Delete the Eino model adapters, callbacks, middleware, orchestration,
summarization and single-agent runner together with their dependencies.
Chat, batch tasks, workflow Agent nodes and sub-agents now share the Pi
runtime, and dispatch is a single code path instead of an engine switch.
Configuration migrates eino_middleware/eino_skills to runtime/skills and
drops the retired callback settings while old files still load. Settings,
i18n and docs describe Pi only. Also carry the Pi follow-up fixes: empty
required lists are omitted from tool schemas, historical tool results stay
with their call batch, model proxies work over HTTP/1.1, single-query
retrieval skips query expansion, and finalization docs match Pi lifecycle
events.
Introduce an isolated Node worker that hosts the Pi SDK while Go keeps
business state, permissions, MCP execution, evidence and delivery checks.
The worker is published per source fingerprint, streams events back to Go
and supports tool callbacks, cancellation, session resume and per-model
transport settings.
Agent dispatch, tool search, plan/task tools and migration controls are
wired on top of it: large tool catalogs load through Pi tool_search, the
conversation task board keeps its existing tools, and legacy mode/route
values still resolve. Workflow gains a native DAG with versioned JSON
checkpoints, and knowledge retrieval moves to native documents, splitter,
HTTP embeddings, vector search and reranking.
Add Modern Standard Arabic (ar-SA) as a selectable UI language alongside
the existing zh-CN, en-US and ru-RU locales.
- web/static/i18n/ar-SA.json: new Arabic locale (4272 leaf strings,
full key/placeholder parity with en-US). The `c2` and `webshell`
sections are intentionally omitted and fall back to English via the
i18next fallback chain (ar-SA -> en-US -> zh-CN).
- web/static/js/i18n.js: register ar-SA, detect `ar*` navigator language,
preload en-US as fallback, set document dir="rtl" for Arabic, and add
the ar-SA language label handling.
- web/static/i18n/{zh-CN,en-US,ru-RU}.json: add the `lang.arSA` label.
- web/templates/{index,api-docs}.html: add the العربية option to the
language dropdown.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Attack chain: failure text goes to textContent, so opt out of i18next
interpolation escaping that rendered upstream errors as //";
give regenerate its own message key; keep the summary card expanded across
a 409 refresh; probe for a cached graph before parsing last_react_input so
polling no longer re-reads a multi-megabyte column; hide the card in the
node-details exclusive state and bound it on narrow screens; drop the dead
hardcoded Chinese title from the API payload.
Blackboard: stop mirroring note/context-* keys into the fact body links
section, which get_project_fact returns verbatim without scope filtering;
single-line category and confidence in index rows so a newline cannot inject
a fake row; make the path overview fail closed on an empty index set.
Provenance: reuse fitUserIntentLedgerText when sanitizing a ledger entry so
a single entry cannot exceed its cap by the three ellipsis runes.
The .cjs harness now escapes interpolated values like real i18next, so the
existing XSS test also pins the escapeValue opt-out.
Retesting a finding creates an independent conversation branch that
snapshots the source history and model trace, so verification can run
multi-turn without writing to the original session.
- POST /api/vulnerabilities/:id/retest creates the branch and persists the
prompt, so a lost response, navigation or refresh can resume it
- new update_vulnerability_status tool closes the loop; a retest branch may
only read and update its own finding
- {{vulnerability_id}}, {{conversation_id}} and {{source_conversation_id}}
resolve on send, in the first turn and in follow-ups
- evidence appends to a read-only vulnerabilities.retest_log column instead
of retest_notes: that field is operator-authored and the edit form
rewrites it wholesale, so a routine edit used to erase the retest trail
- the retest prompt is prefilled with the operator's retest_notes, which
already states how to verify the fix
- copied messages are re-bound as time.Time. Scanning a DATETIME column into
a string yields RFC3339Nano while AddMessage writes the driver's
space-separated format, and messages sort on the raw created_at text, so a
branch rendered its new turn above the inherited history
The review found two failure paths that reported success for work the engine had
not done.
Rollback: it refused only when *non-protected* source files were modified, and
then ran `git reset --hard` to the previous commit - which discards every local
change to tracked files, not just the update's. Edits to roles/skills/tools (the
update itself keeps those via its own stash) and edits made after the update
were silently wiped, while Result said nothing: deployment.md's promise that
"work done afterwards is not swept away" did not hold. Rollback now copies every
protected file that differs right now into `.update-backup/rollback_<ts>/`
before the reset, sets the copies back after it, re-applies hand deletions, and
names what it kept in Result.KeptContent like an update does.
Retry: Apply merges and writes the state file before it builds, so a failed (or
toolchain-less) build leaves HEAD on the new commit with the old binary still in
place. The retry then took the `!snap.UpdateAvailable` no-op branch, aligned the
version and returned err=nil - the job was recorded as succeeded, the page said
"update finished", the CLI printed that source and binary were in place, and the
old executable kept running. The tree now carries a `.update-build-pending`
marker, written the moment the merge lands (and when an adoption commits to its
work tree) and cleared only after the new binary is in place. The no-op branch
reads it: with a toolchain it compiles and reports the build (commits=0,
binaryBuilt=true); without one it keeps refusing exactly like the first attempt,
so "install go and click again" is now a real instruction. The console stops
treating "nothing to pull" as "nothing to do" (the retry button stays live, the
confirm dialog and the done toast say the build is what will happen), and the
CLI's printResult no longer swallows the build-only result.
Both paths are covered by regression tests that fail on the pre-fix tree: two
rollback scenarios driven through real git (edit before and after the update, a
hand deletion), and four retry scenarios driven through a scripted go on PATH
(failed build, state-write failure, an adoption's failed build retried by the
next update, and no toolchain then toolchain).