docs: self-service upgrade message + gated cross-version test (on-demand)

The storage-format refusal now names the release line that wrote each
internal-schema stamp (e.g. v3 -> 0.6.2-0.7.2) plus the exact
export/init/load commands — fail-closed but self-service; the message is
engine-shared so server boot-quarantine and cluster status get it free.

Adds the OMNIGRAPH_OLD_BIN-gated cross-version test: mint a GENUINE v3
graph with a real omnigraph-cli 0.7.2 binary, assert the current binary
refuses it with the release-named message, and the documented rebuild
round-trips. Deliberately NOT wired into CI (the write_cost_s3
disposition): compiling 0.7.2 from source is a 15-25 min job and the
stamp seam changes a few times a year — testing.md documents the
on-demand invocation instead.

Rebased onto current main across the Lance 9.0.0-beta.15 migration;
validated locally against a genuine 0.7.2 binary — the v3 round-trip
passes on the Lance-9 main, which also makes it a live cross-substrate
read-compat check (a Lance-9 binary reading a Lance-7-written manifest
to find the stamp).
This commit is contained in:
Ragnor Comerford 2026-07-06 04:14:27 +03:00 committed by Andrew Altshuler
parent 50db10f65c
commit ca2ad974e1
9 changed files with 1501 additions and 11 deletions

View file

@ -0,0 +1,155 @@
//! Cross-version upgrade: prove the CURRENT binary handles a GENUINE old-format
//! (internal schema v3) graph minted by omnigraph 0.7.2 — not a v4-shaped graph
//! with a rewound stamp. Two things the stamp-rewind stand-in
//! (`sub_current_graph_is_refused_then_rebuilt_via_export_import`) cannot prove:
//!
//! 1. the open-refusal fires on the REAL on-disk v3 shape (lineage in
//! `_graph_commits.lance`, lineage-free `__manifest`) and NAMES the writing
//! release, and
//! 2. the documented `export → init → load` rebuild round-trips the data,
//! including a `Vector` column, off a genuine v3 export.
//!
//! Gated: requires `OMNIGRAPH_OLD_BIN` (an absolute path to a 0.7.2 `omnigraph`
//! binary). Skips gracefully when unset — the same convention as the S3 and
//! system-e2e gates — so the default `cargo test --workspace` stays green
//! without it. CI sets it in the `crossversion_upgrade` job (see
//! `docs/dev/testing.md`).
mod support;
use std::path::{Path, PathBuf};
use std::process::Command;
use support::{HERMETIC_OPERATOR_HOME, cli, fixture, output_failure, output_success};
use tempfile::tempdir;
/// Resolve the old (0.7.2) binary. `None` ONLY when `OMNIGRAPH_OLD_BIN` is
/// unset — the legitimate skip. A var that is SET but points at a missing path
/// is a misconfiguration (wrong install path / renamed binary) and must fail
/// loudly, never skip vacuously: in CI the var is deliberately set so the test
/// is expected to run.
fn old_bin() -> Option<PathBuf> {
let path = PathBuf::from(std::env::var_os("OMNIGRAPH_OLD_BIN")?);
assert!(
path.exists(),
"OMNIGRAPH_OLD_BIN is set but does not exist: {} \
(unset it to skip, or point it at a real 0.7.2 omnigraph binary)",
path.display(),
);
Some(path)
}
/// Run the OLD (0.7.2) binary hermetically (no developer `~/.omnigraph`).
fn run_old(bin: &Path, args: &[&str]) -> std::process::Output {
Command::new(bin)
.env("OMNIGRAPH_HOME", HERMETIC_OPERATOR_HOME)
.env_remove("OMNIGRAPH_CONFIG")
.args(args)
.output()
.expect("spawn old omnigraph binary")
}
fn assert_ok(label: &str, out: &std::process::Output) {
assert!(
out.status.success(),
"old binary `{label}` failed\nstdout:\n{}\nstderr:\n{}",
String::from_utf8_lossy(&out.stdout),
String::from_utf8_lossy(&out.stderr),
);
}
fn nonblank_lines(bytes: &[u8]) -> usize {
String::from_utf8_lossy(bytes)
.lines()
.filter(|l| !l.trim().is_empty())
.count()
}
#[test]
fn current_binary_refuses_and_rebuilds_a_genuine_v3_graph() {
let Some(old) = old_bin() else {
eprintln!(
"skipping cross-version upgrade test: OMNIGRAPH_OLD_BIN is not set to a 0.7.2 binary"
);
return;
};
let temp = tempdir().unwrap();
let old_graph = temp.path().join("old-v3.omni");
// `search.pg` / `search.jsonl` are byte-identical in v0.7.2 and exercise a
// `Vector(4)` column plus indexed strings — a fixture both binaries parse.
let schema = fixture("search.pg");
let data = fixture("search.jsonl");
let og = old_graph.to_str().unwrap();
// 1. Mint a GENUINE v3 graph with the old binary.
assert_ok(
"init",
&run_old(&old, &["init", "--schema", schema.to_str().unwrap(), og]),
);
assert_ok(
"load",
&run_old(
&old,
&["load", "--mode", "overwrite", "--data", data.to_str().unwrap(), og],
),
);
// Prove it is really v3 on disk: pre-v4 graphs carry the now-retired
// `_graph_commits.lance` lineage dataset (a v4 graph has neither).
assert!(
old_graph.join("_graph_commits.lance").exists(),
"a genuine v3 graph must have the legacy _graph_commits.lance dataset",
);
// 2. Old binary export → JSONL.
let export = run_old(&old, &["export", og]);
assert_ok("export", &export);
assert!(!export.stdout.is_empty(), "old export produced no rows");
let v3_jsonl = temp.path().join("v3.jsonl");
std::fs::write(&v3_jsonl, &export.stdout).unwrap();
// 3. The CURRENT binary refuses the genuine v3 graph, names the writing
// release, and nudges to export — on the real on-disk shape.
let refusal = output_failure(cli().arg("snapshot").arg(&old_graph));
let stderr = String::from_utf8_lossy(&refusal.stderr);
assert!(
stderr.contains("export"),
"refusal must nudge the operator to export, got: {stderr}",
);
assert!(
stderr.contains("0.6.2 to 0.7.2"),
"refusal must name the full release range that wrote this stamp (v3 → 0.6.2 to 0.7.2), \
got: {stderr}",
);
// 4. The CURRENT binary rebuilds: fresh init + load the v3 export.
let new_graph = temp.path().join("new-v4.omni");
output_success(cli().arg("init").arg("--schema").arg(&schema).arg(&new_graph));
output_success(
cli()
.arg("load")
.arg("--mode")
.arg("overwrite")
.arg("--data")
.arg(&v3_jsonl)
.arg(&new_graph),
);
// 5. Round-trip fidelity: re-export with the current binary and compare.
let reexport = output_success(cli().arg("export").arg(&new_graph));
assert_eq!(
nonblank_lines(&export.stdout),
nonblank_lines(&reexport.stdout),
"row count must round-trip v3 → v4",
);
let rebuilt = String::from_utf8_lossy(&reexport.stdout);
assert!(
rebuilt.contains("embedding"),
"the Vector column must survive the rebuild, got: {rebuilt}",
);
assert!(
rebuilt.contains("ml-intro"),
"the rebuilt graph must preserve node data, got: {rebuilt}",
);
}

View file

@ -70,6 +70,26 @@ pub(crate) const INTERNAL_MANIFEST_SCHEMA_VERSION: u32 = 4;
/// module doc).
pub(crate) const MIN_SUPPORTED_INTERNAL_SCHEMA_VERSION: u32 = INTERNAL_MANIFEST_SCHEMA_VERSION;
/// The omnigraph release line that wrote a given internal-schema stamp. The
/// open-refusal uses it to tell an operator exactly which binary to use to
/// export a sub-CURRENT graph (the export side of the strand-model upgrade —
/// see `docs/user/operations/upgrade.md`). Ranges are the release tags that
/// stamped each version (verify with
/// `git show vX.Y.Z:crates/omnigraph/src/db/manifest/migrations.rs`):
/// v1 ≤ 0.3.1, v2 0.4.10.6.1, v3 0.6.20.7.2, v4 0.8.x.
pub(crate) fn release_for_internal_schema_version(stamp: u32) -> &'static str {
match stamp {
1 => "0.3.1 or earlier",
2 => "0.4.1 to 0.6.1",
3 => "0.6.2 to 0.7.2",
4 => "0.8.x",
// Unreachable today (13 are mapped; ≥ CURRENT is caught by the ceiling
// guard before this is consulted). Worded to read naturally after
// "created by omnigraph " if a future bump ever leaves a gap.
_ => "an unrecognized older release",
}
}
const INTERNAL_SCHEMA_VERSION_KEY: &str = "omnigraph:internal_schema_version";
/// Read the on-disk stamp from `__manifest`'s schema-level metadata.
@ -109,10 +129,14 @@ pub(crate) fn refuse_if_stamp_unsupported(stamp: u32) -> Result<()> {
if stamp < MIN_SUPPORTED_INTERNAL_SCHEMA_VERSION {
return Err(OmniError::manifest(format!(
"__manifest is stamped at internal schema v{stamp}, but this omnigraph reads only v{current}. \
This graph was created by an older omnigraph release; rebuild it: run `omnigraph export` with \
the older omnigraph binary that created it, then `omnigraph init` + `omnigraph load` with this one. \
(Data, vectors, and blobs are preserved; commit history and branches are not.)",
This graph was created by omnigraph {release}. Rebuild it: with an omnigraph {release} binary run \
`omnigraph export <graph> > graph.jsonl`, then with this binary run \
`omnigraph init --schema <schema.pg> <new-graph>` and \
`omnigraph load --mode overwrite --data graph.jsonl <new-graph>`. \
(Data, vectors, and blobs are preserved; commit history and branches are not.) \
See docs/user/operations/upgrade.md.",
current = INTERNAL_MANIFEST_SCHEMA_VERSION,
release = release_for_internal_schema_version(stamp),
)));
}
Ok(())
@ -160,4 +184,21 @@ mod tests {
"a future stamp must be refused"
);
}
/// The refusal names the release line that wrote each stamp so an operator
/// knows which binary to use for the export step; unknown stamps fall back
/// without panicking.
#[test]
fn release_names_the_writing_line_for_each_stamp() {
assert_eq!(release_for_internal_schema_version(3), "0.6.2 to 0.7.2");
assert_eq!(release_for_internal_schema_version(4), "0.8.x");
assert_eq!(
release_for_internal_schema_version(99),
"an unrecognized older release"
);
// The sub-CURRENT refusal embeds the named release.
let err = refuse_if_stamp_unsupported(3).unwrap_err().to_string();
assert!(err.contains("0.6.2 to 0.7.2"), "got: {err}");
assert!(err.contains("omnigraph export"), "got: {err}");
}
}

View file

@ -1826,10 +1826,16 @@ async fn sub_current_graph_is_refused_then_rebuilt_via_export_import() {
Ok(_) => panic!("a sub-CURRENT graph must be refused on open"),
Err(err) => err,
};
let msg = err.to_string();
assert!(
err.to_string().contains("export"),
msg.contains("export"),
"the refusal must nudge the operator to `omnigraph export`, got: {err}",
);
assert!(
msg.contains("0.7.2"),
"the refusal must name the release that wrote this stamp (v3 → 0.6.2 to 0.7.2) so the \
operator knows which binary to use, got: {err}",
);
// Rebuild with this binary: fresh init + load the export.
let dir_new = tempfile::tempdir().unwrap();