* feat(reindex): support tag updates
Add replace and append tag modes to reindex vector rebuilds, preserve omission-aware behavior, and propagate options through background tasks and namespace rebuilds. Align Python, TypeScript, Go, and CLI interfaces with tests and documentation.
Co-authored-by: TRAE CLI <noreply@bytedance.com>
* fix(reindex): lock file targets exactly
Use an exact path lock for existing file targets while retaining tree locks for directories and prune-orphans scopes. Add a regression test for single-file reindex.
Co-authored-by: TRAE CLI <noreply@bytedance.com>
* fix(reindex): handle prune file targets
Use exact locks for existing file targets in prune-orphans mode while retaining tree scope for missing targets. Document the existing Go ReindexOptions wait semantics and add lock regression coverage.
Co-authored-by: TRAE CLI <noreply@bytedance.com>
---------
Co-authored-by: TRAE CLI <noreply@bytedance.com>
* fix(storage): keep non-memory appends free of memory trailers
ContentWriteCoordinator._write_in_place routed every append through
MemoryFileUtils, which strips the existing trailing newline and appends
a reserved MEMORY_FIELDS metadata trailer, even for resource/skill files
where MEMORY_FIELDS is not a reserved format (see content_visibility).
Append to non-memory files now concatenates raw content instead, matching
POSIX append semantics and the documented visibility rules.
* feat(mcp): add write tool with exact-string edit support
Agents could not use viking:// as a working directory through MCP: no
tool could create or update file content. Add a write tool covering full
writes (mode=replace as create-or-overwrite, append, strict create) and
targeted edits (a list of {old_string, new_string, replace_all}
exact-string replacements applied in order, all-or-nothing), following
the Write/Edit conventions of common agent harnesses.
Edits read via read_visible and write back through the content-write
coordinator, so memory metadata trailers are preserved and semantic /
vector re-indexing triggers as with any other write. Parent directories
are created automatically by the storage layer. Descriptions spell out
writable scopes (resources, user memories/resources, agent) and the
wait=true knob for read-after-write search consistency.
Also update the stale tool-count comment in app.py and the MCP tool
tables in the en/zh guides (13 -> 14 tools).
* feat(mcp): add tree tool, split targeted edits into edit tool
tree renders the recursive directory tree under a viking:// URI,
indented by depth with file sizes, for whole-layout orientation;
level_limit/node_limit bound the output and include_abstract adds
per-file summaries. Missing directories report "(nothing under ...)"
instead of an error, matching the read tool's convention.
edit(uri, old_string, new_string, replace_all) takes over the targeted
exact-string replacement that previously lived in write's edits array,
matching the classic Edit tool signature harnesses already train on.
write now only does full-content writes (content + mode), removing the
mutually-exclusive content/edits schema ambiguity. Edits still read via
read_visible and write back through the content-write coordinator, so
memory metadata trailers are preserved and re-indexing triggers as with
any other write.
* test(plugin): update canonical MCP tool list for tree/write/edit
The marketplace test pins the server-registered MCP tool list; add the
new tree, write, and edit tools to fix plugin-tests CI.
* feat(storage): support plain files at the user scope root
Agents treating viking:// as a working directory naturally drop files
like viking://user/zeus-persona.md at the user root, but the write
coordinator only accepted the memories/ and resources/ subtrees.
Two changes make that work:
- Namespace shorthand: a dotted first segment under viking://user/ is a
file name, not a user id (canonical user ids are dot-free by
convention), so viking://user/zeus-persona.md now canonicalizes to
viking://user/<current-user>/zeus-persona.md, matching how the
reserved memories/resources/skills segments already shorthand.
Dot-free segments still address an explicit user, and an exact match
with the current user id still wins.
- Coordinator: plain files directly under the user root (or in
non-managed subdirectories) anchor their semantic refresh at the
parent directory. The managed subtrees skills/, peers/, privacy/ and
sessions/ remain read-only with an actionable error message.
* fix(namespace): narrow user-root shorthand to text-file extensions
Review on #3936 (codex /review-pr) flagged that treating any dotted
segment as a user-root file shorthand would silently re-route canonical
URIs for valid dotted user ids (e.g. alice.smith) into the current
user space. Shorthand now triggers only when the first segment ends
in a common text-file extension; dotted or email-style user ids keep
resolving as canonical user ids. Adds regression tests pinning both
behaviors.
* fix(mcp): resolve user URIs against current user
* test(mcp): pin plain-file writes directly at the user root
The user-root shorthand exists so an agent can drop viking://user/persona.md
into its workspace, but every new test went through an intermediate directory
(viking://user/project/zeus-persona.md), leaving the no-directory shape — the
one that anchors the write coordinator's refresh at the user root itself —
uncovered. Add the missing case.
Also correct the write tool docstring: the create-extension allowlist applies
to any newly created file, including one created by mode="replace" falling
back to create, not only to an explicit mode="create".
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Materialize session-aware context requests through SessionService before
loading the recall ledger, while retaining the messages.jsonl guard for
partially initialized sessions.
Add coverage for first-turn ledger writes, same-session message capture,
materialization failure recovery, and stateless requests with session
features disabled.
Co-authored-by: TRAE CLI <noreply@bytedance.com>
* feat(memory): support event tag filtering
Add session-level default event tags, commit-time overrides, durable queue propagation, and first-write vector index tagging. Include config update APIs and coverage for serialization, concurrency, extraction, and HTTP behavior.
Co-authored-by: TRAE CLI <noreply@bytedance.com>
* feat(memory): expose event tags in SDKs and CLI
Add session default tag configuration, config updates, and commit-time event tag overrides across embedded Python, standalone Python, TypeScript, Go, and the Rust CLI. Preserve explicit empty-tag semantics and document each public interface.
Co-authored-by: TRAE CLI <noreply@bytedance.com>
* fix(sdk): align legacy session tag APIs
Forward commit-time event tags through the legacy Python HTTP shims and align BaseClient session signatures without adding a new abstract-method requirement for existing subclasses.
Co-authored-by: TRAE CLI <noreply@bytedance.com>
* feat(session): allow updating auto-commit policy
Extend PATCH session config to atomically update event tags and auto-commit settings. Merge policy objects by field, use explicit null to disable automatic commits, preserve omitted fields, and expose the contract across SDKs and CLI.
Co-authored-by: TRAE CLI <noreply@bytedance.com>
* fix(session): align session config interfaces
Replace the generic session create config JSON flag with explicit event-tag and auto-commit options. Preserve omitted, object, and null auto-commit semantics across HTTP, embedded clients, SDKs, and CLI, reject ambiguous null policy fields, and handle nullable event configuration consistently.
Co-authored-by: TRAE CLI <noreply@bytedance.com>
* test(session): trim redundant event tag tests
---------
Co-authored-by: TRAE CLI <noreply@bytedance.com>
Co-authored-by: qin-ctx <qinhaojie.exe@bytedance.com>
Read replicas load the API key store once at startup and never rewrite
it, so a user registered/rotated/removed on the writer stays invisible
(new key -> "Invalid API Key"; removed key -> still accepted).
Add an optional background watcher that polls the shared key store and
reloads the in-memory index only when it actually changes:
- APIKeyManager.reload(): strictly read-only refresh that rebuilds state
and swaps it in atomically, never writing or migrating plaintext keys.
- compute_store_signature(): cheap (path, size, modTime) signature over
accounts.json + every users.json so the watcher skips unchanged polls.
- ApiKeyAuthPlugin starts/stops the watcher behind api_key_watch_enabled
(default off) with api_key_watch_interval_seconds; AuthPlugin.shutdown()
is wired into app shutdown to cancel it cleanly.
Add coverage for reload convergence, read-only/no-migrate guarantees,
uninitialized-store tolerance, signature change detection, and watcher
reload/skip/shutdown behavior.
Co-authored-by: TRAE CLI <noreply@bytedance.com>
Several routers returned Response(status='error', error=ErrorInfo(...))
directly, so FastAPI shipped them with HTTP 200 instead of the mapped
status from ERROR_CODE_TO_HTTP_STATUS. Web-studio's sessions API only
survived because of a code-based fallback; other clients (e.g. a generic
HTTP retry layer) would treat these as success and never surface the
error.
Switch the seven return sites to error_response() so the canonical
mapping drives the HTTP status, and add the three previously-unmapped
codes (INTERNAL_ERROR, NO_VECTOR_DB, INVALID_FILTER) to the map.
Residual follow-up from PR #1764 (ac9f679a).
Co-authored-by: ming <silverchris@foxmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Treat messages.jsonl as the materialization boundary for session-aware recall,
repair partial session roots during the existing authoritative append path,
and preserve Claude capture cursors when writes never reach the server.
Also replay explicitly retryable storage conflicts across memory plugins.
Co-authored-by: TRAE CLI <noreply@bytedance.com>
* feat(retrieval): assemble auto-recall context server-side via /search mode="context"
Auto-recall assembly lived in every harness plugin: each one searched per
memory type, read hits back one by one, and stitched a context block with its
own budget and degradation rules. The implementations drifted, and the shared
weaknesses showed up in production injections — roughly half of the entries
degraded to a bare URI plus a score, character budgets distorted up to 6x on
CJK text, and adjacent turns re-injected the same memories.
This moves assembly into the server as one round trip. /find stays an unchanged
stateless primitive. /search gains mode="context" (mode="list" is the default
and byte-identical to before), and /recall becomes a thin preset over the same
kernel with its v1 field names folded onto the new contract.
New assembly kernel under openviking/retrieve/context_assembler/:
- Token budgeting with a CJK-aware estimate replaces the character budget.
- detail="auto" fills breadth-first then deepens: every candidate gets a
readable floor, then overview, then full for high-scoring entries. An
oversized tier falls back to the previous one instead of being truncated,
bounded by max_tokens / candidates * 2 per entry.
- Overview extraction dispatches by source: memory files use their leading
Summary section, code files reuse code_outline signatures, long documents use
a heading tree plus first paragraph.
- Directory hits start at overview and read their .overview.md sidecar, since
directories carry no stored abstract; their full tier stays capped at
overview. v1 injected the sidecar as if it were a whole file.
- Quotas generalize beyond memory types to resources and skills, with purpose
presets supplying ratios when quotas are absent.
- dedup_turns keeps a per-session ledger at {session_uri}/.recall_log.json so
every harness inherits cross-turn dedup; exclude_uris remains as the
stateless fallback.
- Rendering flattens to one <memory uri=... type=... score=... detail=...>
element per entry. Every tier carries its URI, so the model can always drill
down through the MCP read tool.
- Query expansion and digest rewriting are opt-in and fail closed: both have
timeout fuses, and a failed rewrite still returns the unrewritten block.
Retrieval failures are counted into stats rather than silently yielding an
empty block.
Plugins now send one context request, falling back to /recall and then to raw
find on older deployments, and cache that outcome so only the first turn pays
for the probe. The tri-state recallRewrite knob chooses between local host-CLI
compression and the server digest, and client-side settings move to a plugin
section in ovcli.conf.
* refactor(retrieval): give context tiers a per-category default
The tier ladder assumed `abstract` is a cheap summary. For memory files it
is not: the memory writer stores the whole stripped body in that scalar
because it doubles as the embedding text, so `abstract` costs the same as
`full` and the ladder runs `uri < overview < abstract = full`. Two of the
model's properties fell out of that: exempting `abstract` from the per-entry
cap let a single entry eat several times the budget, and `detail` — which
only ever set a ceiling — collapsed to two distinguishable behaviours across
its four values, since `auto` already allowed `full` for memory.
Tiers now come from a per-category constant table that treats the storage
shape as a given: `events` starts at overview (the one memory type whose
`# Summary` extraction is a real compression) and may deepen to full on
leftover budget; every other category is served at `abstract`, which for
memory already is the complete file at zero read cost and for resources and
skills is the generated 256-char summary. The table carries the note to move
`events` back to `abstract` once the writer stores a separate summary scalar.
Falling out of that: prefetch now reads only the candidates whose planned
tier needs a body rather than every candidate, `detail` becomes a real pin
(start and ceiling) and additionally accepts a per-category map, and
`full_score_threshold` is gone — leftover budget is spent in score order
instead of behind an absolute threshold the observed score band cannot
support. `auto` is still accepted on the wire as a synonym for "unset".
Assembly fixes found alongside:
- Removing the abstract cap exemption would turn an oversized abstract into
a bare URI, so it now falls back to overview first — for memory that is a
cheaper substitute, not a step up.
- Rewrite timeouts were reported as failures on Python 3.10, where
`asyncio.TimeoutError` is a separate class from the builtin.
- `stats.rewrite_usage` read `token_tracker` off `VLMConfig`, which has no
such attribute; usage was structurally always null. It now reads the model
instance's tracker and reports only when the call count moved by exactly
one, since that tracker is shared.
- A single malformed ledger record made every deduped recall in that session
fail, and the file was never rewritten, so it could not heal. Records are
now coerced on read and dropped on the next write, along with records left
ahead of the clock by an archive rotation.
- Entries served as a bare URI no longer enter the dedup cooldown: they lost
to budget pressure, not to the reader having already seen them.
- The render envelope only neutralised a literal `</memory>`, so a body could
forge a sibling entry with its own uri, type and score.
- Flat-mode gathering re-derived the category from the URI, reading
`viking://resources/backup/memories/events/log.md` as an event.
- Cooled and excluded URIs are compensated with extra rows, so a fully cooled
bucket falls through to the next-best hits instead of coming back empty.
- `/recall` quotas overlay the v1 bucket defaults again; `{"events": 5}` had
started dropping the other three buckets.
- The MCP `recall` signature sent its own defaults as if the caller had, which
resolved a different profile than `POST /recall`; an unknown `detail` value
raised `KeyError` through the whole call instead of degrading.
* feat(codex): inject profile context on session start
Reuse the shared profile builder for startup, clear, and resume hooks while preserving archive injection and orphan-session status output.
Co-authored-by: TRAE CLI <noreply@bytedance.com>
* fix(retrieval): raise rewrite timeout default to 30s
* docs(agents): document low-latency recall settings
* fix(codex): prefer luna as recall compressor fallback
* refactor(plugins): unify recall compression setting
* feat(plugins): enable recall compression by default
* docs(agents): use absolute links in image docs
* fix(retrieval): address context assembly review feedback
Co-authored-by: TRAE CLI <noreply@bytedance.com>
* test: trim redundant context assembly coverage
* fix(retrieval): address second-round context assembly review
- Drop the backticked `/search` from the deprecated-recall row in both API
overviews. The reference checker scans the whole row after the method cell
for backticked paths, so it read the description as a route named
`POST /search` and Build Docs failed on an unknown, undocumented route.
- Accept ovcli.conf's full field set in both Python readers. The file's schema
belongs to the Rust CLI, which writes `root_api_key`, `output`,
`echo_command`, `show_progress` and `verbose` and ignores unknown keys; the
two Python readers had drifted into stricter subsets, so the shipped example
already failed to load in both. Adding the new `plugin` section to a working
ovcli.conf would have broken `ov doctor` and every SDK client the same way.
- Return 400 from `mode="context"` for a request `mode="list"` also rejects.
Retrieval validates query and image_url before searching, and the gather
fuse swallowed that rejection along with genuine scope failures, so a body
of `{"mode":"context"}` came back 200 with an empty block instead of the
documented parameter error. Runtime failures still degrade into
`stats.retrieval_errors`.
- Let a context request that asks for a server-side digest outlast the
server's rewrite fuse. The plugin's ordinary 15s request timeout is shorter
than the 30s fuse, so a rewrite that finished inside its own budget was
aborted client-side, discarding the whole response — including the
uncompressed block the server returns when a rewrite fails — and falling
back to `/recall`. The deadline is only extended when the body actually
requests a rewrite, and `OPENVIKING_RECALL_CONTEXT_TIMEOUT_MS` /
`plugin.recallContextTimeoutMs` pins it.
* chore(plugins): sync shared modules into the zcode snapshot
* fix(retrieval): align context quotas and plugin defaults
Restore cross-domain coding recall, reuse authoritative actor resource
scopes, and make bucket quotas the sole width control in purpose mode.
Keep plugin defaults server-owned while preserving explicit legacy limit
settings through quota conversion.
Co-authored-by: TRAE CLI <noreply@bytedance.com>
* fix(retrieval): preserve recall compatibility
Restore the deprecated recall threshold default, distinguish successful empty rewrites from compressor failures, and document legacy quota floors across coding-agent plugins.
Co-authored-by: TRAE CLI <noreply@bytedance.com>
---------
Co-authored-by: TRAE CLI <noreply@bytedance.com>
Co-authored-by: qin-ctx <qinhaojie.exe@bytedance.com>
* fix(server): stop exporting raw query strings and buffering zip responses in observability
Sweep findings: B-03, B-13. Prevent query secrets from reaching traces and keep ZIP responses streaming.
(cherry picked from commit d8ac3dc33b)
* fix(session): tolerate missing/corrupt archive in Phase-2 replay
(NotFoundError / _ArchiveMessagesCorruptError) on a missing or corrupt
archive messages.jsonl instead of returning []. That PR added skip-on-
missing tolerance to the read path (_get_uncovered_archive_messages) and to
resume_queued_commit, but not to the Phase-2 commit replay path
(_prepare_phase2_archive_messages), which calls _read_archive_messages
unguarded while rolling earlier failed archives into the current commit.
Consequence: a terminally-failed earlier archive whose messages.jsonl is
missing/corrupt (legacy "no messages" terminal data, or produced by #3417's
own archive_read terminal path) makes every subsequent commit's Phase-2
extraction raise -> caught by _run_memory_extraction's except -> the current
archive is terminal-failed too. Because the poisoned archive is only removed
from replay once "covered" (which requires a later archive to complete), and
no later archive can ever complete, the session's memory extraction is
permanently poisoned. Raw messages are safe, but extraction is stuck.
Fix: wrap the replay-loop _read_archive_messages call in the same tolerance
_get_uncovered_archive_messages already uses -- skip + warn on not-found
(_is_storage_not_found) and on _ArchiveMessagesCorruptError, re-raise real
storage failures. The skipped archive stays in covered_failed so the current
archive's .done marks it covered, clearing the poison permanently.
Adds a regression test asserting the replay skips a failed archive with a
missing messages.jsonl (and marks it covered) instead of raising, and that a
real storage failure still propagates.
Follow-up to #3417.
(cherry picked from commit 5b8ec9e68a)
* fix(client): align client surfaces without leaking memory metadata
Reconstructs the client-parity work from upstream PR #3439 on current main and strips reserved memory metadata before line slicing in both embedded and HTTP reads.
Based-on: 48b411d58c
Co-authored-by: zhiheng.liu <zhiheng.liu@bytedance.com>
* fix(index): propagate semantic vectorization failures safely
Reconstructs upstream PR #3437 on current main, carries enqueue failures through SemanticDagExecutor, and drains the attempt's embedding tracker before retry-visible failure propagation.
Based-on: 02387deb09
Co-authored-by: zhiheng.liu <zhiheng.liu@bytedance.com>
* fix(core): close privacy and embedding failure gaps
* fix(memory): strip repeated metadata trailers
* fix(core): close public memory visibility gaps
* ci: skip embedding-dependent resource test without secrets
---------
Co-authored-by: zhiheng.liu <zhiheng.liu@bytedance.com>
* fix(ragfs): preserve cache visibility on partial S3 deletes
Surface exact and per-object S3 deletion failures, while always invalidating the affected directory and stat cache scope after a recursive delete attempt.
Source-PR: #3407
Original-Commit: 8d6addf28e
* fix(session): preserve legacy policy and peer identity compatibility
Parse string false and other legacy boolean-like memory policy values without silently enabling extraction or breaking persisted configs. Encode mixed-script peers losslessly, while retaining their former lossy IDs as read-only retrieval and extraction aliases.
Source-PR: #3422
Original-Commit: 0dfd5a9ed9
* fix(memory): drain timer flush tasks during shutdown
Retain the shielded timer flush task and await it when close cancels the timer loop, so batch failures are observed and submitters are resolved without unhandled task exceptions.
Source-PR: #3438
Original-Commit: ca1d74e164
* fix(storage): preserve peer isolation and cache correctness
* fix(ingest): reserve encoded peer namespace
* ci: skip embedding-dependent resource test without secrets
* fix(ragfs): invalidate caches after partial remove
---------
Co-authored-by: zhiheng.liu <zhiheng.liu@bytedance.com>
* feat: implement server-resolved OpenViking Assets manifests
Add the openviking-assets/1 declaration flow with server-owned configuration parsing and native Rust CLI execution.
- Resolve one flat Manifest against one Catalog through an authenticated server endpoint with strict schema and Git semantic validation.
- Reject recursive includes and unsafe clone URLs; return a resolved plan without submitting resources or running server-side batches.
- Keep local credential aliases, manifest state, dry-run, failure isolation, and per-asset create/sync orchestration in the CLI.
- Generate normalized stable asset identities on the server and remove the CLI direct SHA-1 dependency.
- Update flat examples and add server resolver/API plus Rust CLI coverage.
* feat: implement server-resolved OpenViking Assets manifests
* feat: implement server-resolved OpenViking Assets manifests
* fix(pathlock): tolerate missing lock token after recursive delete
* feat: implement server-resolved OpenViking Assets manifests
* feat: implement server-resolved OpenViking Assets manifests
* feat(agent-evolution): reload global switch at commit time
* feat(agent-evolution): expose configured account in status
* test(agent-evolution): cover account in status response
* fix(agent-evolution): align live config reload semantics
* fix(agent-evolution): tolerate non-object live config
* fix(usage-reporter): use snake case count fields
* feat(usage-reporter): add file log sink
* fix
* fix: address live reload and usage sink review findings
* fix(usage-reporter): complete file sink compatibility
* fix: make experience snapshot source unambiguous
* docs(usage-reporter): align count record implementation plan
* fix: address agent evolution review blockers
* fix(usage-reporter): preserve Windows rollover deadline
* fix(usage-reporter): encode file records as JSON envelopes
* fix(usage-reporter): use snake case unique id
* fix(bot): only require VKE credentials when the TOS storage path needs them
Sweep findings: C-14. Gate AK/SK validation on an actual TOS deployment and drop the unused cluster ID.
(cherry picked from commit 8790ba509f)
* fix(server): apply configured temp_upload.default_mode to uploads
Sweep findings: B-11, D-01. Apply the documented configured upload mode when requests omit it.
(cherry picked from commit a0dc2498e8)
* fix(bot): make one-click Docker deployment generate a working config and port mapping
Sweep findings: C-12. Generate the active ov.conf and keep gateway and Docker ports aligned.
(cherry picked from commit c22af83ab6)
* fix(server): make --bot work and propagate bot flags to workers
Sweep findings: B-09, B-15. Honor the public Bot alias and replay resolved Bot settings in worker processes.
(cherry picked from commit 32a898ca14)
* fix(docker): derive entrypoint/health port from configured server port
Sweep findings: F-06. Keep server startup and every container health check on the same effective port.
(cherry picked from commit 000795c7e3)
---------
Co-authored-by: zhiheng.liu <zhiheng.liu@bytedance.com>
Jiahui Zhou