
/exa results 20 to work | the /exa command | yes |
/exa results is a fine setting to keep even without the fork, because it is what this tool falls
back to: with /exa results 20 set, exa_search(query) with no maxResults returns 20. It is
web_search alone that stays clamped to the deployment's ceiling.
The tool goes through ctx.web like web_search does, so it uses the same selected provider, the
same search type and the same Dynamic Highlights setting; only the count differs. Its ceiling of 50
is its own — dynamic highlights measured ~1.6k characters per source, so 50 is already ~20k tokens
of context.
A prompt section next to web_search's tells the model when to reach for it; ordinary lookups stay
on web_search. If the composition has no tools registry the provider still mounts and only the
tool is absent.
Exa's type is the latency/quality dial. All eight were verified against the live API; measured
latency for one query, 8 results:
| Type | Measured | Use |
|---|---|---|
keyword | 464 ms | Keyword only, fastest |
neural | 737 ms | Semantic retrieval |
fast | 798 ms | Speed with minimal quality loss |
instant | 856 ms | Real-time (chat, voice) |
auto | 1,914 ms | Default |
deep-lite | 3,116 ms | Lightweight synthesized output |
deep | 5,282 ms | Multi-step reasoning |
deep-reasoning | 18,278 ms | Hardest research tasks |
The first-party provider's schema lists only auto, keyword and neural — that set is stale.
This provider exposes all eight.
deep* types are discounted by this seamMeasured through this provider's own class, same query, dynamic highlights on:
| Type | Time | Sources returned |
|---|---|---|
fast | 718 ms | 8 |
auto | 215 ms | 8 |
deep | 6,891 ms | 3 |
deep-reasoning | 14,776 ms | 4 |
The raw API returns 8 results for deep; the rest carry no non-blank highlight and are dropped,
because the seam has no other field to derive a snippet from and inventing one would make the seam
lie. The deep* family's real product is the synthesized output, which WebSearchSource has no
field for. In practice the useful range here is keyword, neural, fast, instant and auto.
dsh-tool-webWorth stating plainly, because it is easy to misread:
web_search tool takes only queries — the model cannot ask for a count.dsh-tool-web: searchMaxResults, default 8. Its own comment:
"The consumer owns the returned-context limit; providers and models do not."maxResults on every call, and the seam truncates the returned sources to it —
so no provider can exceed that ceiling.That makes this plugin's numResults one-directional: it can pull the count down, never up.
| Configured | Tool ceiling | Sent to Exa |
|---|---|---|
| 3 | 8 | 3 |
| 12 | 8 | 8 (clamped) |
| 20 | 8 | 8 (clamped) |
/exa status and /exa results report the ceiling the provider actually observed, so a clamped
value is explained rather than silently applied.
Raising the ceiling is not a profile-patch edit in the Web app. dsh-web-app disables the host
tool-web row — - id: tool-web / disabled: true — because only the web service and its search
provider are host-side; the model-facing tool is per session, and the one that actually runs comes
from the agent preset. The shipped standard preset's row carries fetch and searchTimeoutMs
and no searchMaxResults, so it takes the schema default of 8. A profile patch targeting tool-web
lands on the disabled host row and does nothing at all.
Changing it therefore means forking the preset: copy standard into $DSH_HOME/.agent-presets/, add
searchMaxResults to its tool-web row, and select it as the default. That is a real trade — a copy
does not track upstream updates to the shipped preset, and the default is read when a session is
created, so running sessions keep the preset they assembled with. For most uses leaving it at 8 is
the better deal: /exa results still pulls the count down, which is the direction that saves
tokens.
dynamic-highlights-2026-08-28 is a research preview; a change on
Exa's side means updating DYNAMIC_BETA_VALUE.category, domain or date filters, and no full text. Those are Exa features this provider
does not expose yet.exa
by default; running both needs a distinct providerId on one of them.0.1.5-rc.1 only, which is what the peer ranges pin./exa writes are in-memory only. The provider itself works
either way; without a command registry there is simply no /exa.node test/index.test.js # 40 unit tests, no API key needed
EXA_API_KEY=... node test/live.mjs # hits the real API, spends credit
Run the test file directly rather than through node --test: the test runner spawns a child process
per file with piped stdio, which fails with spawn EPERM in a restricted sandbox.
dsh plugin --profile web remove qp-exa-dynamic
Remove the web override from cordis.patch.yml to return to the built-in DeepSeek search. That
edit is hot-reloaded, so it takes effect immediately.
MIT