Repository navigation
feat(mcp): add thread history search and reading tools - #2
Merged
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Agents in T3 Code could not discover or read previous conversations through MCP. Add
thread_list,thread_search, andthread_readso an agent can find a discussion, inspect its context, and return threads sorted by title, creation time, or last update.The tools default to the current project, support explicit environment-wide and archived history, and exclude deleted data. Queries paginate in SQL, return bounded snippets, and let agents continue through long messages. Sorting affects results only; these tools do not modify threads. Read-only thread access is available independently of the existing browser and automation toggles. It uses the current provider-scoped MCP credentials across Codex, Claude, Cursor, Grok, and managed OpenCode. Externally managed OpenCode retains its existing MCP configuration.
Validation: 64 focused tests passed, including real SQLite query behavior, MCP registration and request scoping, and provider capability handling. Server and contracts typechecks and targeted lint passed. Independent subagent review caught and resolved repeated turn scans and running commentary being mistaken for a final reply. No client UI changes.
Model: exact model identifier unavailable in the session. Harness: OpenAI Codex with implementation and review subagents.