Find your next challenge.

The problem

Let users access models through existing subscriptions such as Claude within DSH, using secure authorization such as OAuth where possible instead of requiring separate API keys.

Possibly addressed by:Openai Subscription · Subscriptions · Subscriptions

The problem

Add OAuth 2.0 authentication to the MCP client’s streamable-HTTP transport, including discovery, token persistence, refresh-token rotation, and automatic recovery from 401 responses. This would support MCP servers with short-lived access tokens without requiring users to update static headers or reauthenticate manually.

Possibly addressed by:Mcp Client Plus · Mcp Center · Mcp Connector

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

Record durable, accurately attributed usage and cost events for foreground, auxiliary, tool, compaction, retry, and subagent calls. Provide session totals, warnings, and configurable spending circuit breakers.

Possibly addressed by:Usage Cost · Token Usage Cost · Token Use

The problem

Keep listeners bound to localhost by default, while allowing explicit binding to a selected LAN interface or other address with authentication, host-trust protections, configurable access controls, clear exposure warnings, and gated wildcard binds such as `0.0.0.0`.

Possibly addressed by:Web Lan Access · Lan Proxy · Lan Gateway

The problem

Register and handle dsh:// session links during cold starts and second-instance launches, forwarding them to the web app or desktop navigation to reopen or focus sessions. Provide session actions to copy deep links and clearly report unavailable sessions.

Possibly addressed by:Deeplink · Session Link · Session Deeplink

The problem

Add an automatic approval mode that evaluates proposed agent actions using configurable policies and, where useful, a classifier. Support soft and hard denials while retaining explicit approval gates for risky, destructive, costly, or external operations.

Possibly addressed by:Auto Approver · Auto Approve · Approval Ai Review

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 application-wide font customization and scaling across conversations and UI surfaces, including keyboard shortcuts for increasing or decreasing size and a higher maximum size limit.

Possibly addressed by:Font Size · Font Settings · Ui Tweaks

The problem

Add persistent, editable per-model modality capabilities for text, image, audio, and video across providers, including Strata. Use these declarations to report limits and route attachments and multimodal results correctly to compatible models.

Possibly addressed by:Model Modality · Models Input Modalities · Model Capability

The problem

Provide architecture-level deletion for individual turns and entire sessions, including permanent removal of persisted and in-memory session data and a typed lifecycle event for plugins.

Possibly addressed by:Session Delete · Archive Manager · Session Delete

The problem

Offer official desktop and terminal/TUI interfaces across supported platforms, including terminal operation in virtual machines and headless servers without requiring a graphical environment.

Possibly addressed by:Tui · Deepseek Harness Tui · Omc Tui

The problem

Defer and selectively inject tool descriptions and schemas only when the model needs them or the available tool set changes, reducing prompt, latency, and caching overhead while retaining tool access.

Possibly addressed by:Lazy Tools · Tool Visibility · Tool Visibility

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

Run the complete agent runtime, sessions, tools, plugins, and background work on an SSH host so state survives client disconnects and can be securely resumed with durable event and approval recovery.

Possibly addressed by:Ssh Workspaces · Remote Workspaces · Remote Workspace

The problem

Allow users to organize conversations into user-defined groups, including chats started without a workspace or within a workspace. Request a working directory only when execution requires one.

Possibly addressed by:Plugin No Workspace · Workspace Drag · Just Chat

The problem

Upgrade pi-ai to at least 0.87.1 to expose current OpenCode Go Flash models, including V4.1 Flash, along with current DeepSeek and Mistral support and required session headers. Preserve the streaming-performance patch and improve configuration guidance as needed.

Possibly addressed by:Opencode Go Path · Opencodego · Opencode Go

The problem

Add compressed WebSocket transfer, settlements-first or lazy history loading, and virtualized or paginated rendering for large sessions to reduce transfer time and DOM workload.

Possibly addressed by:Auto Load History · Session Keepwarm · Autoload History

The problem

Provide proactive, configurable compaction with model-visible pressure signals, bounded tool-output spilling, and repeat-call limits. Base it on actual provider limits and ensure deterministic progress with model-free fallbacks when summarization or oversized requests fail.

Possibly addressed by:Smart Compaction · Handoff Compaction · Improved Compact

The problem

Support configurable longer timeouts for large-payload RPCs and model requests, including slow local model loading, generation, retries, and large outputs, while retaining shorter defaults for ordinary calls.