* feat(pdf): refactor MinerU parsing to the official file_parse API
* feat(pdf): remove mineru_api_key from configuration and examples
* feat(pdf): preflight MinerU /health during service initialization
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.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>
* feat: support oidc and ldap auth
* feat: support oidc and ldap auth
* fix: remove heima partner, clean up auth docs, add web-studio unsupported auth banner
- Remove heima from partner list in README (en/zh/ja)
- Remove unsupported env var references (OPENVIKING_AUTH_MODE, OPENVIKING_USERNAME,
OPENVIKING_PASSWORD) from LDAP auth docs
- Remove temporary switch bash snippets from auth docs
- Fix ldap_password description
- Add web-studio unsupported-auth-mode banner for oidc/ldap servers
* fix: address OIDC/LDAP review comments on auth plugin design
Key changes driven by PR review:
- **Role mapping**: OIDC and LDAP external identities always resolve to
USER role. Removed map_role() calls and group_membership-based role
mapping. Admin access is gated by the root API key mechanism only.
- **LDAP credential extraction**: Removed query-parameter-based username/
password extraction (security concern — passwords in URLs can leak via
shell history, proxy logs, and monitoring). Clients must use Basic Auth
header or form data.
- **OIDC identifier sanitization**: Auth0 and other providers may include
characters like "|" in the `sub` claim. These are now replaced with "_"
to produce valid OpenViking user identifiers.
- **Dead code removal**: Removed _extract_groups, memberof_attribute,
require_root_api_key_for_admin, _initialize_api_key_manager, and
get_request_context_checks from both plugins since they are no longer
needed.
- **Docs**: Removed query-parameter curl example, memberof_attribute and
require_root_api_key_for_admin config references.
Co-authored-by: TRAE CLI <noreply@bytedance.com>
* feat: support oidc and ldap auth
* feat: support oidc and ldap auth
* fix(auth): bind lazy OIDC imports at module scope
---------
Co-authored-by: TRAE CLI <noreply@bytedance.com>
Co-authored-by: qin-ctx <qinhaojie.exe@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>
* feat: add audio and video understanding via VLM
* docs: design media resource guards
* fix: bound media staging concurrency
* fix: cap unknown-size media staging
* test: stage media in routing fake
* test: exercise media staging callbacks
* test: trim media understanding coverage
* chore: 清理实现计划文档
* fix: 修复多凭证切换问题
---------
Co-authored-by: Qin Haojie <qinhaojie.exe@bytedance.com>
* docs: fix stale commands, paths, and provider claims
Sweep findings: D-03, D-04, D-05, D-06, D-07, D-08, D-09. Align setup and API examples with current configuration and CLI behavior.
(cherry picked from commit 2b21ee513b)
* fix(review): correct crypto output flag
Addresses blocking review finding on #3401.
(cherry picked from commit 85bb502709)
* docs(ov): finish stale CLI path cleanup
Complete the #3401 salvage by updating the API-writing templates and the remaining encryption guide examples to the Rust CLI surface.
* fix(ov): make local content operations race-safe
Salvage the safe-I/O portions of OpenViking#3414: reject unsupported local watch requests before upload, atomically create download targets, and write snapshot output before reporting JSON success. Add focused regression coverage.
* fix(ov): validate timeout and node-limit inputs
Salvage and complete OpenViking#3414 by validating every timeout and node-limit surface consistently while preserving config commands as a repair path for invalid persisted values.
* fix(ov): allow explicit help before language setup
Salvage OpenViking#3416 with a narrower contract: only clap-recognized -h/--help requests bypass first-run language selection. Bare command groups, legacy -help, and option values keep the existing gate.
* docs(ov): align session and snapshot command examples
Salvage OpenViking#3419 by correcting positional session and snapshot examples, documenting the canonical observer filesystem command, and keeping fs as a compatible alias.
* fix(ov): honor configured output defaults safely
Salvage and complete OpenViking#3424 with CLI-over-config precedence, runtime validation for normal commands, and a table fallback that leaves config repair commands usable. Also clarify the Python-client versus Rust-CLI upload-mode controls.
* fix(ov): preserve zero node-limit semantics
* ci: skip embedding-dependent resource test without secrets
* fix(cli): validate compile timeout consistently
---------
Co-authored-by: zhiheng.liu <zhiheng.liu@bytedance.com>
- add storage.agfs.pathlock.lock_timeout_secs
- use pathlock default timeout instead of hardcoded zero in wrapper
- map legacy storage.transaction.lock_timeout when new config is unset
- remote redolog by using persistent `session_commit` queue.
* 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
* feat(connector): support more git like platform
* feat(connector): support more git like platform
* feat(connector): support more git like platform
* feat(connector): support more git like platform
* feat(connector): support more git like platform
* docs: fix broken links and anchors across READMEs and guides
Sweep findings: D-10, D-11, D-12, D-13, D-14, D-15. Restore valid documentation targets and stable cross-page anchors.
(cherry picked from commit e3504d633d)
* docs: correct contributor and release references
Reconstruct the factual parts of draft #3397 against current upstream: use the supported setup wizard, align the repository tree and workflow names with tracked files, document current release paths, and repair the bug-bounty link. Excludes install-policy and subjective content rewrites.
Based-on: b332e19e40
Based-on: c89afb17f2
Co-authored-by: zhiheng.liu <zhiheng.liu@bytedance.com>
* build: propagate recipe failures and align CMake minimum
Keep build failures visible, use isolated temporary extraction paths, and enforce the native build's CMake 3.15 floor across all contributor guides. CMake version parsing accepts prerelease and vendor suffixes.
Based-on: 8943a12285
Co-authored-by: zhiheng.liu <zhiheng.liu@bytedance.com>
* fix(scripts): surface backfill enumeration failures
Preserve the safety fix from draft #3415 while retaining legacy no-op arguments for existing operational scripts. Deprecated arguments now remain parse-compatible, advertise their status in help, and emit explicit warnings when used.
Based-on: 5516d96048
Co-authored-by: zhiheng.liu <zhiheng.liu@bytedance.com>
---------
Co-authored-by: zhiheng.liu <zhiheng.liu@bytedance.com>
* feat(embedder): support extra_body passthrough in OpenAI embedder config
Adds optional `extra_body` (dict) to the OpenAI dense embedder, merged
into every embeddings.create call. Motivating use case: OpenRouter
provider routing ({"provider": {"sort": "latency"}}) — default routing
shows p90=35s/max=127s tail latency that kills interactive recall
(A/B: sorted routing is consistently sub-second).
Explicit query_param/document_param keys still take precedence on
conflict.
* feat(config): wire extra_body through embedding config layer
Add optional extra_body field to EmbeddingModelConfig and pass it to
OpenAIDenseEmbedder for the openai/azure providers, including the
multi-credential failover merge (parent-level model-behavior field).
* docs(config): document embedding extra_body with OpenRouter routing example
* docs(config): restore concrete host/cors_origins values in EN full schema
* fix(rerank): support DashScope nested request/response envelope
OpenAIRerankClient sent a flat request body ({"model", "query",
"documents"}) and parsed "results" at the top level of the response.
DashScope (qwen3-rerank) requires a nested envelope:
Request: {"model", "input": {"query", "documents"}, "parameters": ...}
Response: {"output": {"results": [...]}, "request_id", "usage"}
This caused DashScope rerank to silently fail — the response had no
top-level "results" key, so the client returned None.
Changes:
- Add _is_dashscope() to detect DashScope endpoints by host marker.
- Add _build_request_body() that produces the nested envelope for
DashScope and the flat body for standard OpenAI/Cohere services.
- Add _extract_results() that reads output.results for DashScope and
top-level results for standard services.
- Accept both "relevance_score" (singular, DashScope) and
"relevance_scores" (plural, some providers) in result items.
- Add 13 tests covering host detection, body construction, response
parsing, end-to-end mocked flows for both providers, plural key
handling, empty documents, and sparse results.
Fixes#3459
* fix(rerank): detect DashScope protocol by URL path, not hostname
Reviewer noted the previous hostname-based switch broke the documented
qwen3-rerank compatible-api endpoint (/compatible-api/v1/reranks), which
must use the flat OpenAI-style body and top-level results.
Switch to path-based detection: only /api/v1/services/rerank uses the
native nested input/output envelope; everything else (including the
DashScope compatible-api and generic OpenAI/Cohere gateways) keeps the
flat protocol. Rename _is_dashscope -> _uses_nested_envelope for clarity.
Add regression tests covering the compatible-api flat path and reconcile
the existing native-path fixtures to the nested envelope.
* docs(rerank): use qwen3-rerank for compatible-api example
The compatible-api/v1/reranks endpoint uses the flat OpenAI-compatible
protocol; qwen3-vl-rerank is a native-envelope model served at
/api/v1/services/rerank. Align the example model with the endpoint the
implementation selects by URL path.
---------
Co-authored-by: zhangyu.34 <zhangyu.34@bytedance.com>
- Add directory_marker_mode: none to all S3 config examples
- Add S3-compatible storage notes with required fields table
- Add Docker networking guidance for Linux vs macOS/Windows
- Remove private IP addresses from examples (use localhost)
- Apply changes to both English and Chinese versions
* perf(vectordb): coalesce auto cuVS rebuilds during bulk ingest
Add an opt-in bulk-ingest maintenance scope that coalesces Auto cuVS background rebuilds across multiple write batches.
- defer derived GPU maintenance until the outermost bulk scope exits while keeping native writes and persistence visible per call
- harden the background worker against debounce, generation, shutdown, and stale-candidate races
- preserve suspension across index replacement and retire replaced workers
- wait for the final Auto GPU snapshot before vectordb_perf records search QPS
- document that the scope is non-transactional and only schedules readiness on exit
Auto cuVS and background rebuild remain disabled by default. Native CPU and remote backends use no-op hooks, so their existing behavior and dtype are unchanged.
* fix(vectordb): reject stale index replacements
* fix(vectordb): harden bulk rebuild lifecycle
---------
Co-authored-by: Yuanqing Zhao <2604121+yuanqingz@users.noreply.github.com>
