v1.7.0
supermemoryai/supermemoryv1.7.0Oct 5, 2026by github-actions[bot]
Upgrading?
AI Summary
This release focuses on performance optimizations, UI/UX enhancements, and new budget management features. It introduces a `--fail-on` CLI flag for severity-based exit codes and a budget policy to pause agents at cost limits. The user interface received significant updates, including collapsible sidebar panels and markdown rendering for report sections.
Key Highlights
- New `--fail-on` CLI flag to gate headless exit codes on severity.
- Budget policy feature (`budget_policy=pause`) to park agents at cost limits.
- UI improvements including collapsible sidebar panels and animated wait indicators.
- Agent refactoring to remove user prompts in favor of a text-free interaction model.
- Enhanced LLM caching and structured provider request logging.
New Features
- New `--fail-on` CLI flag
- Budget policy pausing
- Collapsible sidebar panels
- Markdown report rendering
- Lazy MCP initialization
- Interactive resume picker
Full Release Notes
## What's Changed * fix(models): frontier model check matches the model name only, never the provider route by @0xallam in https://github.com/usestrix/strix/pull/1280 * feat(reporting): link HTTP exchange evidence by @bearsyankees in https://github.com/usestrix/strix/pull/1281 * feat(prompts): require http_exchange_ids for proxy-validated findings by @0xallam in https://github.com/usestrix/strix/pull/1292 * docs: add Vercel AI Gateway provider guide by @erulkey in https://github.com/usestrix/strix/pull/1254 * fix(web_search): send only the agent's query to Exa search by @0xallam in https://github.com/usestrix/strix/pull/1306 * chore(deps): require litellm>=1.101.0 so gpt-6-astra accepts max_tokens by @0xallam in https://github.com/usestrix/strix/pull/1318 * feat(config): STRIX_API_TYPE forces responses vs chat completions by @bearsyankees in https://github.com/usestrix/strix/pull/1324 * fix(build): keep the TUI sidecar hook importable on hatchling 1.32.1 by @bearsyankees in https://github.com/usestrix/strix/pull/1325 * fix(runtime): place extra files as agent-writable sandbox files on every backend by @0xallam in https://github.com/usestrix/strix/pull/1330 * Prompt agents to include local Git blame in technical details by @bearsyankees in https://github.com/usestrix/strix/pull/1329 * fix(reporting): reduce git blame guidance to a trailing hint on the reporting tool by @0xallam in https://github.com/usestrix/strix/pull/1336 * runtime: read_only local sources become :ro bind mounts by @0xallam in https://github.com/usestrix/strix/pull/1342 * feat(mcp): initialize connections lazily by @yoni-at-strix in https://github.com/usestrix/strix/pull/1347 * feat(llm): structured per-attempt provider request log with provider request ids by @0xallam in https://github.com/usestrix/strix/pull/1353 * Let agents delete a vulnerability report they filed by @bearsyankees in https://github.com/usestrix/strix/pull/1354 * Fill in blank tool-call ids so strict providers accept the history by @0xallam in https://github.com/usestrix/strix/pull/1355 * fix(dev): make check-all non-mutating by @Czech-Knight in https://github.com/usestrix/strix/pull/1360 * fix(tui): suspend on ctrl+z by @ian-at-strix in https://github.com/usestrix/strix/pull/1371 * docs(skills): refresh framework behavior and security testing guidance by @bearsyankees in https://github.com/usestrix/strix/pull/1372 * perf(prompt): put per-run scope at the end of the system prompt by @ian-at-strix in https://github.com/usestrix/strix/pull/1375 * perf(llm): give Claude a cache point before the per-run scope by @ian-at-strix in https://github.com/usestrix/strix/pull/1376 * perf(prompt): load requested skills after a cache point by @ian-at-strix in https://github.com/usestrix/strix/pull/1382 * feat(tui): animate the wait_for_agents indicator by @ian-at-strix in https://github.com/usestrix/strix/pull/1383 * feat(budget): budget_policy=pause — park every agent at the cost limit until the operator resumes by @0xallam in https://github.com/usestrix/strix/pull/1387 * perf(llm): pin OpenRouter agents to one provider with session IDs by @ian-at-strix in https://github.com/usestrix/strix/pull/1386 * chore(models): remove the model quality warning and its allowlists by @0xallam in https://github.com/usestrix/strix/pull/1388 * fix(reporting): restore create_vulnerability_report parameter descrip… by @bearsyankees in https://github.com/usestrix/strix/pull/1391 * fix(config): choose Responses vs chat completions from the model, not the base URL by @0xallam in https://github.com/usestrix/strix/pull/1407 * fix(config): use the Responses API whenever the model supports it by @0xallam in https://github.com/usestrix/strix/pull/1408 * fix(finish_scan): stop asking for a section heading in every report field by @0xallam in https://github.com/usestrix/strix/pull/1411 * fix(tui): link every wrapped line of the viewer URL to the full URL by @0xallam in https://github.com/usestrix/strix/pull/1412 * feat(cli): Add --fail-on to gate headless exit code on severity by @siundu254 in https://github.com/usestrix/strix/pull/1399 * fix(cli): force UTF-8 stdout/stderr on Windows so Rich output never raises by @0xallam in https://github.com/usestrix/strix/pull/1414 * fix(preflight): name a non-ASCII character in the API key instead of raising UnicodeEncodeError by @0xallam in https://github.com/usestrix/strix/pull/1415 * fix(tui): render report section bodies as markdown by @0xallam in https://github.com/usestrix/strix/pull/1416 * fix(tui): collapsible, zoomable sidebar panels and a sidebar toggle by @0xallam in https://github.com/usestrix/strix/pull/1417 * fix(cli): verify the model before the TUI opens on a direct launch by @0xallam in https://github.com/usestrix/strix/pull/1418 * fix(telemetry): keep "Exception ignored" finalizer tracebacks off the terminal by @0xallam in https://github.com/usestrix/strix/pull/1419 * feat(cli): pick a prior run interactively when --resume has no name by @0xallam in https://github.com/usestrix/strix/pull/1421 * test(pricing): accept any identically priced provider for bare grok-4.5 by @0xallam in https://github.com/usestrix/strix/pull/1423 * fix(resume-picker): treat ctrl+c as cancel instead of leaking a KeyboardInterrupt traceback by @0xallam in https://github.com/usestrix/strix/pull/1424 * ci: run ruff, mypy, bandit, pytest, Go TUI and viewer checks on every pull request by @0xallam in https://github.com/usestrix/strix/pull/1422 * fix(deps): ship google-auth with every install so Vertex AI works in release binaries by @0xallam in https://github.com/usestrix/strix/pull/1437 * fix(preflight): give the startup model check its own 30s timeout instead of LLM_TIMEOUT by @0xallam in https://github.com/usestrix/strix/pull/1438 * fix(cli): run headless when no terminal is attached instead of crashing the TUI by @0xallam in https://github.com/usestrix/strix/pull/1440 * fix(docker): connect like the docker CLI and explain why the daemon is unreachable by @0xallam in https://github.com/usestrix/strix/pull/1441 * refactor(agents): replace respond_to_user with a text-free wait_for_user by @0xallam in https://github.com/usestrix/strix/pull/1442 * prompts: let the verified user define and change scope in chat by @0xallam in https://github.com/usestrix/strix/pull/1443 * readme: remove the Ask DeepWiki badge by @0xallam in https://github.com/usestrix/strix/pull/1444 * chore: release v1.7.0 by @0xallam in https://github.com/usestrix/strix/pull/1445 ## New Contributors * @erulkey made their first contribution in https://github.com/usestrix/strix/pull/1254 * @Czech-Knight made their first contribution in https://github.com/usestrix/strix/pull/1360 * @ian-at-strix made their first contribution in https://github.com/usestrix/strix/pull/1371 * @siundu254 made their first contribution in https://github.com/usestrix/strix/pull/1399 **Full Changelog**: https://github.com/usestrix/strix/compare/v1.6.2...v1.7.0
Related Repositories
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
Reverse engineer anything with agents, from app behavior down to native binaries.
The open source coding agent.
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.