Prove Your Rebuild Matches the Shipped Binary
A comment-stripped source tree, a byte-reproducible build, and a script that lets a customer check both.
- sessions
- 43
- output tokens
- 942,792
- peak context
- 212,159
- sprints
- 15
Gantry jobs generate detailed logs, which can be used to replay them. On this page a number of such jobs are presented, as screencasts and case studies.
A comment-stripped source tree, a byte-reproducible build, and a script that lets a customer check both.
Default-on build features keep developer builds whole while paid and demo distributions ship without the internal tooling.
Make card detail and finish messages read as prose, without disturbing the tokens inside them
Quick replay clips now scale their length to the size of the run they show.
Measure flakiness with evidence, fix the confirmed offenders by root cause, and guard against their return.
Pin the output height, take the width from the terminal grid
One finish path, a truthful success check, and resume that converges without hand cleanup.
A stop screen that grows to its content, scrolls, and reads the report inline
Try to resolve the merge conflict without a human, and ask only when that fails.
Merge-back that integrates and tests the combined tree before the main branch ever moves.
A collector that archives finished Gantry runs, and an extractor that turns them into normalized datasets.
Making the terminal UI read consistently without disturbing a single machine string
Splitting a run's completion state from the sprint size a person actually scans for.
Capture per-turn context usage as each stage finishes, so a run carries its own numbers
Point Gantry at a check and let it plan, build, and re-plan until that check turns green.
Split the test suite so the everyday gate stops launching the real display stack
Making run identity resolve to the primary checkout no matter where Gantry is invoked
A documentation pass that says test where the words are for people and keeps gate where they name a thing.
Plain plan builds now go straight to the milestone driver, with the startup classifier and its build-family flags removed.
A try-before-you-buy build that checks in, refuses offline when exhausted, and unlocks to unlimited.
A behaviour-preserving rename of Gantry's conversational LLM driver, from brain to assistant, across code and docs.
A hand-editable global file, a first-run picker, and a config command replace the assumed Claude backend.
Replacing the GitHub Actions release pipeline with one local, self-verifying command.
One fresh agent per episode, each writing an anchored script the replay pipeline can film
Put the code and plan text on screen, timed to the voiceover.
Adding one narrated build episode to Gantry's screencast series
A live screencast that drives the real menu, one item at a time, with narration timed to the motion.
A fresh agent reads one past Gantry build and writes its anchored narration essay.
Anchored scripts, aligned narration audio, and a recorder that keeps the voice in step with the replay.
Deterministic source snapshots, license compliance, and signed checksums wired into the release.
Undo only your own changes, lock master while you mutate it, and re-gate the merge so a concurrent run never loses committed work.
Make every build-stage card name the harness and model behind it
Rebuild the missing timelines of old runs from commit times so they replay as first-class timed runs
gantry doctor for a clean machine, plus a path to shipping Gantry as a versioned binary
Grab text out of any pane or error popup with the mouse, and copy it on release
A run classified for milestones but built as one flat sprint no longer announces a structure it never builds.
Give the never-dragged sidebar/feed divider an adaptive layout, and leave a dragged one alone
Turning the monitor's one-line stats glance into a full panel, a commit-activity view, and a pager every drill-down reads through.
Rebuild the sprint sidebar from disk when a run has no event tape
The finish step now checks a resolution actually carried main's changes, and repairs the ones it didn't.
Re-applying dropped layout commits by hand, then pinning them with a test the gate never had.
Rebuilding the terminal front-end around an action registry, a shared file viewer, clipboard copy, and live run statistics.
Turn a live Gantry build into a watchable, unattended screencast
A durable event tape and a replay verb that play a past run back through the live terminal view
Turning a usage-limit wait from a stale corner note into a card that counts down to the resume time.
Classify every already-done unit at once, up front, instead of two slow sequential sweeps.
Codex usage-limit hits become a timed pause and auto-resume, not a dead run
When gantry dies mid-chunk, resume discards the unverified work and rebuilds from the last committed green state.
Turning one oversized file into a directory of per-concern modules, with the test suite as proof nothing moved but the code.
Bank a long run's finished work to master, then resume the rest.
A one-flag compatibility fix that stops a CLI change from halting whole Gantry runs.
When a usage window runs out, sleep until it reopens instead of halting the run.
The conversational assistant reached its run tools only under Claude; this job taught every harness to register them natively.
Joining a fully built but isolated chat backend to the running engine, so a typed message finally gets an answer.
A process-grounded lock makes one engine own a run, and a live transport lets other front-ends attach to watch and steer it.
Teaching a flagless resume to route every driver, not just the layouts it already recognised.
An in-run chat pane and agent backend that turn gantry's dead-stop moments into conversations.
One gate at a time per repository, so overlapping runs stop failing each other
Expose one build's status, artifacts, and controls to an agent — confined to that run
Move conflict resolution into the throwaway worktree so a failed merge never dirties your real tree.
Kill a coding agent for stalling, not for being slow — and keep the work it already finished
Review learns to ask if a sprint covered its brief, and a cut-off agent stream stops meaning failure.
A job type that runs one fresh worker per enumerated item — one at a time, or several at once.
Gantry tells a momentary upstream blip from a real failure and waits it out instead of halting the run.