Building
Roadmap
What the project is working on and what is waiting. Items move only when evidence moves them. Owner-only and security-sensitive work is not listed.
No dates are promised. Last updated 22 September 2026. Suggest something
Now 10
Being built, tested, integrated or proven.
-
INTEGRATING Advanced Systems
Merge Advanced Systems into production
The 22 September branches add a revision-bound 3D scene, governed FreeCAD STEP operations, a STEP-to-slicer path, browser grounding across frames and shadow roots, an Obsidian projection, a Failure Atlas and specialist checkpoints. They are integrated on the canonical Advanced branch and not merged into production.
Blocked by
- Most commits after 19:50 UTC on 2026-09-22 are pending primary release and untested
- Live proofs used synthetic fixtures on isolated cores
- No production merge has been authorised
Capabilities
- Spatial engineering workspace (scene)
- Load STEP designs into the spatial scene
- Governed FreeCAD STEP operations (booleans, split, offset, mirror, transform, fillet, faces, face extension, sealed hollow)
- STEP to verified slicing mesh and slicer estimates
- Recorded engineering trade spaces and calculation receipts
- Governed Obsidian projection of project memory
- Failure Atlas (diagnosis history and cross-trajectory patterns)
- Browser DOM scene with frames and shadow roots; stale-target refusal
- Bounded capability discovery over the body interface
Updated
-
TESTING Local model
Local language model: behavioural viability study
A bounded study of stronger local models under a frozen memory and latency envelope. Gemma 4 12B is the current subject: its training-safe endpoint (Gate C) passed on 2026-09-22, and the behavioural evaluation of its 48-update exposure run is pending. Qwen3.5-9B failed the transfer gate. No model is development-qualified.
Blocked by
- Transfer gate (no critical failure and at most 4 failures of 40) not yet met by any candidate
- Pre-registered rule: if fit improves but transfer still fails, do not automatically extend again
Updated
-
TESTING Voice
Speaking voice technical qualification
The owner-selected local voice is integrated on the integration branch and assembled with the conversation loop on 2026-09-18. Its qualification is pending. Long-form non-regression failed, and first audio, streaming, acronym pronunciation, audible cancellation, restart recovery and fallback have not been measured in qualification.
Blocked by
- Long-form non-regression check failed
- Audible first-audio measurement reserved for the owner-present sitting
Updated
-
TESTING Governance
Production reach for the intent ledger
A 2026-09-18 checkpoint found no production code constructing the intent ledger, so multi-step plans containing an irreversible command were safely refused and could never run. Explainable-plans work (A35) targeted the gap. Whether it is fully closed is uncertain.
Blocked by
- Closure not independently verified
Capabilities
Updated
-
BUILDING Local model
New model-visible contract with bounded tool discovery
Replace offering every tool schema with at most two capability-discovery calls, then one action completion, using complete schemas for the selected tools only. A synthetic 'list files' request needed 5,992 input tokens against a 3,072 allowance under Gemma's proven window, and the offer-every-tool fallback needed 35,937.
Blocked by
- Context delivery defect recorded as unresolved
- Depends on a viable model from the behavioural study
Capabilities
Updated
-
BUILDING Advanced Systems
Advanced Systems requirements census and atomic decomposition
Break 417 source requirements into atomic capabilities with exact source quotes and parent-child links. The matrix had 857 rows on 22 September, 1 of them COMPLETE. The completion gate correctly refuses while rows remain undispositioned.
Blocked by
- 414 source lines still awaited decomposition review at the last recorded check
Updated
-
BUILDING Computer operation
Governed typing and filling on the frame-aware browser path
The Advanced Systems DOM scene reads across frames and shadow roots and refuses stale targets, but only for reading. Typing and filling on this path are still pending validation. In production, browser click and fill remain authority-gated by design.
Blocked by
- Mutation validation pending on the branch
- Depends on Advanced Systems integration
Capabilities
Updated
-
BUILDING Computer operation
Installed-application journeys at release scale
Calculator ran ten verified steps on 2026-09-19, and Paint, Notepad and Calculator passed a partial semantic proof. A 78-action workflow across three applications verified every action on the Advanced operator branch, but the requirement is four distinct applications. Full-universe installed-app journeys are owed at release.
Blocked by
- Mixed-application proof covered 3 of the required 4 applications
- Partial UIA traversal is not full application-state coverage
Capabilities
Updated
-
BUILDING HUD
HUD twelve-category fidelity gate
The project's own HUD fidelity gate requires every one of twelve categories above 9.0. The latest recorded mean is 2.43, with a minimum of 1.42, and the scores were recorded against an earlier surface. The gate is not met.
Blocked by
- Scores need re-measuring against the current ONE HUD surface
Updated
-
BUILDING Research and reasoning
Predict-before-act as one layer
Pieces exist separately: calibration records predictions before outcomes, missions can be simulated as SIMULATED / not_proof, and the Advanced operator lane binds experiment predictions to observation receipts. A single layer that records a prediction before every dispatch is still open.
Blocked by
- 'Record prediction before dispatch' is open for integration on the Advanced branch
Capabilities
Updated
Next 8
Committed to, not started.
-
PLANNED Local model
Production training campaigns and the SEALED evaluation
Freeze an immutable production corpus, run at most five full campaigns and stop at the first development-qualified model. Open the 450-item SEALED test set once, for that one frozen checkpoint. None of the five authorised campaigns has been used.
Blocked by
- Behavioural viability (Gates D and E) not yet shown
- New frozen model-visible contract not yet in place
Updated
-
PLANNED Local model
Integrate a qualified local model into the normal provider path
Serve the exact qualified package behind the same provider gateway the hosted model uses, bound to loopback, with the pinned base, revision and adapter digest checked on every streamed chunk and no silent fallback. Hosted cognition stays in production until then.
Blocked by
- No development-qualified model
- SEALED evaluation not yet run
Updated
-
PLANNED Qualification
The owner-present physical sitting
One session at the machine covers what software cannot: an audible reflex first-audio reading, the owner's own voice interrupting a live answer (journey J8), a hand in frame moving a panel (journey J10), and the camera acceptance runbook. J8 and J10 stay FIXTURE_TESTED until then.
Blocked by
- Scheduled after the release-candidate freeze, which waits on a qualified model
Capabilities
Updated
-
PLANNED Qualification
Release-candidate freeze and qualification (Z08.P14)
Freeze an exact candidate and qualify it serially: full suite, mandatory gates, security, mutation, journeys, soak, recovery, backup and restore, restart and shutdown. The release row Z08.P14 has been active since 2026-08-30, final_gate_passed is false, and the certification matrix reads 'JARVIS-READY-V1: NO'.
Blocked by
- No full suite recorded at the current head; the last full run (2026-09-17) had 277 failures and 34 errors before partition
- Tier 1 mutation score 73.5% against the harness's own 90% target
- Waits on the local-model decision
Updated
-
PLANNED HUD
Re-measure the ONE HUD on the final surface
The ONE HUD's own performance acceptance still reads NOT YET MEASURED. Later UI edits invalidated the keyboard walk of 2026-09-18, and fifteen HUD instrument artifacts carry stale source stamps. The project re-measures rather than re-stamps.
Blocked by
- Several instruments need the native shell and thirty-minute soaks
- Must follow the last UI change
Capabilities
Updated
-
PLANNED Missions
Missions that survive a real machine reboot
Missions persist before step one and resume after an application restart without duplicate effects. Surviving a full machine reboot (CAP-MSN-07) is implemented but not proven, and the project will not accept a process kill as a substitute.
Blocked by
- Requires an actual reboot of the owner's machine
Updated
-
PLANNED System health
Live chaos and recovery matrix
Bounded recovery and self-healing are tested, and child-process death and restart storms were read truthfully on /health. The live chaos matrix, which injects failures into a running system and verifies each recovery path, is still owed.
Blocked by
- Link-lost HUD recovery not yet verified live
Capabilities
Updated
-
PLANNED Qualification
Prove JARVIS boots and runs without the build assistant
The last step of the owner's completion order. After promotion to local main, JARVIS must boot and run with the AI build assistant absent, which shows the system does not depend on the tools used to build it.
Blocked by
- Follows release qualification and local-main promotion
Updated
Later 1
Ideas and deliberately postponed work.
-
DEFERRED Fabrication
Physical 3D printing
Print preparation works in software: STEP to verified mesh, slicer estimates and READY / NOT READY / WHY readiness. The physical start needs a fresh single-use approval bound to the G-code hash, a responsible adult present, a clear E-stop and a proven stop path. The final send refuses every caller today, and no evidence shows JARVIS has ever started a print.
Blocked by
- Start gate refuses until a pause has been observed on a real running print
- Requires an owner-present check under existing governance
Capabilities
Updated
What the status words mean
- PLANNED
- Committed to, not started.
- BUILDING
- Being implemented.
- TESTING
- Implemented, under test.
- INTEGRATING
- Tested, being wired into the production path.
- DEFERRED
- Deliberately postponed.