client-core: port TranscriptSource and joinPages page-boundary healing
Closes docs/RUST.md's "client-core prerequisites for P1" box: the cache-vs-server stitching TranscriptSource.kt does, and the joinPages/healSplitMessage/adoptRun page-boundary healing TranscriptItems.kt does, both ported into client-core with no UI framework dependency. Neither Kotlin file had a JVM unit test of its own, so the port used the Kotlin source and AGENTS.md's "things that have bitten" paging incidents as the spec instead of a test-for-test transcription. Both regressions get a dedicated test: TranscriptSource::page refuses before == 0 before touching the cache or the network (loadOlderPage's incident), and adopt_run now runs on every page join rather than only the one where a split call was found (the "one run drawn as two" incident). fetch_transcript_lines (api.rs, additive) pairs each transcript line with the exact server bytes via serde_json::value::RawValue rather than re-serializing a parsed Value, so a cached line and a live SSE frame for the same event agree byte-for-byte -- the fetch_transcript_page other callers under iris/ depend on is untouched. client-core: 85 -> 109 tests. cargo test/clippy --all-targets/fmt clean. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
irisandClaude Fable 5.1 committed
1 parent
9717d1c4b0
commit
73251d6b8b
7 files changed
+995
-32
No files matched your search
@@ -17,7 +17,12 @@ edition = "2024"
|
||||
[dependencies]
|
||||
event-model = { path = "../event-model" }
|
||||
serde = { version = "1", features = ["derive"] }
|
||||
serde_json = { version = "1", features = ["float_roundtrip"] }
|
||||
# "raw_value" is `fetch_transcript_lines`'s reason -- it needs the exact
|
||||
# bytes the server sent, not this crate's own re-serialization of a parsed
|
||||
# `Value`, so a cached line and a live SSE frame for the same event agree
|
||||
# byte-for-byte (see that method's doc). "float_roundtrip" is why they
|
||||
# agree on a `ts` at all -- see server/Cargo.toml's identical comment.
|
||||
serde_json = { version = "1", features = ["float_roundtrip", "raw_value"] }
|
||||
# The blocking HTTP client for the REST calls and the long-lived SSE GETs.
|
||||
# `server/` already depends on ureq for its own outbound HTTPS (the usage
|
||||
# poll in usage.rs) and it is rustls-backed like the rest of this project's
|
||||
|
||||
+74
-8
@@ -10,6 +10,7 @@
|
||||
|
||||
use std::io::Read;
|
||||
|
||||
use event_model::SeqEvent;
|
||||
use serde::Deserialize;
|
||||
use serde_json::Value;
|
||||
|
||||
@@ -116,6 +117,14 @@ impl<T: Transport> ApiClient<T> {
|
||||
Self { transport }
|
||||
}
|
||||
|
||||
/// The transport underneath, for a caller that needs the raw SSE
|
||||
/// stream (`event_stream::follow_session_events`) rather than one of
|
||||
/// this client's typed REST calls -- `transcript_source::TranscriptSource`
|
||||
/// is the one that does.
|
||||
pub fn transport(&self) -> &T {
|
||||
&self.transport
|
||||
}
|
||||
|
||||
fn json_request<R: for<'de> Deserialize<'de>>(
|
||||
&self,
|
||||
method: &str,
|
||||
@@ -266,15 +275,72 @@ impl<T: Transport> ApiClient<T> {
|
||||
limit: u32,
|
||||
coalesce: bool,
|
||||
) -> Result<Vec<Value>, ApiError> {
|
||||
let mut path = format!("/sessions/{session_id}/transcript?limit={limit}");
|
||||
if let Some(before) = before {
|
||||
path.push_str(&format!("&before={before}"));
|
||||
}
|
||||
if coalesce {
|
||||
path.push_str("&coalesce=true");
|
||||
}
|
||||
self.json_request("GET", &path, None)
|
||||
self.json_request(
|
||||
"GET",
|
||||
&transcript_path(session_id, before, limit, coalesce, None),
|
||||
None,
|
||||
)
|
||||
}
|
||||
|
||||
/// A page of transcript history, each line handed back paired with the
|
||||
/// exact text it came from, and bounded below by `after` -- the shape
|
||||
/// `crate::transcript_source::TranscriptSource` needs to store what it
|
||||
/// fetched in the transcript cache without a second round trip to fetch
|
||||
/// the raw text separately. Ported from `Api.kt`'s `fetchTranscript`.
|
||||
///
|
||||
/// Uses [`serde_json::value::RawValue`] rather than re-serializing a
|
||||
/// parsed [`Value`], so the stored line is the exact bytes the server
|
||||
/// sent (key order and float literal included) rather than this
|
||||
/// crate's own idea of how to write them back out -- the cache and a
|
||||
/// live SSE frame must agree byte-for-byte on the same event, which is
|
||||
/// exactly what caught the `serde_json` float-rounding bug this
|
||||
/// project's `AGENTS.md` records.
|
||||
pub fn fetch_transcript_lines(
|
||||
&self,
|
||||
session_id: &str,
|
||||
before: Option<u64>,
|
||||
limit: u32,
|
||||
coalesce: bool,
|
||||
after: Option<u64>,
|
||||
) -> Result<Vec<(String, SeqEvent)>, ApiError> {
|
||||
let path = transcript_path(session_id, before, limit, coalesce, after);
|
||||
let raw: Vec<Box<serde_json::value::RawValue>> = self.json_request("GET", &path, None)?;
|
||||
raw.into_iter()
|
||||
.map(|value| {
|
||||
let line = value.get().to_string();
|
||||
let event: SeqEvent = serde_json::from_str(&line).map_err(|e| ApiError {
|
||||
message: format!(
|
||||
"the server sent a transcript line this build couldn't parse: {e}"
|
||||
),
|
||||
status: None,
|
||||
})?;
|
||||
Ok((line, event))
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
}
|
||||
|
||||
/// The query string shared by [`ApiClient::fetch_transcript_page`] and
|
||||
/// [`ApiClient::fetch_transcript_lines`], so the two agree on how each
|
||||
/// parameter is written rather than keeping two copies to drift.
|
||||
fn transcript_path(
|
||||
session_id: &str,
|
||||
before: Option<u64>,
|
||||
limit: u32,
|
||||
coalesce: bool,
|
||||
after: Option<u64>,
|
||||
) -> String {
|
||||
let mut path = format!("/sessions/{session_id}/transcript?limit={limit}");
|
||||
if let Some(before) = before {
|
||||
path.push_str(&format!("&before={before}"));
|
||||
}
|
||||
if coalesce {
|
||||
path.push_str("&coalesce=true");
|
||||
}
|
||||
if let Some(after) = after {
|
||||
path.push_str(&format!("&after={after}"));
|
||||
}
|
||||
path
|
||||
}
|
||||
|
||||
/// The blocking [`Transport`] backed by `ureq`, the same crate `server/`
|
||||
|
||||
@@ -11,5 +11,6 @@ pub mod notifications;
|
||||
pub mod sse;
|
||||
pub mod transcript_cache;
|
||||
pub mod transcript_fold;
|
||||
pub mod transcript_source;
|
||||
|
||||
pub use event_model::*;
|
||||
@@ -294,6 +294,191 @@ fn split_run(tail: &[TranscriptItem], behind: Option<&str>) -> Vec<TranscriptIte
|
||||
out
|
||||
}
|
||||
|
||||
/// Puts a page of older items in front of the ones already loaded, healing
|
||||
/// whatever the page boundary cut in two. Ported from `TranscriptItems.kt`'s
|
||||
/// `joinPages`.
|
||||
///
|
||||
/// Two things straddle a boundary: a tool call separated from its result,
|
||||
/// and a message separated from the rest of itself. Both were one thing
|
||||
/// before the transcript was cut into pages.
|
||||
///
|
||||
/// A boundary lands wherever it lands, and roughly half the time that is
|
||||
/// between a call and its result. The newer page then holds a `ToolEnd`
|
||||
/// whose start it never saw, which `fold_event` draws as a row of its own
|
||||
/// -- correctly, because a call that renders as nothing is indistinguishable
|
||||
/// from one that never happened. When the older page arrives it brings the
|
||||
/// real `ToolStart`, and concatenating the two lists left *both*: the same
|
||||
/// call twice.
|
||||
///
|
||||
/// Merged by the call's own id rather than by position, because position is
|
||||
/// exactly what a page boundary destroys. The older row wins on what a
|
||||
/// start knows and the newer on what an end knows, which is the only way
|
||||
/// round that loses nothing.
|
||||
///
|
||||
/// The third thing is the *run*, and it is the one the Kotlin original used
|
||||
/// to miss (AGENTS.md's "things that have bitten"): every page ends up
|
||||
/// here, but `adopt_run` must run on *every* join, not only the one where a
|
||||
/// split call was found -- a boundary landing cleanly between two finished
|
||||
/// calls, which is most of them, would otherwise leave the older page's
|
||||
/// calls under the run name they were folded with. On screen: one run of
|
||||
/// tool calls drawn as two groups, with the seam wherever the reader
|
||||
/// happened to have paged.
|
||||
pub fn join_pages(earlier: &[TranscriptItem], later: &[TranscriptItem]) -> Vec<TranscriptItem> {
|
||||
let (older, newer) = heal_split_message(earlier, later);
|
||||
let started_earlier: std::collections::HashSet<&str> = older
|
||||
.iter()
|
||||
.filter_map(TranscriptItem::as_tool_run)
|
||||
.collect();
|
||||
// Owned rather than borrowed from `newer`: `kept` below needs to consume `newer` by
|
||||
// value, and a map borrowing it would keep that alive.
|
||||
let ended_later: std::collections::HashMap<String, TranscriptItem> = newer
|
||||
.iter()
|
||||
.filter_map(|item| item.as_tool_run().map(|id| (id.to_string(), item.clone())))
|
||||
.filter(|(id, _)| started_earlier.contains(id.as_str()))
|
||||
.collect();
|
||||
let healed: Vec<TranscriptItem> = older
|
||||
.into_iter()
|
||||
.map(|row| match row {
|
||||
TranscriptItem::ToolRun {
|
||||
seq,
|
||||
id,
|
||||
run_id,
|
||||
tool,
|
||||
input,
|
||||
asks: row_asks,
|
||||
images: row_images,
|
||||
..
|
||||
} if ended_later.contains_key(id.as_str()) => {
|
||||
let &TranscriptItem::ToolRun {
|
||||
ref output,
|
||||
done,
|
||||
asks: ref half_asks,
|
||||
images: ref half_images,
|
||||
..
|
||||
} = &ended_later[id.as_str()]
|
||||
else {
|
||||
unreachable!("filtered to ToolRun above");
|
||||
};
|
||||
TranscriptItem::ToolRun {
|
||||
seq,
|
||||
id,
|
||||
run_id,
|
||||
tool,
|
||||
input,
|
||||
output: output.clone(),
|
||||
done,
|
||||
// Kept from both halves: a question or an image can be
|
||||
// attached to either, depending on which side of the
|
||||
// boundary its event fell.
|
||||
asks: row_asks.into_iter().chain(half_asks.clone()).collect(),
|
||||
images: row_images.into_iter().chain(half_images.clone()).collect(),
|
||||
}
|
||||
}
|
||||
other => other,
|
||||
})
|
||||
.collect();
|
||||
let kept: Vec<TranscriptItem> = newer
|
||||
.into_iter()
|
||||
.filter(|item| match item.as_tool_run() {
|
||||
Some(id) => !ended_later.contains_key(id),
|
||||
None => true,
|
||||
})
|
||||
.collect();
|
||||
debug_assert!(
|
||||
match (healed.last(), kept.first()) {
|
||||
(Some(last), Some(first)) => last.seq() <= first.seq(),
|
||||
_ => true,
|
||||
},
|
||||
"a joined page must stay ordered by seq at the boundary"
|
||||
);
|
||||
let mut out = adopt_run(&healed, &kept);
|
||||
out.extend(kept);
|
||||
out
|
||||
}
|
||||
|
||||
/// Rejoins a message the page boundary cut, and hands back the two pages to
|
||||
/// concatenate. Ported from `TranscriptItems.kt`'s `healSplitMessage`.
|
||||
///
|
||||
/// `fold_event` never leaves two assistant messages next to each other
|
||||
/// inside one page, so two meeting at a join are always the two halves of
|
||||
/// one reply, and leaving them apart drew a single answer as two with a
|
||||
/// paragraph break through the middle of a sentence.
|
||||
///
|
||||
/// The newer half keeps its identity, for the reason `adopt_run`'s doc
|
||||
/// gives. It grows by what the older half brings, which is safe here and
|
||||
/// nowhere else -- the join is at the oldest end of what is loaded, so the
|
||||
/// growth extends off the top of the screen.
|
||||
fn heal_split_message(
|
||||
earlier: &[TranscriptItem],
|
||||
later: &[TranscriptItem],
|
||||
) -> (Vec<TranscriptItem>, Vec<TranscriptItem>) {
|
||||
let (
|
||||
Some(TranscriptItem::AssistantMsg {
|
||||
text: head_text, ..
|
||||
}),
|
||||
Some(TranscriptItem::AssistantMsg {
|
||||
seq: tail_seq,
|
||||
text: tail_text,
|
||||
settled: tail_settled,
|
||||
}),
|
||||
) = (earlier.last(), later.first())
|
||||
else {
|
||||
return (earlier.to_vec(), later.to_vec());
|
||||
};
|
||||
let merged = TranscriptItem::AssistantMsg {
|
||||
seq: *tail_seq,
|
||||
text: format!("{head_text}{tail_text}"),
|
||||
settled: *tail_settled,
|
||||
};
|
||||
let mut newer = vec![merged];
|
||||
newer.extend(later[1..].iter().cloned());
|
||||
(earlier[..earlier.len() - 1].to_vec(), newer)
|
||||
}
|
||||
|
||||
/// Hands the older calls at the join the name of the run they are joining.
|
||||
/// Ported from `TranscriptItems.kt`'s `adoptRun`.
|
||||
///
|
||||
/// The two pages were folded separately, so a run split by the boundary
|
||||
/// came back as two runs with two names. Naming the joined run after the
|
||||
/// *older* half would be the obvious way round and is wrong: the newer half
|
||||
/// is the part already on screen, and renaming it is renaming the row the
|
||||
/// reader is looking at, which is how a list loses its anchor.
|
||||
fn adopt_run(earlier: &[TranscriptItem], later: &[TranscriptItem]) -> Vec<TranscriptItem> {
|
||||
let Some(TranscriptItem::ToolRun { run_id, tool, .. }) = later.first() else {
|
||||
return earlier.to_vec();
|
||||
};
|
||||
// A question is in a run of its own on both sides of the join, the same as it would be
|
||||
// had the two pages been folded as one. Without this the heal would merge a group
|
||||
// straight through the row the reader was asked something on.
|
||||
if tool == ASK_USER_QUESTION {
|
||||
return earlier.to_vec();
|
||||
}
|
||||
let joining = run_id.clone();
|
||||
let tail_len = earlier
|
||||
.iter()
|
||||
.rev()
|
||||
.take_while(|item| matches!(item, TranscriptItem::ToolRun { tool, .. } if tool != ASK_USER_QUESTION))
|
||||
.count();
|
||||
if tail_len == 0 {
|
||||
return earlier.to_vec();
|
||||
}
|
||||
let split = earlier.len() - tail_len;
|
||||
let mut out = earlier[..split].to_vec();
|
||||
out.extend(earlier[split..].iter().cloned().map(|mut item| {
|
||||
// `take_while` above already restricted this slice to non-question tool calls;
|
||||
// this just guards the invariant rather than trusting it silently.
|
||||
debug_assert!(
|
||||
matches!(&item, TranscriptItem::ToolRun { tool, .. } if tool != ASK_USER_QUESTION),
|
||||
"adopt_run must never rename a question's own run"
|
||||
);
|
||||
if let TranscriptItem::ToolRun { run_id, .. } = &mut item {
|
||||
*run_id = joining.clone();
|
||||
}
|
||||
item
|
||||
}));
|
||||
out
|
||||
}
|
||||
|
||||
/// Folds one transcript event onto `items`, the way `foldEvent` does in
|
||||
/// `TranscriptItems.kt`. Every wire event has a case; see the module doc
|
||||
/// for the one difference from the Kotlin original (no `Unknown` fallback
|
||||
@@ -955,4 +1140,134 @@ mod tests {
|
||||
let err = fold_page(&values).unwrap_err();
|
||||
assert!(err.contains("couldn't parse"));
|
||||
}
|
||||
|
||||
fn tool_start(seq: u64, id: &str, tool: &str) -> SeqEvent {
|
||||
event(
|
||||
seq,
|
||||
Event::ToolStart {
|
||||
id: id.to_string(),
|
||||
tool: tool.to_string(),
|
||||
input: serde_json::json!({}),
|
||||
},
|
||||
)
|
||||
}
|
||||
|
||||
fn tool_end(seq: u64, id: &str, output: &str) -> SeqEvent {
|
||||
event(
|
||||
seq,
|
||||
Event::ToolEnd {
|
||||
id: id.to_string(),
|
||||
output: output.to_string(),
|
||||
},
|
||||
)
|
||||
}
|
||||
|
||||
/// AGENTS.md's "things that have bitten": `joinPages` used to run
|
||||
/// `adoptRun` only on the path where a *split* call was found, so a
|
||||
/// boundary landing cleanly between two already-finished calls -- most
|
||||
/// of them -- left the older page's calls under the run name they were
|
||||
/// folded with, drawing one run of tool calls as two groups. Two
|
||||
/// finished, unrelated calls (no id in common) must still end up under
|
||||
/// one run name after the join.
|
||||
#[test]
|
||||
fn a_clean_boundary_between_two_finished_runs_is_still_healed_into_one_run() {
|
||||
let older = fold_all(&[tool_start(1, "a", "Bash"), tool_end(2, "a", "old output")]);
|
||||
let newer = fold_all(&[tool_start(3, "b", "Bash"), tool_end(4, "b", "new output")]);
|
||||
let joined = join_pages(&older, &newer);
|
||||
let run_ids: Vec<_> = joined
|
||||
.iter()
|
||||
.map(|item| match item {
|
||||
TranscriptItem::ToolRun { run_id, .. } => run_id.as_str(),
|
||||
other => panic!("expected only ToolRun items, got {other:?}"),
|
||||
})
|
||||
.collect();
|
||||
assert_eq!(
|
||||
run_ids,
|
||||
vec!["b", "b"],
|
||||
"the older call must adopt the newer, already-on-screen run's name"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_call_split_across_the_boundary_merges_into_one_row() {
|
||||
let older = fold_all(&[tool_start(1, "x", "Bash")]);
|
||||
let newer = fold_all(&[tool_end(2, "x", "the result")]);
|
||||
let joined = join_pages(&older, &newer);
|
||||
assert_eq!(
|
||||
joined,
|
||||
vec![TranscriptItem::ToolRun {
|
||||
seq: 1,
|
||||
id: "x".to_string(),
|
||||
run_id: "x".to_string(),
|
||||
tool: "Bash".to_string(),
|
||||
input: "{}".to_string(),
|
||||
output: "the result".to_string(),
|
||||
done: true,
|
||||
asks: Vec::new(),
|
||||
images: Vec::new(),
|
||||
}],
|
||||
"the older half's tool/input and the newer half's output/done must both survive"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_message_split_across_the_boundary_is_rejoined_with_the_newer_halfs_identity() {
|
||||
let older = vec![TranscriptItem::AssistantMsg {
|
||||
seq: 1,
|
||||
text: "Hel".to_string(),
|
||||
settled: false,
|
||||
}];
|
||||
let newer = vec![
|
||||
TranscriptItem::AssistantMsg {
|
||||
seq: 2,
|
||||
text: "lo".to_string(),
|
||||
settled: true,
|
||||
},
|
||||
TranscriptItem::UserMsg {
|
||||
seq: 3,
|
||||
text: "next".to_string(),
|
||||
attachments: Vec::new(),
|
||||
},
|
||||
];
|
||||
let joined = join_pages(&older, &newer);
|
||||
assert_eq!(
|
||||
joined,
|
||||
vec![
|
||||
TranscriptItem::AssistantMsg {
|
||||
seq: 2,
|
||||
text: "Hello".to_string(),
|
||||
settled: true,
|
||||
},
|
||||
TranscriptItem::UserMsg {
|
||||
seq: 3,
|
||||
text: "next".to_string(),
|
||||
attachments: Vec::new(),
|
||||
},
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
/// A question is in a run of its own on both sides of a join -- healing
|
||||
/// must never rename the run of calls the reader was asked something
|
||||
/// on, the same rule `splitRun` enforces for a live turn boundary.
|
||||
#[test]
|
||||
fn adopt_run_never_renames_into_a_question_row() {
|
||||
let older = fold_all(&[tool_start(1, "a", "Bash"), tool_end(2, "a", "done")]);
|
||||
let newer = vec![TranscriptItem::ToolRun {
|
||||
seq: 3,
|
||||
id: "q".to_string(),
|
||||
run_id: "q".to_string(),
|
||||
tool: ASK_USER_QUESTION.to_string(),
|
||||
input: "{}".to_string(),
|
||||
output: String::new(),
|
||||
done: false,
|
||||
asks: Vec::new(),
|
||||
images: Vec::new(),
|
||||
}];
|
||||
let joined = join_pages(&older, &newer);
|
||||
match &joined[0] {
|
||||
TranscriptItem::ToolRun { run_id, .. } => assert_eq!(run_id, "a"),
|
||||
other => panic!("expected a ToolRun, got {other:?}"),
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,507 @@
|
||||
//! Where a session screen gets a transcript from: this phone's copy first,
|
||||
//! the server for the rest. Ported from `app/.../TranscriptSource.kt`; see
|
||||
//! `docs/TRANSCRIPT_CACHE.md` for the design this implements and
|
||||
//! `docs/CLIENT_CORE.md` for how this file corresponds to the Kotlin.
|
||||
//!
|
||||
//! One seam rather than a cache the screen has to remember to consult.
|
||||
//! Everything fetched before is asked of this, and everything the server
|
||||
//! sends is written into the cache on the way past, so a caller never
|
||||
//! learns which side answered. The one rule worth keeping in mind: the
|
||||
//! cache is never load-bearing. Every read here has a network path beside
|
||||
//! it producing the same result.
|
||||
//!
|
||||
//! **Not ported**: `EventStream.kt`'s reconnect-with-backoff loop and the
|
||||
//! ability to close a live stream from another thread. Both are wall-clock
|
||||
//! and thread-lifetime concerns that belong to whatever runtime the caller
|
||||
//! embeds this crate in (a Tokio task, an iris timer, a Kotlin coroutine
|
||||
//! scope) rather than to this pure logic -- `follow` below is the same
|
||||
//! decorator shape `iris/desktop-app/src/app.rs` and
|
||||
//! `iris/android-app/src/transcript_client.rs` already hand-wrote around
|
||||
//! `event_stream::follow_session_events`, just with the cache write built
|
||||
//! in so a future caller does not have to repeat it a third time.
|
||||
|
||||
use event_model::SeqEvent;
|
||||
|
||||
use crate::api::{ApiClient, ApiError, Transport};
|
||||
use crate::event_stream::{self, StreamItem};
|
||||
use crate::transcript_cache::SessionCache;
|
||||
|
||||
/// How many events a session screen opens with, cached or fetched.
|
||||
///
|
||||
/// The server's own default page size, named here because the cached
|
||||
/// opening has to be the same size as the fetched one -- a reader must not
|
||||
/// get a shorter first screen for having been here before (`OPENING_WINDOW`
|
||||
/// in the Kotlin original).
|
||||
pub const OPENING_WINDOW: u32 = 80;
|
||||
|
||||
/// A transcript-line parse failure, told apart from [`ApiError`] so a
|
||||
/// caller can tell "the server is unreachable" from "the server (or this
|
||||
/// phone's own disk) sent something this build cannot read" -- the two
|
||||
/// mean different things to a reader (retry, versus a build that is
|
||||
/// behind).
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct ParseError(pub String);
|
||||
|
||||
impl std::fmt::Display for ParseError {
|
||||
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
||||
f.write_str(&self.0)
|
||||
}
|
||||
}
|
||||
impl std::error::Error for ParseError {}
|
||||
|
||||
/// Either half of what can go wrong asking for a page: the network, or a
|
||||
/// line neither the cache's nor the server's copy of `parseSeqEvent` could
|
||||
/// read.
|
||||
#[derive(Debug, Clone)]
|
||||
pub enum PageError {
|
||||
Api(ApiError),
|
||||
Parse(ParseError),
|
||||
}
|
||||
|
||||
impl From<ApiError> for PageError {
|
||||
fn from(e: ApiError) -> Self {
|
||||
Self::Api(e)
|
||||
}
|
||||
}
|
||||
|
||||
impl From<ParseError> for PageError {
|
||||
fn from(e: ParseError) -> Self {
|
||||
Self::Parse(e)
|
||||
}
|
||||
}
|
||||
|
||||
fn parse_line(line: &str) -> Result<SeqEvent, ParseError> {
|
||||
serde_json::from_str(line).map_err(|e| ParseError(format!("{e}")))
|
||||
}
|
||||
|
||||
/// This phone's copy of one session's transcript, plus the server it
|
||||
/// falls back to. Ported from the Kotlin `TranscriptSource` class.
|
||||
pub struct TranscriptSource<T: Transport> {
|
||||
api: ApiClient<T>,
|
||||
session_id: String,
|
||||
pub cache: SessionCache,
|
||||
}
|
||||
|
||||
impl<T: Transport> TranscriptSource<T> {
|
||||
pub fn new(api: ApiClient<T>, session_id: impl Into<String>, cache: SessionCache) -> Self {
|
||||
Self {
|
||||
api,
|
||||
session_id: session_id.into(),
|
||||
cache,
|
||||
}
|
||||
}
|
||||
|
||||
/// The cached opening window, or `None` when there is nothing usable
|
||||
/// to draw.
|
||||
///
|
||||
/// Meant to be drawn *before* [`Self::probe`] returns, which is the
|
||||
/// whole point of the feature: the rows are on screen while the check
|
||||
/// that they are still the server's rows is in flight, and a failed
|
||||
/// check replaces them exactly as a reset does.
|
||||
pub fn cached_opening(&self, limit: usize) -> Option<Vec<SeqEvent>> {
|
||||
self.cache.tail()?;
|
||||
let lines = self.cache.newest(limit);
|
||||
if lines.is_empty() {
|
||||
return None;
|
||||
}
|
||||
match lines.iter().map(|l| parse_line(l)).collect() {
|
||||
Ok(events) => Some(events),
|
||||
// A line this build cannot read at all, which the cache's own checks cannot
|
||||
// see: it reads a seq off a line, not an event. Nothing to serve, so a cold
|
||||
// open.
|
||||
Err(ParseError(_)) => {
|
||||
self.cache.purge();
|
||||
None
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Whether the server's event at the cached cursor is still the cached
|
||||
/// one.
|
||||
///
|
||||
/// A caller must not resume a live stream from a cached seq unless it
|
||||
/// is the same conversation: a transcript is append-only in ordinary
|
||||
/// use, but the file backing it can be replaced or truncated (a
|
||||
/// sandbox re-seeded with the same ids, a backup restored, a session
|
||||
/// re-imported), and the server's catch-up on such a file would hand
|
||||
/// this phone a continuation of a *different* conversation, spliced
|
||||
/// onto the cached one with no seam. Caught with one request of a few
|
||||
/// hundred bytes.
|
||||
///
|
||||
/// `Ok(false)` purges the cache and means "open cold". `Err` is the
|
||||
/// server not being askable, which is neither: the cached rows stay
|
||||
/// on screen and the caller tries again on its own reconnect schedule.
|
||||
///
|
||||
/// What this cannot see is a line changed in the middle of the file
|
||||
/// with the tail intact -- that is what a full reload is for.
|
||||
pub fn probe(&self) -> Result<bool, ApiError> {
|
||||
let Some(tail) = self.cache.tail() else {
|
||||
return Ok(false);
|
||||
};
|
||||
// `before = seq + 1` is the newest event with seq <= the cursor, which is the
|
||||
// event *at* the cursor when the server still has one there.
|
||||
let page = self.api.fetch_transcript_lines(
|
||||
&self.session_id,
|
||||
Some(tail.seq + 1),
|
||||
1,
|
||||
false,
|
||||
None,
|
||||
)?;
|
||||
let matches = page.len() == 1
|
||||
&& parse_line(&tail.line)
|
||||
.map(|cached| cached == page[0].1)
|
||||
.unwrap_or(false);
|
||||
if !matches {
|
||||
self.cache.purge();
|
||||
}
|
||||
Ok(matches)
|
||||
}
|
||||
|
||||
/// Today's opening fetch, kept as the start of the live run. Only
|
||||
/// called when the cache has nothing to open with, or when
|
||||
/// [`Self::probe`] said what it had was not the server's.
|
||||
pub fn fetch_opening(&self) -> Result<Vec<SeqEvent>, ApiError> {
|
||||
let page =
|
||||
self.api
|
||||
.fetch_transcript_lines(&self.session_id, None, OPENING_WINDOW, false, None)?;
|
||||
for (line, event) in &page {
|
||||
self.cache.append(line, event.seq);
|
||||
}
|
||||
self.cache.flush();
|
||||
Ok(page.into_iter().map(|(_, event)| event).collect())
|
||||
}
|
||||
|
||||
/// The page before `before`: from the cache when it holds it,
|
||||
/// otherwise from the server bounded by what the cache already has.
|
||||
///
|
||||
/// `before == 0` always answers an empty page without asking the
|
||||
/// cache or the server anything -- see AGENTS.md's "things that have
|
||||
/// bitten": there is no event before the first one, so a page request
|
||||
/// there is not a harmless no-op, it is indistinguishable from having
|
||||
/// reached the start of history and would latch a caller's "there is
|
||||
/// more" flag false forever. Guarded here rather than left to every
|
||||
/// caller, because it is a fact about the question, not about who is
|
||||
/// asking it.
|
||||
///
|
||||
/// The server bound (`after`) is what keeps the cache worth having. A
|
||||
/// coalesced page reaches back as far as its row count takes it -- a
|
||||
/// single reply is hundreds of lines -- so a page fetched after the
|
||||
/// reader has been away could run straight past the cached run and
|
||||
/// overlap it, and an overlapping page cannot be stored. Told where
|
||||
/// this phone's copy starts, the server stops there instead.
|
||||
pub fn page(
|
||||
&self,
|
||||
before: u64,
|
||||
limit: u32,
|
||||
coalesce: bool,
|
||||
) -> Result<Vec<SeqEvent>, PageError> {
|
||||
if before == 0 {
|
||||
return Ok(Vec::new());
|
||||
}
|
||||
if let Some(lines) = self.cache.page(before, limit as usize, coalesce) {
|
||||
return lines
|
||||
.iter()
|
||||
.map(|l| parse_line(l).map_err(PageError::from))
|
||||
.collect();
|
||||
}
|
||||
let after = self.cache.covered_up_to(before).map(|v| v - 1);
|
||||
let page = self.api.fetch_transcript_lines(
|
||||
&self.session_id,
|
||||
Some(before),
|
||||
limit,
|
||||
coalesce,
|
||||
after,
|
||||
)?;
|
||||
if let Some((_, first_event)) = page.first() {
|
||||
// `before` rather than the newest line's seq: a coalesced page covers
|
||||
// everything up to the cursor it was asked with, and nothing in its lines
|
||||
// says so.
|
||||
let lines: Vec<String> = page.iter().map(|(line, _)| line.clone()).collect();
|
||||
self.cache
|
||||
.store_page(&lines, first_event.seq, before, coalesce);
|
||||
}
|
||||
Ok(page.into_iter().map(|(_, event)| event).collect())
|
||||
}
|
||||
|
||||
/// [`event_stream::follow_session_events`], with every frame written to
|
||||
/// the cache before `on_item` sees it.
|
||||
///
|
||||
/// Before, so that an event held back for a reader who is scrolled
|
||||
/// away is already on disk -- what the cache holds is what the server
|
||||
/// sent, not what a screen has got round to drawing. Flushed on each
|
||||
/// status change, which is a turn's boundary and the granularity a
|
||||
/// crash may as well lose, and once more when the stream ends.
|
||||
pub fn follow(
|
||||
&self,
|
||||
after: u64,
|
||||
mut on_item: impl FnMut(StreamItem) -> bool,
|
||||
) -> Result<(), ApiError> {
|
||||
let cache = &self.cache;
|
||||
let result = event_stream::follow_session_events(
|
||||
self.api.transport(),
|
||||
&self.session_id,
|
||||
after,
|
||||
|item| {
|
||||
if let StreamItem::Event { raw, event } = &item {
|
||||
cache.append(raw, event.seq);
|
||||
if matches!(event.event, event_model::Event::Status { .. }) {
|
||||
cache.flush();
|
||||
}
|
||||
}
|
||||
on_item(item)
|
||||
},
|
||||
);
|
||||
cache.flush();
|
||||
result
|
||||
}
|
||||
|
||||
/// Leaves the cache with everything it was given -- called once a
|
||||
/// caller is done with this source, mirroring the Kotlin `close`'s
|
||||
/// final flush (that method's stream cancellation itself is the
|
||||
/// runtime concern the module doc says is not ported here).
|
||||
pub fn close(&self) {
|
||||
self.cache.flush();
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use crate::api::{Body, RawResponse};
|
||||
use std::collections::VecDeque;
|
||||
use std::io::Read;
|
||||
use std::sync::Mutex;
|
||||
|
||||
/// A transport that answers fixed bodies in call order, and records
|
||||
/// every path it was asked for -- so a test can assert *how many*
|
||||
/// requests a method made, which is the point for the `before == 0`
|
||||
/// guard (AGENTS.md's regression: the guard must stop the request
|
||||
/// before it happens, not merely tolerate the empty answer).
|
||||
#[derive(Default)]
|
||||
struct ScriptedTransport {
|
||||
responses: Mutex<VecDeque<(u16, String)>>,
|
||||
calls: Mutex<Vec<String>>,
|
||||
}
|
||||
|
||||
impl ScriptedTransport {
|
||||
fn respond(&self, status: u16, body: impl Into<String>) {
|
||||
self.responses
|
||||
.lock()
|
||||
.unwrap()
|
||||
.push_back((status, body.into()));
|
||||
}
|
||||
|
||||
fn call_count(&self) -> usize {
|
||||
self.calls.lock().unwrap().len()
|
||||
}
|
||||
}
|
||||
|
||||
impl Transport for ScriptedTransport {
|
||||
fn request(
|
||||
&self,
|
||||
_method: &str,
|
||||
path: &str,
|
||||
_body: Option<Body>,
|
||||
) -> Result<RawResponse, ApiError> {
|
||||
self.calls.lock().unwrap().push(path.to_string());
|
||||
let (status, body) = self
|
||||
.responses
|
||||
.lock()
|
||||
.unwrap()
|
||||
.pop_front()
|
||||
.unwrap_or_else(|| panic!("ScriptedTransport got an unscripted request: {path}"));
|
||||
Ok(RawResponse {
|
||||
status,
|
||||
body: body.into_bytes(),
|
||||
})
|
||||
}
|
||||
|
||||
fn stream(&self, path: &str) -> Result<Box<dyn Read + Send>, ApiError> {
|
||||
self.calls.lock().unwrap().push(path.to_string());
|
||||
let (_, body) = self
|
||||
.responses
|
||||
.lock()
|
||||
.unwrap()
|
||||
.pop_front()
|
||||
.unwrap_or_else(|| {
|
||||
panic!("ScriptedTransport got an unscripted stream request: {path}")
|
||||
});
|
||||
Ok(Box::new(std::io::Cursor::new(body.into_bytes())))
|
||||
}
|
||||
}
|
||||
|
||||
fn source(
|
||||
transport: ScriptedTransport,
|
||||
cache_root: &std::path::Path,
|
||||
) -> TranscriptSource<ScriptedTransport> {
|
||||
let api = ApiClient::new(transport);
|
||||
let cache = crate::transcript_cache::TranscriptCache::new(cache_root).session("s1");
|
||||
TranscriptSource::new(api, "s1", cache)
|
||||
}
|
||||
|
||||
fn status_line(seq: u64) -> String {
|
||||
format!(r#"{{"seq":{seq},"ts":1.0,"type":"status","state":"idle"}}"#)
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_cold_cache_has_no_opening_and_fetches_from_the_server() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let transport = ScriptedTransport::default();
|
||||
transport.respond(200, format!("[{}]", status_line(1)));
|
||||
let source = source(transport, dir.path());
|
||||
|
||||
assert_eq!(source.cached_opening(80), None);
|
||||
let opening = source.fetch_opening().unwrap();
|
||||
assert_eq!(opening.len(), 1);
|
||||
assert_eq!(opening[0].seq, 1);
|
||||
// The fetch wrote through: reopening the same cache now has something to show.
|
||||
assert!(source.cache.tail().is_some());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn probe_matching_the_cached_tail_leaves_the_cache_alone() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let transport = ScriptedTransport::default();
|
||||
transport.respond(200, format!("[{}]", status_line(1)));
|
||||
let source = source(transport, dir.path());
|
||||
source.fetch_opening().unwrap();
|
||||
|
||||
let transport2 = ScriptedTransport::default();
|
||||
transport2.respond(200, format!("[{}]", status_line(1)));
|
||||
let cache = crate::transcript_cache::TranscriptCache::new(dir.path()).session("s1");
|
||||
let source2 = TranscriptSource::new(ApiClient::new(transport2), "s1", cache);
|
||||
assert!(source2.probe().unwrap());
|
||||
assert!(source2.cache.tail().is_some());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn probe_mismatching_the_cached_tail_purges_the_cache() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let transport = ScriptedTransport::default();
|
||||
transport.respond(200, format!("[{}]", status_line(1)));
|
||||
let source = source(transport, dir.path());
|
||||
source.fetch_opening().unwrap();
|
||||
|
||||
// The server now answers with a different event at the same seq -- the file
|
||||
// behind this session was replaced.
|
||||
let transport2 = ScriptedTransport::default();
|
||||
let different = r#"{"seq":1,"ts":1.0,"type":"status","state":"running"}"#.to_string();
|
||||
transport2.respond(200, format!("[{different}]"));
|
||||
let cache = crate::transcript_cache::TranscriptCache::new(dir.path()).session("s1");
|
||||
let source2 = TranscriptSource::new(ApiClient::new(transport2), "s1", cache);
|
||||
assert!(!source2.probe().unwrap());
|
||||
assert!(source2.cache.tail().is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn probe_finding_no_server_leaves_the_cache_untouched() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let transport = ScriptedTransport::default();
|
||||
transport.respond(200, format!("[{}]", status_line(1)));
|
||||
let source = source(transport, dir.path());
|
||||
source.fetch_opening().unwrap();
|
||||
|
||||
let transport2 = ScriptedTransport::default();
|
||||
transport2.respond(500, "server on fire");
|
||||
let cache = crate::transcript_cache::TranscriptCache::new(dir.path()).session("s1");
|
||||
let source2 = TranscriptSource::new(ApiClient::new(transport2), "s1", cache);
|
||||
assert!(source2.probe().is_err());
|
||||
assert!(
|
||||
source2.cache.tail().is_some(),
|
||||
"an unreachable server must not be treated as a mismatch"
|
||||
);
|
||||
}
|
||||
|
||||
/// The regression this module exists to close: `before == 0` must
|
||||
/// never reach the network or the cache, because an empty answer there
|
||||
/// is indistinguishable from "there is genuinely no more history" --
|
||||
/// AGENTS.md's `loadOlderPage` incident.
|
||||
#[test]
|
||||
fn paging_before_the_first_event_makes_no_request_at_all() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let transport = ScriptedTransport::default();
|
||||
let source = source(transport, dir.path());
|
||||
let page = source.page(0, 80, true).unwrap();
|
||||
assert!(page.is_empty());
|
||||
assert_eq!(source.api.transport().call_count(), 0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_page_already_covered_by_the_cache_never_reaches_the_server() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let transport = ScriptedTransport::default();
|
||||
transport.respond(200, format!("[{},{}]", status_line(1), status_line(2)));
|
||||
let source = source(transport, dir.path());
|
||||
source.fetch_opening().unwrap();
|
||||
|
||||
let calls_before = source.api.transport().call_count();
|
||||
let page = source.page(2, 10, true).unwrap();
|
||||
assert_eq!(page.len(), 1);
|
||||
assert_eq!(page[0].seq, 1);
|
||||
assert_eq!(
|
||||
source.api.transport().call_count(),
|
||||
calls_before,
|
||||
"a cache hit must not touch the network"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_server_page_is_bounded_by_what_the_cache_already_covers() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let transport = ScriptedTransport::default();
|
||||
transport.respond(200, format!("[{}]", status_line(5)));
|
||||
let source = source(transport, dir.path());
|
||||
source.fetch_opening().unwrap();
|
||||
// The cache now covers seq 5 onward with nothing older, so covered_up_to(5)
|
||||
// is None (nothing stored below it) -- fetch a page further back and confirm
|
||||
// the request the cache-less path makes carries no `after` in that case, then
|
||||
// a second page that the cache *does* bound.
|
||||
let transport2 = ScriptedTransport::default();
|
||||
transport2.respond(200, format!("[{}]", status_line(3)));
|
||||
let cache = crate::transcript_cache::TranscriptCache::new(dir.path()).session("s1");
|
||||
let source2 = TranscriptSource::new(ApiClient::new(transport2), "s1", cache);
|
||||
source2.page(5, 10, true).unwrap();
|
||||
assert_eq!(
|
||||
source2.api.transport().calls.lock().unwrap()[0],
|
||||
"/sessions/s1/transcript?limit=10&before=5&coalesce=true"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_bad_cached_opening_line_purges_rather_than_panicking() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let cache = crate::transcript_cache::TranscriptCache::new(dir.path()).session("s1");
|
||||
cache.append("not json at all", 1);
|
||||
cache.flush();
|
||||
let transport = ScriptedTransport::default();
|
||||
let source = TranscriptSource::new(ApiClient::new(transport), "s1", cache);
|
||||
assert_eq!(source.cached_opening(80), None);
|
||||
assert!(
|
||||
source.cache.tail().is_none(),
|
||||
"a damaged line purges the cache"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn follow_writes_events_to_the_cache_before_the_caller_sees_them() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let transport = ScriptedTransport::default();
|
||||
transport.respond(200, format!("{}\n\n", sse_frame(&status_line(1))));
|
||||
let source = source(transport, dir.path());
|
||||
let mut seen = Vec::new();
|
||||
source
|
||||
.follow(0, |item| {
|
||||
if let StreamItem::Event { event, .. } = item {
|
||||
seen.push(event.seq);
|
||||
}
|
||||
true
|
||||
})
|
||||
.unwrap();
|
||||
assert_eq!(seen, vec![1]);
|
||||
assert_eq!(source.cache.tail().unwrap().seq, 1);
|
||||
}
|
||||
|
||||
fn sse_frame(data: &str) -> String {
|
||||
format!("data:{data}")
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user