Find your next challenge.

The problem

Attach stable per-conversation session identifiers, such as UUID-based OpenCode headers, to outbound inference requests. Allow provider- and model-level control over header names, formats, and omission, together with related prompt-cache settings to improve routing and cache affinity.

Possibly addressed by:Opencode Session Header · X Opencode Session · Session Header

The problem

Allow team leads to specify an optional provider, model, and reasoning effort for each teammate, including cheaper or local models, while defaulting to the parent session and enforcing configured model allowlists.

Possibly addressed by:Agent Team Model · Subagent Model Config · Configurable Subagents

The problem

Provide an official way to identify and remove or rewind past a moderation-rejected node, restoring files and truncating later history so the session can continue safely. Expose a distinct moderation error to help clients stop futile retries.

The problem

Allow web search to use independently configured providers, credentials, endpoints, and optional auxiliary models, including a zero-LLM mode and reuse of the selected model when needed. Clearly expose provider failures and any search-related model charges, with appropriate safeguards and cost tracking.

Possibly addressed by:Web Search Diy · Web Search · Websearch

The problem

Provide an official VS Code extension for running DeepSeek Harness from the editor sidebar, including connections to remote development systems over SSH.

Possibly addressed by:Vscode Shell · Vsceditor · Visual Studio

The problem

Display effective context and session limits, including output reserves, and warn before compaction or exhaustion. Clearly distinguish input-context exhaustion, output truncation, and automatic compaction, while offering recovery guidance such as /compact, /clear, a new session, or one-click compaction.

Possibly addressed by:Idle Compactor · Context Budget · Auto Compact

The problem

Allow users to create isolated sessions without selecting a project or workspace, with an explicit working directory and existing sandbox and approval semantics. Sessions can later be saved or moved into a project.

Possibly addressed by:Temp Workspace · Project Context · Desktop Temporary Workspace

The problem

Provide a backend-agnostic, first-party memory plugin or service with session, agent, tenant, topic, and repository scoping; automatic capture and recall; safe lifecycle handling; provenance, deduplication, bounded injection, and tools for managing facts and lessons. Support importing existing memories and preserving history safely across migrations.

Possibly addressed by:Agent Memory · Plugin Memory · Hybrid Memory

The problem

Provide a standardized way for plugins to declare capabilities such as file, environment, network, shell, and registry access, with clear user warnings or confirmations for sensitive operations. This would make plugin permissions and supply-chain risks more transparent before and during execution.

Possibly addressed by:Plugin Security Review · Plugin Audit · Plugin Vetting

The problem

Expose deterministic pre- and post-compaction integration points, including a post-compaction lifecycle signal, so plugins can restore or re-seed model-visible context after compaction without polling.

Possibly addressed by:Force Compact · Compactor · Manual Compact Plugin

The problem

Expose each model’s reasoning-effort support, defaults, and multimodal input metadata so the model picker can display accurate capability indicators and clients can validate selections.

Possibly addressed by:Better Reasoning Effort · More Models Thinking Level · Reasoning Effort

The problem

Add official support for packaging macOS desktop apps locally through the existing `--unsigned` workflow, skipping signing and notarization and placing artifacts in `unsigned-artifacts/`. This should work without Apple credentials, source changes, or a maintained patch.

Possibly addressed by:Desktop Packager

The problem

Let users navigate previously submitted prompts with Up/Down keys and recover from unexpected execution paths through a flexible rewind mechanism, across the relevant interfaces.

Possibly addressed by:Keyboard History · Input History · Prompt History

The problem

Add reusable sequential workflows with independently configurable prompts, models, and skills per node, including multiple ordered prompts within a node. All nodes should share conversation context and a workspace so workflows can run repeatedly without manual reconfiguration or copying intermediate results.

Possibly addressed by:Workflow Designer · Task Engine · Agent Dag Workflow

The problem

Improve responsiveness and reliability of the web interface when many subagents run concurrently by batching streamed events, coalescing token updates, and avoiding excessive client-side rendering overhead.

Possibly addressed by:Subagent Team · Subagents · Background Agents

The problem

Give each session an isolated working directory and allow filesystem operations outside agent turns to target an explicit session scope. Propagate session identity through filesystem APIs and endpoints so shared DSH processes can safely serve multiple users.

Possibly addressed by:Session Scope · Session Workspace · Multi Workspace

The problem

Add a persisted composer preference that lets users choose whether Enter or Cmd/Ctrl+Enter sends a message, with the other action inserting a newline. Preserve IME composition, default behavior, and Queue/Steer semantics during execution.

Possibly addressed by:Composer Modenter · Composer Keys Setting · Enter Send

The problem

Make Goal mode detect repeated no-progress rounds and waiting or idle states, pausing or stopping continuation when background work is running or no meaningful task remains. This prevents unnecessary calls, injected turns, and token consumption.

Possibly addressed by:Goal Auto · Goal Pause Guard · Goal Restart

The problem

Provide task-aware model selection with a provider-organized picker and an independent reasoning-effort control. Make the selection available in Composer and workflow dialogs, with persistence and keyboard-accessible controls.

Possibly addressed by:Model Selector · Effort · Model Select Plus

The problem

Allow each model in a provider or catalog route to declare its wire protocol and use that declaration for discovery and request routing across Anthropic Messages, OpenAI Chat Completions, and OpenAI Responses. Support adding protocols through the UI and provide a clear diagnostic when one cannot be inferred.

Possibly addressed by:Live Model Catalog · Provider Hub · Model Catalog Refresh