Roadmap
Where fullsend is going, organized by delivery horizon from the July 28, 2026 planning session:
- Now — August 2026 window (~30 days)
- Next — matters, but not promised this month
- Later — on the horizon
Items are listed in planning order, not priority rank. Tracking spans fullsend-ai/fullsend and fullsend-ai/agents (best-effort). The team also does maintenance and platform work that is not listed here.
Earlier published roadmaps and rotated milestone sections (Foundation, prior monthly done recaps) live in archived-roadmap.md for history only.
Now
| Deliverable | Outcome | Tracking |
|---|---|---|
| PR risk assessment | Risk signal on PRs | fullsend#4698 |
| Basic auto-merge capability | Smallest safe foothold + config | fullsend#2791 · fullsend#3016 |
| Review-fix loop | Less human mechanical iteration | fullsend#5666 · fullsend#5550 · agents#447 · agents#343 · agents#478 |
| Versioned docs | Better docs experience for users | fullsend#5717 · fullsend#5718 |
| Contributor meeting | Broader contributor call | — |
| Agent contribution example | Help users see how to improve fullsend; make it easier to contribute | fullsend#5720 |
| Per-workflow cost visibility | Cost by workflow type | fullsend#5361 · fullsend#5537 |
| Jira poller | Jira events → agents | fullsend#3812 · fullsend#4885 · fullsend#3428 · fullsend#2269 |
| Example custom agent that responds to Jira | BYOA pattern for Jira | fullsend#3812 |
| Triage agent works in response to Jira | Default triage from Jira | fullsend#2264 |
| Make agent status comments configurable | Reduce agent spam on issues for users who don't want it | fullsend#3697 |
| Customer validation | Customer research and validation support | — |
| BYOA API servers | Host-side APIs for sandboxes | fullsend#879 · fullsend#881 · fullsend#5242 · fullsend#5243 |
| Multi-endpoint telemetry / storage | Multi-endpoint telemetry and storage | fullsend#5545 · fullsend#5533 · fullsend#294 |
| GitLab MVP | Usable GitLab path | fullsend#1964 · fullsend#5556 |
| Remove per-org install | Unified install | fullsend#2302 · fullsend#2887 · fullsend#5197 |
| Public mint | Finish and operate public mint | fullsend#5116 · fullsend#5115 · fullsend#5634 |
| Roll out repos management | Repos + mint operable | fullsend#181 |
| Doc use cases and practices | Copyable practices | fullsend#419 · fullsend#5372 |
| Shared configs | Ready-made / shareable presets | fullsend#4910 · fullsend#4914 |
Next
| Deliverable | Outcome | Tracking |
|---|---|---|
| Code agent works in response to Jira | Code agent from Jira | fullsend#2265 |
| Multi-agent stages with their own sandboxes | Per-stage isolation (ADR-first) | fullsend#3978 |
| Scheduled custom agents | Cron / scheduled runs | fullsend#313 · agents#442 |
| Eval scenarios | Concrete eval measurements | agents#209 · agents#180 |
| Increase SIT / reduce functional tests | More behaviour/SIT; less overlapping functional | fullsend#3236 · fullsend#3786 |
| Multi-target repo for PR creation | PRs across more than one target repo | fullsend#298 · fullsend#1276 |
| Propose OpenShell to use fullsend | Partnership, not a chore | — |
| GPG-signed commits from code and fix | Signed commits (e.g. Ansible) | fullsend#5165 · agents#357 · agents#318 |
| Working OpenCode implementation | OpenCode as a runtime | fullsend#1260 |
| Pi runtime pilot | Second production runtime; Bedrock/Azure access | fullsend#6464 |
| Persistent agent memories | Traceable only; no hidden memory | — |
| Cross-forge orchestration | GitHub + GitLab / multi-org | — |
Later
| Deliverable | Outcome | Tracking |
|---|---|---|
| Kubernetes and OpenShift execution | Forge-decoupled agent runtime | — |
| Security hardening | Prompt injection, credentials, threat model | fullsend#172 · fullsend#174 · fullsend#84 · fullsend#159 · fullsend#877 · fullsend#2826 · fullsend#2828 |
| Human factors and governance | Ownership, review fatigue, contributor motivation | human-factors · governance |
| Production feedback loops | Prod signals → triage / prioritization | production-feedback |
| Agent attestations | Cryptographic provenance for agent output | fullsend#267 |
July 2026 (done)
July focused on adoption: public mint and Cloudflare deploy paths, forge-aware repo management, layered config, BYOA/CEL docs, and GitLab polling foundations — plus agent-side review/eval/docs work in fullsend-ai/agents.
Links use /issues/N (GitHub serves merged PRs there too) so previews don’t try to load a PR diff.
- Cloudflare / public mint — Worker mint path, WASM host bridge, and deploy platform mode (fullsend#5427, fullsend#5447, fullsend#5615); mint privilege ADRs (fullsend#5328)
- Repos management — forge-aware
repos, mixed-forge manifests, upgrade mint checks, docs (fullsend#5617, fullsend#5623, fullsend#5643, fullsend#5600, fullsend#5602) - Layered configuration —
config.base.yaml+ parent fallback; merge semantics docs (fullsend#5652, fullsend#5625, fullsend#5651) - BYOA / harness — agent files out of scaffold embed; CEL trigger guidance (fullsend#5588, fullsend#5532, fullsend#5404)
- GitLab polling — client polling + cron-polling event router (fullsend#5391)
- Telemetry — OTEL env forwarding to managed agents (fullsend#5531)
- Security docs —
SECURITY.md; destructive forge ops guidance (fullsend#5635, fullsend#5587) - Behaviour testing — forge constraints docs; URL harness scenarios; pool/cleanup (fullsend#5546, fullsend#5407, fullsend#5444)
- Agents: review / fix loop — scoped re-review dispatch; two-pass large-PR review (agents#355, agents#190)
- Agents: evals — fix-agent
/fs-fixfunctional eval (agents#381) - Agents: triage — in-progress action; skip code agent on workflow-file-only changes (agents#434, agents#326)