mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
Merge remote-tracking branch 'origin/master' into codex/agent-session-jsonl-location
# Conflicts: # docs/config-catalog.md # docs/cordis-catalog/services.md # docs/core-data-structures/bash.md # docs/module-graph.md # docs/rfc/INDEX.md # docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md # docs/rfc/implemented/feature/2026-06-30-hook-bridges.md # examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md # examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl # examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md # examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md # examples/acp-agent/tests/snapshots/skill-load/session.jsonl # examples/acp-agent/tests/snapshots/text-turn/session.jsonl # examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl # packages/bash/bash-local/README.md # packages/bash/bash-local/src/run.ts # packages/bash/bash-local/tests/run.spec.ts # packages/bash/bash/README.md # packages/bash/tool-bash/README.md # packages/bash/tool-bash/src/index.ts # packages/bash/tool-bash/tests/tools.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-core/src/index.ts # packages/session-persistence/session-persistence-jsonl/src/index.ts # packages/session-persistence/session-persistence-sqlite/src/index.ts # packages/session-persistence/session-persistence/README.md # packages/session-persistence/session-persistence/src/index.ts # packages/ui/acp-agent/README.md # packages/ui/stdio-agent/README.md
This commit is contained in:
Yichen Jiang
@@ -1,20 +1,8 @@
|
||||
/**
|
||||
* SQLite durable session-persistence backend (`@deepseek-ai/dsh-session-persistence-sqlite`).
|
||||
*
|
||||
* A SECOND {@link SessionPersistence} implementation, built to validate that the
|
||||
* abstract seam + the shared `runPersistenceContract` suite are genuinely
|
||||
* backend-agnostic: the same append-only / contiguous-seq / lazy-materialization
|
||||
* / interrupted-turn-close-on-load semantics the JSONL backend expresses over
|
||||
* file bytes, expressed here over `node:sqlite` rows. Each `SessionEvent` maps
|
||||
* 1:1 onto a row `(session_id, seq, type, time, data, source_event_seqs, surface_op)`.
|
||||
*
|
||||
* Like the JSONL backend it supplies ONLY the storage primitives (the
|
||||
* {@link PersistenceBackend} hooks below — INSERT/DELETE/SELECT inside
|
||||
* transactions); all the write-path orchestration lives in the backend-agnostic
|
||||
* {@link PersistenceCoordinator} this class composes. The four stateful public
|
||||
* {@link SessionPersistence} methods delegate to the coordinator; the pure
|
||||
* locator remains backend-owned.
|
||||
*
|
||||
* SQLite durable session-persistence backend. It maps each session header and
|
||||
* event to rows, and delegates write-path orchestration to
|
||||
* {@link PersistenceCoordinator}. It has no independent per-session artifact,
|
||||
* so its locator returns `undefined`.
|
||||
* @module @deepseek-ai/dsh-session-persistence-sqlite
|
||||
*/
|
||||
|
||||
@@ -90,10 +78,8 @@ export class SessionPersistenceSqlite extends SessionPersistence implements Pers
|
||||
|
||||
constructor(ctx: Context, public config: Config) {
|
||||
super(ctx)
|
||||
// Open the database asynchronously (the parent directory may need creating);
|
||||
// every hook awaits `ready` first. Opening synchronously would force a sync
|
||||
// mkdir and block plugin apply. schemastery (static Config) has already
|
||||
// filled `journalMode`; the cast records that runtime fact.
|
||||
// Open asynchronously so directory creation does not block plugin apply;
|
||||
// every storage hook awaits the same readiness promise.
|
||||
this.ready = this.openDb(config.path, (config as Required<Config>).journalMode)
|
||||
this.coordinator = new PersistenceCoordinator<number>(this.ctx, this)
|
||||
}
|
||||
@@ -127,10 +113,8 @@ export class SessionPersistenceSqlite extends SessionPersistence implements Pers
|
||||
return this.coordinator.load(id)
|
||||
}
|
||||
|
||||
// `list` is BOTH the public service method and the PersistenceBackend hook —
|
||||
// one method (the SELECT below). The coordinator adds no orchestration for
|
||||
// listing, so routing it through the coordinator would just recurse. Defined
|
||||
// once, in the "PersistenceBackend hooks" section.
|
||||
// One method serves both public `list` and the backend hook; delegating it to
|
||||
// the coordinator would call this hook recursively.
|
||||
|
||||
/**
|
||||
* The per-session init promises, exposed for white-box tests that await a
|
||||
|
||||
@@ -56,35 +56,17 @@ export interface EventRow {
|
||||
export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist'
|
||||
|
||||
/**
|
||||
* Open the database at `path` and apply the schema + pragmas. `foreign_keys`
|
||||
* makes `ON DELETE CASCADE` drop a session's events with its row; the
|
||||
* `journal_mode` pragma is set from the plugin's `journalMode` config (`wal`
|
||||
* default — the durability model the ADR records; the row shape maps 1:1
|
||||
* onto `SessionEvent`; opencode runs this exact shape on SQLite/WAL).
|
||||
*
|
||||
* The table-layout version is persisted in SQLite's `PRAGMA user_version` and
|
||||
* checked on open: a fresh database (user_version 0) is stamped with the
|
||||
* current {@link SCHEMA_VERSION}; an existing database whose version is NOT the
|
||||
* current one (written by a different, incompatible build — older or newer) is
|
||||
* REJECTED rather than opened against a layout this build does not understand.
|
||||
* There are no migrations: an earlier layout is not upgraded in place — it is
|
||||
* rejected. v1 had a different `sessions` shape; v2 lacked all of
|
||||
* `seed_length`/`source_event_seqs`/`surface_op`. v3 is SKIPPED: two unmerged
|
||||
* branches each shipped a DISTINCT v3 (one adding only `seed_length`, the other
|
||||
* adding only the surface columns), so an on-disk v3 is ambiguous — it could be
|
||||
* either sibling layout, neither of which has all of this build's columns. v4
|
||||
* is the merged layout carrying every column; bumping past the collided v3
|
||||
* makes the version check reject both sibling v3 databases instead of opening
|
||||
* one against columns it does not have.
|
||||
* Open the database and apply its schema and pragmas. A zero `user_version` is
|
||||
* stamped with {@link SCHEMA_VERSION}; every other non-current version rejects
|
||||
* rather than being migrated in place.
|
||||
* @param path - the SQLite database file to open (created when absent).
|
||||
* @param journalMode - the journal pragma to apply — a closed in-code union, validated by the plugin Config.
|
||||
* @param journalMode - validated journal pragma.
|
||||
* @returns the open handle with pragmas applied and both tables ensured.
|
||||
*/
|
||||
export function openDatabase(path: string, journalMode: JournalMode): DatabaseSync {
|
||||
const db = new DatabaseSync(path)
|
||||
db.exec('PRAGMA foreign_keys = ON')
|
||||
// journalMode is a closed in-code union (validated by the plugin Config), not
|
||||
// user-controlled SQL — safe to interpolate (PRAGMA takes no bound params).
|
||||
// The validated union is safe to interpolate into a non-bindable PRAGMA.
|
||||
db.exec(`PRAGMA journal_mode = ${journalMode.toUpperCase()}`)
|
||||
// `PRAGMA user_version` always returns exactly one row { user_version }.
|
||||
const { user_version: onDisk } = db.prepare('PRAGMA user_version').get() as { user_version: number }
|
||||
@@ -93,9 +75,7 @@ export function openDatabase(path: string, journalMode: JournalMode): DatabaseSy
|
||||
throw new Error(`session database at "${path}" has schema version ${onDisk}, incompatible with this build (${SCHEMA_VERSION})`)
|
||||
}
|
||||
if (onDisk === 0) {
|
||||
// Fresh (or pre-versioning) database: stamp the current layout version.
|
||||
// PRAGMA does not accept bound parameters, so interpolate the integer
|
||||
// constant (SCHEMA_VERSION is a trusted in-code number, not user input).
|
||||
// Stamp fresh or pre-versioning databases.
|
||||
db.exec(`PRAGMA user_version = ${SCHEMA_VERSION}`)
|
||||
}
|
||||
db.exec(`
|
||||
@@ -162,28 +142,11 @@ export function rowToEvent(row: EventRow): SessionEvent {
|
||||
}
|
||||
|
||||
/**
|
||||
* The preserved prefix of an ordered event-row list (mirrors the JSONL
|
||||
* backend's `scanLog`): the longest prefix of complete, seq-contiguous,
|
||||
* parseable rows, PLUS the seq from which a never-committed torn tail must be
|
||||
* deleted (or `undefined` if the whole list is intact).
|
||||
* Find the preserved prefix of ordered event rows. Fully written rows in an
|
||||
* interrupted final turn remain in the prefix. The first unparsable row or seq
|
||||
* gap after the last `turn/end` marks a tolerated torn tail; the same hole in
|
||||
* the committed region rejects.
|
||||
*
|
||||
* A crash can leave a durable log whose final turn never closed: real,
|
||||
* fully-written rows sit after the last `turn/end`. Those are PRESERVED — a
|
||||
* single turn can be huge in a long-horizon task, so truncating it would
|
||||
* destroy real work; the backend closes the orphaned open turn with a synthetic
|
||||
* `turn/end {kind:'interrupted'}` on load (the session-persistence RFC). The ONLY thing excluded is
|
||||
* a torn trailing fragment — a row whose `data` never parses, or a seq gap —
|
||||
* AFTER the last committed `turn/end`; that bounds the preserved region and its
|
||||
* seq is returned as `tornFrom` so `load` can physically delete it.
|
||||
*
|
||||
* The last `turn/end` is computed from the `type` COLUMN (never parsing tail
|
||||
* `data`), so a malformed `data` in an uncommitted tail row is discarded rather
|
||||
* than making the session unloadable. A parse error or seq gap AT OR BEFORE the
|
||||
* last committed `turn/end` is committed-data corruption and throws.
|
||||
*
|
||||
* This relies on the session-log invariant that every event lives inside a turn
|
||||
* (`Session.append` enforces it): only the final turn can be open, so the
|
||||
* preserved tail is at most one unclosed turn.
|
||||
* @param rows - one session's event rows, ordered by seq ascending.
|
||||
* @returns the preserved event prefix, plus `tornFrom` — the seq the physical
|
||||
* delete starts at — when a torn tail exists.
|
||||
@@ -207,12 +170,8 @@ export function scanRows(rows: readonly EventRow[]): { preserved: SessionEvent[]
|
||||
if (parsed[i]?.ok && rows[i]?.type === 'turn/end') { lastTurnEnd = i; break }
|
||||
}
|
||||
|
||||
// Walk the longest PREFIX of complete, seq-contiguous, parseable rows
|
||||
// (row i has seq === i). This includes the fully-written rows of an
|
||||
// interrupted final turn AFTER the last turn/end — real work, never
|
||||
// truncated. The walk stops at the first hole:
|
||||
// - at or before the last committed turn/end → committed corruption (throw);
|
||||
// - after it (or no committed turn/end) → tolerated torn tail (stop).
|
||||
// Preserve the contiguous prefix, including a complete interrupted turn;
|
||||
// holes through the last committed boundary throw, while later holes stop.
|
||||
const preserved: SessionEvent[] = []
|
||||
for (let i = 0; i < rows.length; i++) {
|
||||
const p = parsed[i]
|
||||
|
||||
Reference in New Issue
Block a user