Conversation
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: a6cf56062e
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Remove the lead/worker provider feature which allowed switching between a lead model for initial turns and a worker model for subsequent turns with automatic fallback on failures. Removed across all layers: - goose crate: LeadWorkerProvider, LeadWorkerProviderTrait, ModelChange agent event, related posthog tracking, and all tests - goose-cli: lead/worker display logic, ModelChange stream event - goose-server: ModelChange message event - desktop UI: LeadWorkerSettings modal, lead/worker status display, CurrentModelContext, and related config labels Signed-off-by: Douwe Osinga <douwe@squareup.com>
DOsinga
force-pushed
the
remove-lead-worker
branch
from
a6cf560 to
bcb1e6c
Compare
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 0426566333
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| pub enum AgentEvent { | ||
| Message(Message), | ||
| McpNotification((String, ServerNotification)), | ||
| ModelChange { model: String, mode: String }, | ||
| HistoryReplaced(Conversation), |
There was a problem hiding this comment.
After AgentEvent::ModelChange is removed from the enum, all downstream matches need to be updated as well; crates/goose-server/src/routes/session_events.rs still matches AgentEvent::ModelChange (around line 465) and publishes MessageEvent::ModelChange (around line 468), while MessageEvent no longer defines that variant in routes/reply.rs. This leaves the server event-stream path inconsistent and causes goose-server to fail to compile when that module is built.
Useful? React with 👍 / 👎.
DOsinga
force-pushed
the
remove-lead-worker
branch
from
0426566 to
869afc0
Compare
Signed-off-by: Douwe Osinga <douwe@squareup.com> # Conflicts: # ui/desktop/src/hooks/useChatStream.ts
DOsinga
force-pushed
the
remove-lead-worker
branch
from
869afc0 to
ff31fc6
Compare
* origin/main: fix(openai): use Responses API for gpt-5.4 (#7982) Remove lead/worker provider (#7989) chore(release): release version 1.28.0 (#7991) Fix empty tool results from resource content (e.g. auto visualiser) (#7866) Separate SSE streaming from POST work submission (#7834) fix: include token usage in Databricks streaming responses (#7959) Optimize tool summarization (#7938)
* main: (22 commits) feat: add gemini-acp provider, update docs on subscription models + improvements to codex (#8000) fix(openai): use Responses API for gpt-5.4 (#7982) Remove lead/worker provider (#7989) chore(release): release version 1.28.0 (#7991) Fix empty tool results from resource content (e.g. auto visualiser) (#7866) Separate SSE streaming from POST work submission (#7834) fix: include token usage in Databricks streaming responses (#7959) Optimize tool summarization (#7938) fix: overwrite the deprecated googledrive extension config (#7974) refactor: remove unnecessary Arc<Mutex> from tool execution pipeline (#7979) Revert message flush & test (#7966) docs: add Remote Access section with Telegram Gateway documentation (#7955) fix: update webmcp blog post metadata image URL (#7967) fix: clean up OAuth token cache on provider deletion (#7908) fix: hard-coded tool call id in code mode callback (#7939) Fix SSE parsers to accept optional space after data: prefix (#7929) docs: add GOOSE_INPUT_LIMIT to config-files.md (#7961) Add WebMCP for Beginners blog post (#7957) Fix download manager (#7933) Improve the formatting of tool calls, show thinking, treat Reasoning and Thinking as the same thing (sorry Kant) (#7626) ...
Signed-off-by: Douwe Osinga <douwe@squareup.com> Co-authored-by: Douwe Osinga <douwe@squareup.com> Signed-off-by: esnyder <elijah.snyder1@gmail.com>
Signed-off-by: Douwe Osinga <douwe@squareup.com> Co-authored-by: Douwe Osinga <douwe@squareup.com> Signed-off-by: esnyder <elijah.snyder1@gmail.com>
2 participants
Summary
Remove the lead/worker provider feature entirely from the codebase.
The lead/worker provider allowed switching between a "lead" model for initial turns and a "worker" model for subsequent turns, with automatic fallback to the lead model on consecutive failures.
Changes
Deleted files (3):
crates/goose/src/providers/lead_worker.rs— full provider implementation (~500 lines)ui/desktop/src/components/settings/models/subcomponents/LeadWorkerSettings.tsx— settings modalui/desktop/src/components/settings/models/subcomponents/LeadWorkerSettings.test.tsx— its testsgoose crate:
LeadWorkerProviderTraitandas_lead_worker()/get_active_model_name()from theProvidertraitModelChangevariant fromAgentEventenum and all match armsGOOSE_LEAD_MODELcheck in providercreate()and related helper functionsgoose-cli:
ModelChangefromStreamEventenum and its handlingdisplay_session_info()by removing theprovider_instanceparameter and lead/worker display logicgoose-server:
ModelChangefromMessageEventSSE enum and its stream handlingDesktop UI:
CurrentModelContext/useCurrentModelInfofrom BaseChatGOOSE_LEAD_PROVIDER/GOOSE_LEAD_MODELconfig labelsTesting
cargo build✅cargo clippy --all-targets -- -D warnings✅cargo test -p goose✅npx tsc --noEmit✅pnpm test— all 321 UI tests pass ✅