Skip to content

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

Rust

Merge remote-tracking branch 'origin/pr/1826' into release/3.2.10

AkitaOnRails014bb8832bab
diff --cc CHANGELOG.md
index 19dd3475,6e632414..be19850b
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@@ -11,124 -11,11 +11,127 @@@ version in [`docs/changelog/`](docs/cha
## [Unreleased]
+### Changed
+
+- Documented the settings that `config.default.toml` had left out, and added
+ `docs/config-properties.md`, a reference table of every key `config.toml`
+ accepts with its default, environment variable and purpose. The template now
+ describes the `llm_*` keys (including `llm_compat_strict` and
+ `[[llm_fallbacks]]`), the embedding endpoint and prefix keys,
+ `tcp_keepalive_secs`, `base_path`, `release_base_url`, `cors_allow_origins`,
+ `consolidate_on_session_end`, `backfill_on_start`, `run_autowire`,
+ `claude_true_yolo`, the `contradiction_band_*` keys, and the `[run]`,
+ `[hook_spool]`, `[handoff]`, `[maintenance]`, `[dream]`, `[retrieval]`,
+ `[search.fts]`, `[profile]` and `[[admission_webhooks]]` sections. It also
+ lists the remaining keys of `[decay]` (including `[decay.half_life_days]`),
+ `[consolidation]`, `[auto_improve]`, `[auto_scope]` and `[auth]`, and the
+ `[auto_improve.scheduler.experience_entropy_filter]` table. The new entries
+ are all commented examples, and keys with a built-in default show that
+ default. `AGENTS.md` now requires a new config key to land in both files.
+
### Fixed
+- Sorted recent page lists by timestamp rather than RFC3339 text, so updates
+ with different fractional-second precision appear in chronological order
+ in the legacy recent API, project activity, folder previews and namespace
+ listings. Kept title-sort and equal-timestamp path tie-breaks (#1247).
+
+- Fixed `restore` replacing live data when a backup without `config.toml`
+ contains API keys that the configured pepper cannot verify. It now refuses
+ before the swap, preserving the live wiki, database and config, and names
+ the original configuration as the remedy (#1495).
+
+- Preserved explicit DOCX/PPTX line breaks and DOCX tabs in document imports
+ when XML uses paired tags, including formatted PowerPoint breaks in slides
+ and speaker notes. DOCX carriage returns now also keep adjacent text runs
+ on separate lines instead of joining their words. Paragraph tab-stop
+ definitions no longer insert spurious tabs into the extracted text (#1786).
+
+- Kept a wiki-sync server page when its repository file was recreated after
+ the sync planned a deletion. `sync --propagate-deletes --apply` now rechecks
+ local absence before sending the delete, preserves the page's baseline and
+ reports the changed file for the next sync, including with `--prefer repo`
+ (#1787).
+- Transcript imports (`backfill`, the `run` ledger, `recover`) now drop Codex
+ memory-writing agent runs by the same signals the live hook uses: the
+ checkout cwd, an event's recorded cwd, or a Codex user prompt that opens
+ with `## Memory Writing Agent`. A custom `CODEX_HOME` whose last path
+ component is not `.codex` previously reimported those sessions (#1790).
+- Admission webhook HTTP requests now follow redirects only within the
+ configured `scheme://host:port` origin (up to 10 hops) and fail on
+ cross-origin redirects without forwarding page payloads or applying foreign
+ response mutations, surfacing the redirect refusal cause in logs and
+ `reject`-policy errors (#1794).
+- `ai-memory project access` and `ai-memory project grants` now refuse empty
+ or whitespace-only `--workspace`, `--project`, and (for access) `--mode`
+ values before sending any request to the server. These commands take
+ required names and never call `resolve_scope`, so the #1774 choke point
+ did not cover them (#1791).
+- `ai-memory user grant` and `ai-memory user revoke` now refuse empty or
+ whitespace-only `--user`, `--workspace`, `--project`, and (for grant)
+ `--level` values before sending any request to the server. These commands
+ take required names and never call `resolve_scope`, so the #1774 choke
+ point did not cover them (#1792).
+- Stopped the lifecycle relay from treating an oversized HTTP response as a
+ transport failure and immediately resending its batch. A response beyond the
+ 64 KiB acknowledgement cap now retains its HTTP status, stops the flush, and
+ keeps unacknowledged events pending, including on HTTP 429 backpressure (#1799).
+- Decoded WebVTT cue character references before document-import sanitization,
+ preserving literal escaped tags and applying the existing text-size limit
+ to the decoded text. SRT extraction is unchanged (#1800).
+- Preserved native OIDC hook-spool entries when the POSIX or PowerShell script
+ bundle drained the shared queue. Scripts now leave those entries for native
+ credential resolution instead of posting them anonymously and retiring them
+ on a 2xx or 401 response; static, anonymous and legacy entries still drain
+ normally (#1801).
+- Refused backup restores with a missing or invalid gzip trailer before
+ replacing live data, even when all tar entries were readable (#1805).
+- Kept separate pre-migration archives when installations share a backup
+ destination and start in the same second, instead of overwriting an
+ existing installation's snapshot (#1806).
+- Restored the previous wiki file when `restore-page` could not commit its
+ SQLite update, including a rejected case-colliding historical path. Restores
+ now share the page writer's lock through conformance, file replacement and
+ indexing so a concurrent write to that same path cannot leave disk and
+ SQLite disagreeing (#1807).
+- Kept concurrent page edits current during opt-in cold-cluster dedup and dream
+ merges. Each write batch now skips if a selected source version changed,
+ preserving the newer body, tier and pin along with unchanged peers (#1808).
+- Dropping the final store writer handle now finishes when its command queue
+ is full. Accepted writes still drain before the writer thread exits, including
+ when callers have cancelled their waits (#1809).
+
+- Scheduled empty-project cleanup now preserves projects that have sent or
+ received agent messages, including claimed/cancelled history, so it cannot
+ silently delete their inbox/outbox through a project cascade (#1810).
+
+- Fixed `server add` rejecting valid inline tables in `servers.toml`, including
+ token rotations and URL changes. Updates now accept the same table forms as
+ reads and removal, preserving registered roots and other profiles (#1812).
+- Kept OpenCode V1 failed tool results in the managed workstream ledger,
+ including their visible error text and error status, instead of importing
+ only the call and silently dropping the failure reason (#1814).
+- Initialized the TypeScript SDK's MCP session before the first `callTool`,
+ fixing HTTP 422 responses with `--http-stateful`. Raw calls still skip
+ schema checks, and later wrapped calls reuse the session (#1816).
+- Preserved literal reasoning tags and their contents inside structured JSON
+ strings when parsing OpenAI-compatible tolerant replies and Anthropic text
+ replies. Reasoning blocks outside the JSON are still removed, including
+ when a strict OpenAI-compatible request falls back to tolerant parsing (#1817).
+- Disabled HTTP redirect following on the native hook client (`build_client`)
+ so 3xx responses from SSO gateways, captive portals, or proxies fail closed
+ instead of following to a 200 OK login page, which dropped spooled hook events
+ and injected login HTML into agent handoff context (#1818).
+- Supported singular units (`day`, `week`, `month`) and weeks in
+ `parse_since_to_epoch` for git commit filtering during consolidation
+ bootstrapping, trimmed surrounding whitespace, rejected negative intervals,
+ and used checked arithmetic to prevent integer overflow panics (#1820).
+- Kept OpenCode 2 failed tool results in the managed workstream ledger,
+ including their visible error text and error status, instead of importing
+ only the call and recording a status-error loss (#1823).
+ - Imported OpenCode 2 compaction session messages into the managed workstream
+ ledger (`summary`, or `error.message` on a failed compaction) instead of
+ dropping them with no event and no loss (#1824).
- Refused empty and whitespace-only `--workspace` and `--project` flags at the
shared CLI scope-resolution choke point (`resolve_scope`,
`resolve_scope_noting_marker_project`, `resolve_scope_with_marker`, and
diff --cc crates/ai-memory-workstream/src/transcript.rs
index 0d5f356e,d15dd322..7edaab6d
--- a/crates/ai-memory-workstream/src/transcript.rs
+++ b/crates/ai-memory-workstream/src/transcript.rs
@@@ -8903,177 -8792,139 +8942,329 @@@ mod tests
assert!(second.losses.is_empty());
}
+ #[test]
+ fn opencode2_failed_tool_results_keep_the_visible_error() {
+ let home = tempfile::tempdir().unwrap();
+ let db = opencode_db(home.path(), None);
+ fs::create_dir_all(db.parent().unwrap()).unwrap();
+ let connection = Connection::open(&db).unwrap();
+ connection
+ .execute_batch(
+ "CREATE TABLE session_v2(id TEXT PRIMARY KEY, directory TEXT NOT NULL, \
+ time_updated INTEGER NOT NULL);\
+ CREATE TABLE session_message(id TEXT PRIMARY KEY, session_id TEXT, type TEXT, \
+ time_updated INTEGER, data TEXT);",
+ )
+ .unwrap();
+ connection
+ .execute(
+ "INSERT INTO session_v2 VALUES ('s2', ?1, 10)",
+ [home.path().join("repo").to_string_lossy().to_string()],
+ )
+ .unwrap();
+ // Completed tools use `content`; terminal failures use `error` as a
+ // string (older OpenCode) or `{message}` (current schema). Optional
+ // error `content` is the visible result when present.
+ let rows = [
+ (
+ "completed",
+ 1,
+ json!({
+ "status": "completed",
+ "input": {"cmd": "ok"},
+ "content": [{"type": "text", "text": "success"}],
+ "error": {"type": "ignored", "message": "not a completed result"}
+ }),
+ ),
+ (
+ "failed-object",
+ 2,
+ json!({
+ "status": "error",
+ "input": {"cmd": "fail"},
+ "error": {"type": "Tool.Error", "message": "Permission denied"}
+ }),
+ ),
+ (
+ "failed-string",
+ 3,
+ json!({
+ "status": "error",
+ "input": {"cmd": "fail"},
+ "error": "disk full"
+ }),
+ ),
+ (
+ "failed-content",
+ 4,
+ json!({
+ "status": "error",
+ "input": {"cmd": "fail"},
+ "error": {"type": "Tool.Error", "message": "hidden"},
+ "content": [{"type": "text", "text": "visible content error"}]
+ }),
+ ),
+ (
+ "pending",
+ 5,
+ json!({
+ "status": "pending",
+ "input": {"cmd": "wait"},
+ "error": {"type": "Tool.Error", "message": "not a terminal result"}
+ }),
+ ),
+ (
+ "running",
+ 6,
+ json!({
+ "status": "running",
+ "input": {"cmd": "wait"},
+ "error": {"type": "Tool.Error", "message": "not a terminal result"}
+ }),
+ ),
+ (
+ "streaming",
+ 7,
+ json!({
+ "status": "streaming",
+ "input": {"cmd": "wait"},
+ "error": "not a terminal result"
+ }),
+ ),
+ (
+ "malformed",
+ 8,
+ json!({
+ "status": "error",
+ "input": {"cmd": "fail"},
+ "error": {"type": "Tool.Error"}
+ }),
+ ),
+ ];
+ for (id, updated, state) in rows {
+ connection
+ .execute(
+ "INSERT INTO session_message VALUES (?1, 's2', 'assistant', ?2, ?3)",
+ params![
+ id,
+ updated,
+ json!({"content":[{"type":"tool","name":"bash","state":state}]})
+ .to_string()
+ ],
+ )
+ .unwrap();
+ }
+ let before = fs::read(&db).unwrap();
+ let transcript = export_opencode2(home.path(), None, "s2", None).unwrap();
+ let results: Vec<_> = transcript
+ .events
+ .iter()
+ .filter(|event| event.kind == WorkstreamEventKind::ToolResult)
+ .collect();
+ assert_eq!(
+ results
+ .iter()
+ .map(|event| event.content.as_str())
+ .collect::<Vec<_>>(),
+ [
+ "success",
+ "Permission denied",
+ "disk full",
+ "visible content error"
+ ]
+ );
+ assert_eq!(results[0].metadata, json!({"status": "completed"}));
+ assert_eq!(
+ results[1].metadata,
+ json!({"status": "error", "is_error": true})
+ );
+ assert_eq!(
+ results[1].source_record_id.as_deref(),
+ Some("failed-object")
+ );
+ assert_eq!(
+ results[2].metadata,
+ json!({"status": "error", "is_error": true})
+ );
+ assert_eq!(
+ results[3].metadata,
+ json!({"status": "error", "is_error": true})
+ );
+ for status in ["pending", "running", "streaming"] {
+ assert!(
+ transcript
+ .losses
+ .iter()
+ .any(|loss| loss.contains(&format!("ended with status {status}"))),
+ "missing loss for {status}: {:?}",
+ transcript.losses
+ );
+ }
+ assert_eq!(
+ transcript
+ .losses
+ .iter()
+ .filter(|loss| loss.contains("ended with status error"))
+ .count(),
+ 1,
+ "malformed error should stay a loss: {:?}",
+ transcript.losses
+ );
+ let replay = export_opencode2(home.path(), None, "s2", None).unwrap();
+ assert_eq!(
+ transcript
++ .events
++ .iter()
++ .map(|event| &event.event_id)
++ .collect::<Vec<_>>(),
++ replay
++ .events
++ .iter()
++ .map(|event| &event.event_id)
++ .collect::<Vec<_>>()
++ );
++ assert!(
++ export_opencode2(home.path(), None, "s2", transcript.source_cursor.as_deref())
++ .unwrap()
++ .events
++ .is_empty()
++ );
++ assert_eq!(fs::read(&db).unwrap(), before);
++ }
++
+ #[test]
+ fn opencode2_compaction_summaries_are_imported() {
+ let home = tempfile::tempdir().unwrap();
+ let db = opencode_db(home.path(), None);
+ fs::create_dir_all(db.parent().unwrap()).unwrap();
+ let connection = Connection::open(&db).unwrap();
+ connection
+ .execute_batch(
+ "CREATE TABLE session_v2(id TEXT PRIMARY KEY, directory TEXT NOT NULL, \
+ time_updated INTEGER NOT NULL);\
+ CREATE TABLE session_message(id TEXT PRIMARY KEY, session_id TEXT, type TEXT, \
+ time_updated INTEGER, data TEXT);",
+ )
+ .unwrap();
+ connection
+ .execute(
+ "INSERT INTO session_v2 VALUES ('s2', ?1, 10)",
+ [home.path().join("repo").to_string_lossy().to_string()],
+ )
+ .unwrap();
+ let rows = [
+ (
+ "done",
+ 1,
+ json!({
+ "status": "completed",
+ "reason": "auto",
+ "summary": "compacted four turns"
+ }),
+ ),
+ (
+ "running",
+ 2,
+ json!({
+ "status": "running",
+ "reason": "manual",
+ "summary": "compacting now"
+ }),
+ ),
+ (
+ "failed-object",
+ 3,
+ json!({
+ "status": "failed",
+ "reason": "auto",
+ "error": {"type": "ProviderError", "message": "rate limited"}
+ }),
+ ),
+ (
+ "failed-string",
+ 4,
+ json!({
+ "status": "failed",
+ "reason": "auto",
+ "error": "provider timeout"
+ }),
+ ),
+ (
+ "failed-empty",
+ 5,
+ json!({
+ "status": "failed",
+ "reason": "auto",
+ "error": {"type": "ProviderError"}
+ }),
+ ),
+ (
+ "empty-completed",
+ 6,
+ json!({
+ "status": "completed",
+ "reason": "auto",
+ "summary": " "
+ }),
+ ),
+ ];
+ for (id, updated, data) in rows {
+ connection
+ .execute(
+ "INSERT INTO session_message VALUES (?1, 's2', 'compaction', ?2, ?3)",
+ params![id, updated, data.to_string()],
+ )
+ .unwrap();
+ }
+ let before = fs::read(&db).unwrap();
+ let transcript = export_opencode2(home.path(), None, "s2", None).unwrap();
+ let events: Vec<_> = transcript
+ .events
+ .iter()
+ .filter(|event| event.kind == WorkstreamEventKind::Compaction)
+ .collect();
+ assert_eq!(
+ events
+ .iter()
+ .map(|event| event.content.as_str())
+ .collect::<Vec<_>>(),
+ ["compacted four turns", "rate limited", "provider timeout"]
+ );
+ assert_eq!(events[0].metadata, json!({"status": "completed"}));
+ assert_eq!(events[1].metadata, json!({"status": "failed"}));
+ assert_eq!(events[1].source_record_id.as_deref(), Some("failed-object"));
+ assert_eq!(events[2].metadata, json!({"status": "failed"}));
+ for status in ["running", "failed"] {
+ assert!(
+ transcript
+ .losses
+ .iter()
+ .any(|loss| loss.contains(&format!("compaction ended with status {status}"))),
+ "missing loss for {status}: {:?}",
+ transcript.losses
+ );
+ }
+ assert_eq!(
+ transcript
+ .losses
+ .iter()
+ .filter(|loss| loss.contains("compaction ended with status failed"))
+ .count(),
+ 1,
+ "empty failed compaction should stay a loss: {:?}",
+ transcript.losses
+ );
+ assert!(
+ !transcript
+ .losses
+ .iter()
+ .any(|loss| loss.contains("status completed")),
+ "empty completed compaction is omitted, not a loss: {:?}",
+ transcript.losses
+ );
+ let replay = export_opencode2(home.path(), None, "s2", None).unwrap();
+ assert_eq!(
+ transcript
.events
.iter()
.map(|event| &event.event_id)
diff --cc docs/managed-workstreams.md
index 0ee32c32,e60821a4..80a6f13a
--- a/docs/managed-workstreams.md
+++ b/docs/managed-workstreams.md
@@@ -562,14 -562,10 +562,18 @@@ another shell, pass `--workstream-id <u
the source harness, role, event sequence, and content. Historical tool activity
is labelled completed evidence and must never be replayed as a pending call.
+OpenCode V1 tool failures contribute their visible `state.error` text as a
+result, with `status: "error"` and `is_error: true` in the ledger metadata.
+Successful calls keep their ordinary `state.output` result.
+
+OpenCode 2 tool failures contribute their visible error text as a result, with
+`status: "error"` and `is_error: true` in the ledger metadata. Successful calls
+keep their ordinary `state.content` text parts.
+
+ OpenCode 2 compaction messages import their `summary` as a compaction event
+ (and, when a failed compaction has no summary, `error.message`). The V1 adapter
+ already imported compaction parts the same way.
+
Search and tail also return optional `source_record_id` and `metadata` fields.
The text CLI prints the source record and correlation metadata as escaped JSON;
`--json` preserves these fields for consumers. Older server responses without