Skip to content

refactor(opencode): reduce streaming latency and request overhead #19237

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
jwcrystal wants to merge 1 commit into
base: dev
Choose a base branch
from
+36 −35
Open

refactor(opencode): reduce streaming latency and request overhead #19237

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion packages/opencode/src/bus/index.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,7 +84,7 @@ export namespace Bus {
return Effect.gen(function* () {
const state = yield* InstanceState.get(cache)
const payload: Payload = { type: def.type, properties }
log.info("publishing", { type: def.type })
log.debug("publishing", { type: def.type })

const ps = state.typed.get(def.type)
if (ps) yield* PubSub.publish(ps, payload)
Expand Down
65 changes: 33 additions & 32 deletions packages/opencode/src/session/llm.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,38 +128,39 @@ export namespace LLM {
...input.messages,
]

const params = await Plugin.trigger(
"chat.params",
{
sessionID: input.sessionID,
agent: input.agent,
model: input.model,
provider,
message: input.user,
},
{
temperature: input.model.capabilities.temperature
? (input.agent.temperature ?? ProviderTransform.temperature(input.model))
: undefined,
topP: input.agent.topP ?? ProviderTransform.topP(input.model),
topK: ProviderTransform.topK(input.model),
options,
},
)

const { headers } = await Plugin.trigger(
"chat.headers",
{
sessionID: input.sessionID,
agent: input.agent,
model: input.model,
provider,
message: input.user,
},
{
headers: {},
},
)
const [params, { headers }] = await Promise.all([
Plugin.trigger(
"chat.params",
{
sessionID: input.sessionID,
agent: input.agent,
model: input.model,
provider,
message: input.user,
},
{
temperature: input.model.capabilities.temperature
? (input.agent.temperature ?? ProviderTransform.temperature(input.model))
: undefined,
topP: input.agent.topP ?? ProviderTransform.topP(input.model),
topK: ProviderTransform.topK(input.model),
options,
},
),
Plugin.trigger(
"chat.headers",
{
sessionID: input.sessionID,
agent: input.agent,
model: input.model,
provider,
message: input.user,
},
{
headers: {},
},
),
])

const maxOutputTokens =
isOpenaiOauth || provider.id.includes("github-copilot")
Expand Down
4 changes: 2 additions & 2 deletions packages/opencode/src/session/processor.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,7 +84,7 @@ export namespace SessionProcessor {
const part = reasoningMap[value.id]
part.text += value.text
if (value.providerMetadata) part.metadata = value.providerMetadata
await Session.updatePartDelta({
Session.updatePartDelta({
sessionID: part.sessionID,
messageID: part.messageID,
partID: part.id,
Expand Down Expand Up @@ -307,7 +307,7 @@ export namespace SessionProcessor {
if (currentText) {
currentText.text += value.text
if (value.providerMetadata) currentText.metadata = value.providerMetadata
await Session.updatePartDelta({
Session.updatePartDelta({
sessionID: currentText.sessionID,
messageID: currentText.messageID,
partID: currentText.id,
Expand Down
Loading