A model can cite a plausible deep link it never opened, written from
memory. The client cannot tell it from a link a search tool returned,
because server-side MCP tool results never reach it.
evidence_check.urls compares every http(s) link of the final answer,
bare or inside a Markdown link, with the URLs of the request (system
prompt, system, user and tool messages) and of the request's successful
MCP tool results. Links are compared without scheme, fragment, "www."
and trailing slash; a link counts as retrieved when it equals an evidence
URL or is a shorter form of one at a path or query boundary. Unbacked
links (at most five) are listed in an appended note; urls_note replaces
the default note, with {urls} as the placeholder for the list.
Assistant messages are not evidence, so an invented link is marked again
when the client sends it back on the next turn.
Assisted-by: Claude Code:claude-opus-5-5
Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de>
(cherry picked from commit 523e8cd3c4)
ChatEndpoint gained a compressor parameter after the spec was written, so
the openai test package no longer compiled.
Assisted-by: Claude:claude-sonnet-5-5 go golangci-lint
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The comment in sourceURLs named ExecuteMCPToolCall, which the tool
consumer matrix test (core/services/addons/tools) reads as a marker of a
file that discovers or executes tools. evidence.go only reads tool
output, so reword the comment instead of classifying the file.
Docs-Not-Needed: comment-only change, no behaviour change
Assisted-by: Claude Code:claude-opus-5-5
Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de>
(cherry picked from commit 1043d3cbc4)
Keep balanced parentheses in source URLs and decode MCP text arrays before
extracting links. This preserves Wikipedia paths and escaped query
separators instead of appending truncated citations.
Assisted-by: Codex:gpt-6
Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de>
(cherry picked from commit 9b81cb20ab)
A system prompt that tells a model to look things up first does not stop
it from answering from its own knowledge, for example when the question
comes with a picture.
profile.require_tool makes the first model call of a chat request that
offers the profile's server-side MCP tools use tool_choice "required".
Every follow-up call of the server-side tool loop is made with the
client's tool_choice again: a "required" that stayed in place would make
the model call a tool after every tool result and never answer until the
iteration limit.
With a tokenizer template the backend enforces "required" with a grammar
built from the chat template's tool-call format. Where LocalAI builds the
tool-call grammar itself, the first call's grammar leaves out the
no-action function instead.
The first call is not forced when no server-side tool was offered, when
the client set tool_choice or function_call itself, or when the request
does not end with a user message, so a request returning a client tool's
result cannot bounce tool calls between client and server.
Assisted-by: Claude Code:claude-opus-5-5
Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de>
(cherry picked from commit 2801938aac)
A research profile asks the model in its system prompt to cite its
sources, but a model can answer from a search result without naming a
single link, and the client never sees the server-side tool results that
held them.
evidence_check.sources appends one line with the distinct http(s) URLs
returned by the request's successful MCP tool calls (at most five, in
order of appearance) when the final answer names no URL itself. An answer
that already links something is left unchanged, and nothing is added when
no tool result holds a URL, so a link is never made up. The label is
configurable through evidence_check.sources_label (default "Sources") for
profiles that answer in another language.
It runs in the existing evidence gate, on the same streaming and
non-streaming paths as the number note.
Assisted-by: Claude Code:claude-opus-5-5
Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de>
(cherry picked from commit 4ee6ff1395)
A trigger run or an agent job has nobody to approve a step, and so far
the approval mode auto_readonly and the act.* grants were only recorded.
The prompt was the only thing that kept such a run from acting.
Every tool call of an unattended run now goes through one check at the
call. A tool that only reads runs. Any other tool needs the grant of its
class, and the check fails closed:
- act.files for write_file, edit_file, move_file, delete_file and the
built-in bash;
- act.addons, or act.addons:<id>, for add-on tools whose declared kind is
not read, plus act.spend when the add-on gates the tool with a
permission;
- act.spend for MCP tools.
A trigger holds its new acts list within the grants of its agent. A
trigger that declared read only runs, or that a binding in auto_readonly
mode made without asking, is refused every non-read tool whatever it
holds. A binding that cannot be read counts as auto_readonly. A job
holds the act grants of its agent. Sub-agents follow their parent, and a
saved agent cannot be started from an unattended run.
A refused call answers with a plain sentence the model can pass on, not
an error, and writes one audit log line. Triggers set acts through the
REST API; a model never can. A trigger whose plan names a file it writes
keeps act.files.
Assisted-by: Claude:claude-sonnet-5-5 go ginkgo swag
The Skills page asks for the skills of the saved agents with
agents=true and shows them with the agent's name. A skill of the
agent layer says who proposed it, can be removed (to the Trash) and
is not offered to other agents. The list of a plain chat or of the
agent form never carries them.
Assisted-by: Claude:claude-sonnet-5-5 go node
A saved agent keeps its own skills in LocalAI/agents/<agent>/skills.
Only a chat that runs that agent sees them. They sit between the folder
and personal layers, so an agent's version of a skill wins for that
agent, and they count as granted without being listed in the agent's
skills.
An agent writes one by a skill change proposal, as before; the new
layer only reads them. A proposal for an agent skill cannot take the
name of a core skill or of a document slot (read from slots.json).
When writing-skills loads in a chat of a saved agent it starts with
"Do not write files. Call propose_change with kind skill.", and the
skills.write grant makes it visible to the agent.
The Skills list gains the agent layer, with the agent's ID and name,
and a skill can be read or removed (to the Trash) with the agent
query parameter.
Assisted-by: Claude:claude-sonnet-5-5 go swag
The add-on guide names one manifest api, one way to move a file and no
migration path, and drops the section on arguments of older tool
versions. The Swagger files are generated again, which also brings in
fields that the last generation missed, and the test of the apps view
now emits every field it documents. The inventory of the add-on suites
lists the specs by their new names.
Assisted-by: Claude:claude-sonnet-5-5 go swag
A connector add-on no longer carries file bytes in the connector
envelope. The ops media and send_file need a transfer handle, and the
gateway refuses a call to them without one, or for a kind that declares
no files.
- The manifest field files.transfer, the inline file of a request and
of an answer (ConnectorFile) and the 1 MiB cap
(MaxConnectorFileBytes) are removed. The 2 MiB limit of a connector
call between hosts drops to 1 MiB, because it holds text and no file.
- A kind that declares no files moves no file: the host answers a sender
who attaches one with a plain sentence and does not offer attach_file.
A direction left out of a declared files block still gets the host
ceiling.
- The inline layer is gone from the file limit, from the API
(inline_bytes) and from the Files section of the connector page.
- The Telegram and Slack add-ons keep only the streaming paths. The
tests moved to the handle path, and the studio test rig gives every
connector add-on a table of handles.
Assisted-by: Claude:claude-sonnet-5-5 go test node
No release carried add-ons, so nothing reads older add-on data or
manifests. Delete the code that did.
- Connectors: the kind and the add-on of the Telegram connectors that
core once carried are gone (LegacyAddon, KindTelegram, the stored
binding normalization, the platform titles). A binding needs a kind,
and its add-on is the one that serves the kind. The conversion of the
old agent pool lists every connector as dropped instead of making a
Telegram binding, and its notes say so.
- The library index reads only the id field of an entry, not addonId.
- A host control that has a capability block (the network policy) is
attached by that block alone, not by a tool that replaces bash.
- The Office create tools no longer answer for the argument names of an
earlier schema, and the identity file note about old addresses is
gone.
- The known debt of the provider-name guard drops the entries of the
conversion and of the resource listing shim, and its ceiling goes
from 13 to 5.
Assisted-by: Claude:claude-sonnet-5-5 go test
No release ever shipped add-ons, so there is no installed base on api 1.
The manifest must now declare api {"min": 2, "max": 2}; a manifest with
api 1, no api or a wider range is refused with a message that names the
range.
Every field that was gated on api 2 is now part of the contract, so the
Min*API constants and their gates are gone, and so are HostAPIMin and
the apiMin host field. Three older-manifest shims go with them: the
resource listing the host implied for one add-on, the legacyArgs hint
for arguments an older version of a tool took, and the tests that
checked the gates. All shipped manifests and the test fixtures declare
api 2.
Assisted-by: Claude:claude-sonnet-5-5 go test
For a kind that declares files.transfer, the connector manager gives the
add-on a handle and not the bytes, in both directions.
Inbound, the add-on streams the file to the host. The chat upload then
reads it from the blob store, so a 6 MB PDF reaches the chat. Outbound,
the manager checks the access of the chat to the file, gives the
process that runs the add-on only the hash and the size of the content,
and the add-on pulls the chunks. The file limit of such a kind has no
inline cap: it is the smallest of the host ceiling, the ability the kind
declares and the limit the owner set for the bot, and the sentence names
the number and the layer. A kind without transfer keeps the 1 MiB inline
cap, and its sentence says so.
Checks: the files of one message may add up to three times the limit;
the media type that the add-on states must be among the types the kind
declares; an outbound file must have a type that the kind declares and
must not start with an HTML page. Every transfer writes one audit line
with direction, binding, size, result, layer and time, and no name or
content. The binding page no longer says "larger files need streaming"
for a kind that streams.
The specs run the real Telegram and Slack add-ons, the real gateway and
the real file operations over scripted platform APIs, with a 6 MB file in
each direction.
Not in this change: a daily byte counter per binding, and a virus scan
(the table has a hook that accepts everything).
Assisted-by: Claude:claude-sonnet-5-5 go test
Bindings saved before permissions were enforced have no capabilities, so
they deny files from senders, triggers, memory writes and talk-back, and
the owner could only fix that through the REST API.
The shared connector page now has a section for it, so every connector
add-on gets it: a switch and a description for each capability with the
sensitive ones marked, the role matrix (never a sensitive capability, never
above the ceiling), pairing with a code shown once, the approved channels
for talk-back, and a read-only view of the access check with the latest
decisions. A binding with no capability shows a notice that says why the
features are off, with an "Allow the usual" button that turns on the
non-sensitive everyday set.
The kinds endpoint returns the closed list of capabilities with a title,
a description and the sensitive and usual flags. The field is additive.
Assisted-by: Claude:claude-sonnet-5-5 go node playwright swag
A connector binding gets an approval setting: ask, auto or auto_readonly,
with four limits for the two automatic modes (live triggers, minutes
between runs of a recurring trigger, runs a day, lifetime in days). The
setting is generic, so every connector add-on can show it, and the
shared connector page of the add-ons now draws it. A binding that sets
nothing asks, as before.
This change stores, validates and exposes the setting. The next change
acts on it.
Assisted-by: Claude:claude-sonnet-5-5 go swag node
A saved agent now has a Builtins list: the capabilities its owner gave
it (memory.write, profile.write, skills.write, pages.write,
dashboard.write, triggers.propose, triggers.run, talkback.channels,
talkback.new_channel, files.upload, act.files, act.addons, act.send,
act.spend and the opt-in group saved_agents). The list is empty by
default, and nothing turns a grant on for a template, an import or a
write that omits the field.
A chat of the agent holds the grants the user may use at the turn
(agent scope). A tool exists when the grant is held, the chat did not
switch its group off and the run can hold rights: a sub-agent or a run
that started by itself never does. propose_change and revert_change
now exist only for a chat that holds the grant of at least one kind,
and the schema lists only those kinds.
propose_change gains the kinds skill, page and dashboard. A skill is a
SKILL.md for the personal or the agent layer, and a skill with
locked: true is refused, also as a shadow of a locked personal skill.
A page is a set of files checked against the Pages rules and written
as one change set. The dashboard is a home.json checked against its
schema. All three are re-checked when the owner confirms or edits.
GET /api/chats/agents/builtin-grants lists each grant with its title,
description and sensitive flag. The agent record, the write body and
the export file carry builtins; an old file imports as before and an
unknown name is dropped in an import and refused in a write.
Assisted-by: Claude:claude-sonnet-5-5 go gofmt swag
A connection now has a write mode, chosen on the add-on page: off (the
default), propose (each change waits for the person to confirm) or auto
(a chat of the person makes it at once). The host enforces it for every
write tool of an add-on that holds a credential, before the add-on is
called, and holds the call to the repository list of the connection.
Host:
- Binding.WriteMode, stored in both stores and in the connector API
(write_mode). Absent means off, so existing bindings stay read only.
- A credentialed add-on may declare write tools. They name the resource
with the credential slot argument, never resourceId. A tool can set
approval "always", a ceiling that keeps a proposal even in auto.
- The proposal broker fetches the credential for the preview and again
for the apply, so it is never stored. A mode lowered between the
proposal and the confirmation refuses the apply. A proposal that
awaits a person cannot be confirmed by a chat turn.
- New capability name tools.write for the roles a connector kind
declares.
Add-on, tools (kind write): comment-issue, comment-pr, create-issue,
edit-issue (title, close or reopen), add-labels, review-comment-pr.
They preview plain facts, refuse a stale target, cap and screen the
text for secrets, and keep a receipt journal plus a hidden marker in the
text, so a change whose answer was lost is not sent twice.
Assisted-by: Claude:claude-sonnet-5-5 go gofmt ginkgo node
A connector chat whose sender holds talkback.channels gets the tool
send_message. It writes in the conversation, or as a new top-level
message in a channel that the owner listed on the binding (id, label,
approved; at most 10). The tool names no platform.
An unlisted channel is refused and the error lists the ones that are.
A listed channel that the owner did not approve needs the sensitive
talkback.new_channel for each message, so only a paired sender can use
it. The agent cannot add or approve a channel, so text it read in a page
or a file cannot widen where it writes.
Messages go through the outbox (rate limit and queue), with the size cap
and the mention breaking. Each attempt adds an audit row with channel,
kind, capability, length and a hash, never the text.
A trigger can report to an approved channel with delivery target
channel. The binding, the capability and the listing are checked again
when the run ends; any failure sends the notice to the Inbox.
LOCALAI_DISABLE_CONNECTOR_TALKBACK turns both off.
Assisted-by: Claude:claude-sonnet-5-5 go swag
ASR backends like Nemotron-3.5 append end-of-utterance language tags to
transcripts ("<de-DE>", "<en-US>", ...). The committed transcript feeds
the LLM conversation (the user item Transcript field), but the per-utterance
tag is unreliable for short/ambiguous utterances (a German "Hallo." tagged
<en-US>) and the LLM treats it as a language signal, switching the reply
language against the session instructions.
commitUtteranceWithTranscript now strips the EOU tags from the transcript
that goes to appendUserItem/generateResponse (the LLM context). The emitted
input_audio_transcription event keeps the raw transcript (debugging /
client display).
Regression tests: stripEOULanguageTags unit specs + a client-commit spec
asserting the emitted event keeps the raw tag while the LLM user message is
tag-free.
Signed-off-by: nexxtmobile.de <git@nexxtmobile.de>
(cherry picked from commit dff488044c)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Anthropic sends tool_choice as an object: {"type": "auto" | "any" |
"none"} or {"type": "tool", "name": ...}. The endpoint only read the
"tool" object, so {"type": "none"} still offered the tools and
{"type": "any"} did not require a call. The object was also forwarded
to the backend unchanged, and the llama.cpp backend turns any object
tool_choice into "required", so even {"type": "auto"} forced a tool
call there. Read the object form, and forward the OpenAI equivalent.
Assisted-by: Claude:claude-opus-5-5
Signed-off-by: jaeminbird <jaeminbird@gmail.com>
(cherry picked from commit 5bd07865a3)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
/v1/messages always answered stop_reason "end_turn" for text replies,
even when generation stopped at max_tokens. Clients that continue a
truncated turn (the Anthropic SDKs, Claude Code) treated the cut-off
reply as complete. Use the same check the OpenAI endpoint uses for
finish_reason "length", in both the streaming and non-streaming paths.
Assisted-by: Claude:claude-opus-5-5
Signed-off-by: jaeminbird <jaeminbird@gmail.com>
(cherry picked from commit d905ab5fdc)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The finetune.start and quantize.start operations defaulted to the
backend names "trl" and "llama-cpp-quantization", and the backend
lister had one method per engine family. Both were special cases that
a new engine could not use.
The lister now answers for a gallery tag. A start call that names no
backend gets the first installed backend of the tag in gallery order,
and a named backend must carry the tag. With no engine installed the
call fails with a 400 that says so. The shipped gallery order keeps
trl and llama-cpp-quantization as the defaults, and a test pins it.
The change is additive for add-ons: no manifest field or operation
changes.
Assisted-by: Claude:claude-sonnet-5-5 go gofmt
The previous commit was made on a stale base and so reverted work that
landed on master before it. This commit puts every file back to the
state of its parent's parent. The permission enforcement of the
previous commit stays.
Assisted-by: Claude:claude-sonnet-5-5 go
The capabilities, role grants and pairing that a connector binding
stores now decide what a sender can make the agent do.
Authorize is one pure function: the capability must be in the owner's
ceiling for the binding and the sender must be on the allowlist. A
sensitive capability then needs a paired sender; roles never count for
it. Any other capability needs a pairing or a role that the owner
granted and that the kind lists. The default is no.
Each message gets a grant for its sender. A message that joins a
running turn narrows it to what both senders may do. The tool builder
offers a gated tool only for a held capability, and the tool checks
again when the model calls it, so a call that gets through is refused
with the reason. Today this covers propose_change (memory and profile
kinds), revert_change, the trigger tools, and files sent to the bot. A
chat worker gets the grant with the start request.
The capability gate that the trigger features ask is now answered by
Authorize, and the application sets it. Other features can add a
global switch with AddCapabilitySwitch.
Every use records an allow or deny row (time, binding, sender IDs,
roles, capability, result; no text or codes). GET
/api/chats/connectors/{id}/access returns the effective permissions
per kind of sender and the latest rows, for an add-on settings page.
A binding saved before this change has no capabilities, so its senders
lose these features until the owner enables them.
Assisted-by: Claude:claude-sonnet-5-5 go swag
The Tools menu of a chat listed a ninth built-in group, "changes", by its
raw ID with no text, and only some rows said what a switch did. The
registry now carries a title, a description of what the model can do when
the group is on, and what happens when it is off, for every group. Groups
that nobody described fall back to the label and description of their
first tool, so a new tool group needs no change in the interface.
An add-on row can show the title and description its manifest declares:
the broker may implement the optional AddonLister, and the lists carry
both fields next to the ID.
A saved agent gets builtins_off and builtins_on. builtins_off is a
ceiling: a chat of the agent shows the group off with a reason and cannot
switch it on, and a sub-agent follows it. builtins_on lists the opt-in
groups the agent's chats start with. Both are additive columns, a write
that does not name them keeps the stored ones, and groups the server does
not offer are dropped so an imported file still loads. An agent with
switches exports as version 3, so an older server refuses the file
instead of giving the agent every tool; a single-folder agent without
switches still exports as version 2.
Assisted-by: Claude:claude-sonnet-5-5 go gofmt swag
Add a manifest credentials declaration, host-enforced per-binding
resource lists, Request.Credential and ResourceKey set by the host, and
a typed ErrRateLimited that reaches the model as rate_limited.
Assisted-by: Claude:claude-sonnet-5-5 [go]
POST and PUT on /api/chats/agents take folders, a list of path and mode
rows, up to eight. The old folder field still works and is read as a
list with one entry. Responses carry folders, the effective mode of each
row and a notice with the count of shared folders a chat does not mount.
A folder inside another folder of the same agent takes the mode of the
outer one, because the file store gives a node the highest mode among
the roots above it and cannot hold a read only folder inside a write
folder. The editor data shows that mode.
An agent with one folder still exports as version 2. An agent with
several exports as version 3 with folders. A server that reads version 2
refuses version 3. Import keeps a folder that is not found as a row
that is not chosen.
Assisted-by: Claude:claude-sonnet-5-5 go gofmt
A connector chat can now propose a trigger, the person answers it in the
chat, and the run reports to the chat.
The trigger tools propose_trigger and list_triggers are offered in a
connector chat when a capability gate allows triggers.propose for the
binding. The gate is a small interface on the service with a deny-all
default, so nothing changes until the application sets one. Change and
delete stay in Studio.
A proposal from a chat stores the binding, chat and thread, a four
character code and a 24 hour expiry. The host writes the proposal and the
code in that chat. "confirm CODE" or "cancel CODE", as a whole message in
the same chat and thread, is handled before any model turn and needs
proposals.confirm. A binding may make 3 proposals an hour. Proposals that
lapse are marked expired, and the proposal card shows that state.
A trigger carries a delivery: the Inbox (default) or the chat of the
proposal, with the modes always, on_change and on_problem. The host writes
the last message of the run, cut and with broadcast mentions broken; a
message of exactly [SILENT] writes nothing; three failures in a row raise
one alert per 6 hours. A failed delivery falls back to the Inbox. Host
messages of a binding go through an outbox of 20 a minute that queues the
rest. While triggers.run is off, runs of such a trigger are skipped, not
replayed, and the record is unchanged. The audit records each step with a
hash and no text.
Assisted-by: Claude:claude-sonnet-5-5 go test ginkgo eslint
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
A connector kind can now declare the roles it gives to a sender and the
capabilities it can grant to a role. The owner of a binding enables a
ceiling of capabilities and maps roles to them. The host stores these
values and returns them with the binding and the kind list, so an add-on
settings page can show them.
Capability names are a closed list owned by the host. Sensitive names
may be listed by a kind but are never granted to a role; only a paired
sender can use them.
Pairing proves that the owner controls a platform account. The owner
asks for a one-use code (valid ten minutes) and sends it as a direct
message to the bot from an allowlisted account. The host checks the code
before any model turn and never logs it. A binding holds three paired
senders, a pairing ends after 90 days, and five wrong codes in an hour
lock the sender out for an hour.
Contract: connector kinds gain optional roles and permissions, and a
message gains optional roles. They need manifest api 2, which the host
already accepts; protocol is unchanged and manifests that declare
nothing new behave as before. The host drops roles a kind does not
declare.
Enforcement of the capabilities by feature is not part of this change.
Assisted-by: Claude:claude-sonnet-5-5 go swag
The thread_context binding setting is removed. When the kind declares
the history ability and the bot is mentioned in a thread, the host
reads the thread once for a new chat, as before. The other guards stay:
the ability check, the bound, the untrusted block, and a failure never
blocks the answer.
A binding stored by an earlier build still loads. The JSON store
ignores the unknown field. The GORM row no longer maps the
thread_context_off column; AutoMigrate does not drop it and it accepts
NULL, so reads and writes keep working. No data is migrated or removed.
Assisted-by: Claude Code:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The Settings page states the ceiling in effect from this field.
Assisted-by: Claude Code:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The connector list shows, for each binding and each kind, the limit in
effect in both directions, the layer that sets it, the ability the kind
declares and the most an owner may set. A binding accepts
file_receive_max_bytes and file_send_max_bytes; a value above the limit
of the kind is a 400.
Assisted-by: Claude Code:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
GET /api/chats takes an optional origin parameter: person (chats a
person started), automated (every other chat) or one origin kind such as
trigger or connector. The limit counts the chats kept, so a flood of
chats that a connector or a trigger started cannot push the chats of a
person off a page, and the other way round. Without the parameter the
list is unchanged.
Assisted-by: Claude Code:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
A kind can declare options with a few values and a default (manifest
api 2). The host checks the owner's choice against the declaration,
stores it on the binding, shows it in the REST API and sends the value in
effect with every poll. The add-on decides what the option means.
Assisted-by: Claude Code:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
A binding reads the earlier messages of a thread by default. The new
thread_context option turns that off, and the kind list says which kinds
can give a thread's messages. It is stored like send_files: the zero
value keeps the default.
Assisted-by: Claude Code:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The chat's network view, the administrator view and the line the model
reads about the network of its commands now take their name from the
capabilities.network an add-on declares, or from the title of its
commands tool when it declares none. The sentences no longer say
"Sandbox" or "the sandbox". The API gains a network object with the
title and the preset titles next to the existing addon field.
The text of the built-in bash and of the host-exec setting names an
add-on that provides bash instead of one add-on.
Assisted-by: Claude Code:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The prompt, the Tools menu reasons, the network error texts, the CLI help,
the API instructions and the assistant tool descriptions said "Sandbox" for
the add-on that runs commands. Core must not know that name.
The reason a chat has no commands now uses the title the provider declares
("the Zeta add-on is off for this chat") or, when none is installed, says
"the add-on that runs commands". Text that has no provider in hand speaks of
the network of commands or of an add-on that isolates them.
Assisted-by: Claude Code:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Union of both case lists in the add-on suite inventory; the swagger
files are regenerated from the merged code.
Assisted-by: Claude Code:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Document the optional body of the confirm route, the context-files route,
the card the thread draws for any kind and source, and the Memory tab. The
context-file listing is a person's own action, so the actor scan allows it.
Assisted-by: Claude Code:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The apps API spec checks that the generated docs match the emitted
fields, so it needs a descriptor in its full fixture.
Assisted-by: Claude Code:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The proposal card lets the owner correct the text before confirming.
POST /api/chats/changes/{id}/confirm now accepts an optional JSON body
{"content": "..."}. The text has the same size limit and text check as a
proposal, the file and the audit hash hold what was written, and a
refused text leaves the proposal waiting.
Assisted-by: Claude Code:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The Memory settings page needs to know which index and topic files the
host loads into the prompt. GET /api/chats/context-files walks the
registered context sources, expands the agent and channel folders that
exist, adds the agent profiles and reports each file with its size, the
line count of the index, and the caps. It only reads; the page edits and
deletes through the Files API.
Assisted-by: Claude Code:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
List, read, confirm, dismiss and undo the changes a model proposed, and
read their audit. The routes sit under /api/chats with the other chat
routes and need the chats feature. A person reaches only their own
proposals; another person's id is a 404.
Assisted-by: Claude Code:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The Network row of the Tools menu could never show the Off, Registries and
All switcher: the host stopped setting `applies` because isolation alone does
not prove network-policy enforcement, and nothing else set it.
Let the provider report enforcement in its typed execution status
(`networkPolicyEnforced`). The host sets `applies` only when that report is
true and the status is available and isolated. The Sandbox reports it for the
gVisor and KVM backends, whose guests reach the network only through the proxy
that asks the host. Providers that do not report it keep the "not enforced"
text.
When the host cannot read the status, give the unknown state a reason
(`unknown_reason`) in the API and the Tools menu: owner unreachable, not
reported, stale, invalid, not selected, no answer or reported unknown. Log the
class of each failure, rate limited. After a failure that a restart of the
add-on owner can cause, let a long turn bind and read again, at most once every
five seconds, instead of keeping the first failure for the whole turn.
The Sandbox now reports "unavailable" with a reason when it started without
settings, and explains a backend it does not know.
When the Sandbox document skills are hidden because the Sandbox is not known to
be isolated, say so in the skill list, in the turn note and in the
`load_skill` error, instead of "This chat has no skills now".
Assisted-by: Claude Code:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(addons): model execution status observations
Keep observation lifetimes explicit before runtime integration. The pure
reducer rejects retries and stale replies using exact binding identity.
Cover all eleven trace families, the complete transition matrix and
bounded histories with safety and liveness checks.
Assisted-by: nib:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(addons): visualize execution status traces
Generate a self-contained viewer from the real reducer and shared traces.
Check independent expectations, coverage and bounded invariants before
exporting data. Detect stale artifacts and nondeterministic generation
without maintaining a second reducer in JavaScript.
Assisted-by: nib:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(addons): honor the viewer artifact root
Keep default viewer output under SDD_LOCAL_ROOT when configured.\nLet go generate use the same default without forcing a source artifact.\nRetain the portable fallback and explicit output and check semantics.
Assisted-by: nib:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(addons): add typed extension contracts
Validate optional home commands, execution bindings and requested host
operations without changing manifest versions or granting authority.
Decode bounded execution status payloads conservatively and document
strict staging compatibility for older hosts.
Assisted-by: nib:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(addons): reject noncanonical extension keys
Reject case aliases before typed decoding can override canonical fields
or bypass presence checks. Keep locale maps outside exact-key checks.
Add regression coverage for status, declaration objects, and nested
entries. All status errors return unknown readiness and isolation.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(addons): reject root enums for status tools
Status tools must accept the empty object. The supported schema enums
contain only strings, so a root enum excludes every object.
Reject root enums only for execution status bindings. Cover incompatible
root constraints and optional properties without changing shared validation.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(addons): project typed home commands
Resolve declared home destinations and display metadata in the installed
Apps view. Pin packaged command icons to immutable asset URLs.
Cover strict declaration transport, immutable receipts, exact health echo,
and process restart. Keep legacy packages and disabled installed intent.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(addons): preserve typed lifecycle declarations
Copy execution and host-operation declarations from installed receipts.
The existing capability completeness test exposes the missing fields.
Exercise real staged Manager upgrades, activation rollback and recovery.
Check installed Apps metadata through pinned mTLS frontends for each actor.
Verify mutation isolation and name receipt replay coverage accurately.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(addons): stabilize fixture archive digests
Map iteration changes tar entry order between identical publishes.
Sort fixture filenames so unchanged packages retain their digest.
Check repeated publish bytes, digests and lexical archive entry order
with and without a manifest transform. Register the regression case.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(addons): resolve explicit host policy grants
Load strict administrator policy files once before application startup.
Honor explicit empty overrides without reading ignored policy files.
Copy programmatic and manager grants to isolate startup authority.
Keep the legacy CLI fallback until the official deployment policy ships.
The generic resolver already defaults to empty grants.
Verify config, CLI, hostops and execution-status checks with GOMAXPROCS=2,
-p=2 and -ldflags="-s -w" to fit the available build disk.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(addons): select explicit deployment grants
Move official host grants out of the generic executable into reviewed
host deployment policy. Stock Docker explicitly selects the shipped file;
unconfigured binaries and nil or empty programmatic grants grant nothing.
Document the standalone upgrade break and deliberate operator selection.
Do not infer consent from installed addons or merge explicit overrides.
Guard policy packaging and generic configuration boundaries with tests.
Verify executionstatus, viewer -check, config, CLI, packaging and root
architecture tests with auth, GOMAXPROCS=2 and bounded build parallelism.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(addons): gate activation on required host ops
Refuse unmet required requests before package publication or runtime
withdrawal. Keep installed intent unavailable when startup grants change.
Optional requests permit degraded operation and never create authority.
Carry bounded admin diagnostics through Apps and the owner carrier.
Keep startup policy immutable and broker authorization authoritative.
Verify executionstatus, viewer -check, lifecycle, packages, updates,
hostops, Apps and gateway offline with auth and bounded parallelism.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(addons): guard host operation registry parity
Compare startup admission names against real builtin registrations so
registry drift cannot silently change request satisfaction.
Cover dynamic progress and stop operations and connector inbound.
Reject missing, extra, duplicate and case-changed names with negative
controls. Record both regression cases in the suite inventory.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(addons): fence status observation effects
Keep observation ownership in admitted runtime operations. Deny all
correlated callbacks before dispatch, including inbound-class callbacks.
Reject status outputs before callers can open or adopt artifact handles.
Retain bounded denial correlations until the runtime endpoint closes so
late callbacks cannot recover ordinary authority. Preserve independent
ordinary operations and document the dedicated read API for T9.
Verify the status model, viewer, and race-enabled gateway, hostops and
runtime suites with the pinned offline environment.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(addons): drain callbacks before retirement
Server.Close does not wait for active callback requests. Clearing retired
observation correlations first can restore inbound authority.
Stop endpoint admission before closing connections. Drain admitted requests
before releasing correlations, and refuse dispatch after Stop. Keep locks
out of handlers and cleanup waits so cancellation cannot deadlock teardown.
Cover pending inbound callbacks, decoded authorization paused across Stop,
and handlers that ignore cancellation. Preserve ordinary authorized work
on other endpoints. Document delayed reclamation under the existing bound.
Verify the status model and viewer, then race-test gateway, hostops,
runtime, the model and root architecture checks with auth enabled.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(addons): bind owner status to exact clients
Add authenticated, versioned status reads over the owner carrier.
Revalidate actor permissions and provider selection before dispatch and
before returning an observation. Keep status separate from authority.
Admit the captured client against its immutable identity under the
withdrawal lock. Never dispatch an old binding through a replacement.
Generate runtime operation IDs on the owner and retain the T8 effect fence.
Cover forged identities, strict DTOs, stale replies, restart ordering,
wire discriminators, and unchanged model exclusion of uiOnly tools.
Document the T10 callback and request-shell integration requirements.
Verify the model and viewer, then race-test gateway, runtime, tools,
and the model with auth enabled.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(addons): compose owner status with runtime
Exercise installed addon processes through the authenticated mTLS carrier.
Keep runtime clients real while channel barriers control lookup ordering.
Reject captured clients after same-generation replacement before dispatch.
Reject completed status reads when replacement precedes owner consumption.
Prove fresh bindings succeed and record named tools and host operation IDs.
Verify the model and viewer, then race-test gateway, runtime, tools,
the model, and the protocol fixture package with auth enabled.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(studio): scope execution status observations
Run the execution status reducer within one explicit request lifetime.
Coalesce consumers without retries and withdraw stale or canceled reads.
Keep owner admission and production lifecycle integration separate for
review before wiring the shell into requests and turns.
Assisted-by: OpenAI:ChatGPT
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(studio): isolate consumer cancellation
Consumer cancellation during validation must not withdraw a valid
observation from other consumers. Return unknown locally before shared
invalidation, while preserving parent closure and freshness failures.
Cover cancellation and deterministic deadline expiry with one-read
reducer traces and live-consumer checks.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(addons): track selection mutation epochs
Detect selection ABA at config and owner mutation boundaries. Clone
provider pins for Studio readers and share synchronized selection state
across config value copies.
Track lifecycle publication, candidate rollback and recovery transitions.
Keep reads and unchanged publications stable. These lifetime epochs do
not replace current-incarnation checks or grant execution authority.
Verify race tests for config and the add-on Manager, plus application
compilation with auth tags. Request binding remains separate work.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(addons): expose owner binding transport
Add a host-only binding API with an optional owner resolver. Forward
conversation claims over authenticated mTLS with strict versioned DTOs.
Compare full bindings during validation and deny missing resolvers.
Keep ordinary tool execution unchanged through an optional backend.
Test trusted resolver fixtures, stale bindings, denial and compatibility.
Application authority and store revisions remain a separate milestone.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(studio): fence selection snapshots with epochs
Read actor-scoped records and opaque mutation tokens under store locks.
Invalidate tokens after successful eligibility changes, including ABA.
Keep reads, rejected writes and turn history from invalidating tokens.
Clone mutable records so callers cannot bypass mutation tracking.
Support authoritative revisions only for memory-only JSON stores.
File stores lack exclusive ownership; GORM lacks persisted revisions.
Fail closed for both rather than trust frontend-local state.
Ordinary chats remain unchanged; application integration stays separate.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(studio): enforce persistent JSON ownership
Acquire lifetime sidecar locks before loading or repairing JSON data.
Enable selection revisions only under cooperating exclusive ownership.
Close drains operations before releasing ownership and rejects later use.
Clean up unpublished stores when application initialization fails.
Retain published locks through Shutdown because HTTP users may remain live.
Document coordinated upgrades and the advisory local-filesystem boundary.
Keep GORM revisions unsupported pending a separate approved design.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Codex:gpt-5
* test(application): isolate warning log capture
Run warning assertions in isolated test subprocesses. The suite leaves
background log producers running, which race with global logger changes.
Keep the parent logger unchanged and check child exits and completion
markers. Preserve pin persistence and ownership warning assertions.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(studio): resolve local owner execution bindings
Resolve execution providers from owner-held chat and agent snapshots.
Fence bindings with selection epochs, mutation tokens and live runtime
identity. Recompute every component during status authorization.
Keep named-user and SQL observations unavailable until authoritative
access and shared selection revisions can detect ABA changes.
Drain restart test producers before releasing JSON store ownership.
Register six product resolver cases in the gateway suite inventory.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(studio): bound product scopes to chat turns
Keep request-local product state alive through tool calls, checkpoints
and persistence. Give chat priming its own scope instead of seeding the
next turn with a closed observation.
Exercise one reducer read per scope across prompt and tool consumers.
Check closure of pending reads on normal completion and interruption.
Provider wiring and safety projection remain separate work.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(studio): consume typed execution providers
Replace the Sandbox-specific status heuristic with owner-bound typed reads.
Share one reducer observation across turn consumers and close it at the
outer scope boundary. Keep priming and standalone requests independent.
Sandbox exposes a separate callback-free typed read while preserving its
private Settings payload. Unknown backends never imply isolation.
Provider isolation does not prove host network-policy enforcement.
Local-owner JSON bindings are supported. Named-user and SQL bindings
remain explicitly unavailable and fail closed.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(application): isolate auth startup lifetime
Shutdown does not join every background producer. Auth startup tests
can therefore delete their temporary directory while a writer remains.
Run each case in a bounded child process. The parent waits for child
exit before deleting the fixture, preserving every startup assertion.
Production shutdown and JSON ownership retention remain unchanged.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(ui): resolve installed Home app commands
Project Home navigation from installed addon declarations, not product IDs.
Reserve native and skill names and suppress every colliding addon alias.
Re-read the authenticated registry before navigation and reject stale
actors, generations, immutable entries and destinations. Keep mounted
consumers polling through disabled and failed states. Abort pending reads
on actor changes and ignore replies from obsolete request epochs.
Studio declares its own alias. Preserve legacy redirects and pin migration.
Add unit coverage, localized Home copy and command lifecycle documentation.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(ui): accept resolved Home command metadata
Apps resolves inherited titles beyond the explicit manifest label cap.
Bound resolved labels to 147 Unicode characters, including secondary pages.
Keep the backend's 60-character limit for explicit manifest labels.
Match packaged icon paths to the contract's ASCII alphabet and image types.
Accept dotted names while rejecting traversal, encodings and foreign assets.
Verify 68 focused cases, 657 total cases, lint, i18n checks and the UI build.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(ui): bind safety notices to actual providers
Warn for addon host execution and unknown isolation without changing tool
permissions or built-in host consent. Reset dismissal when the admitted
binding, observation, actor or chat context changes.
Expose presentation-only status identity from the admitted request.
Keep configured network policy visible when enforcement is unverified.
Render bounded provider explanations as escaped React text.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(ui): isolate command status across sessions
Invalidate command observations when actors or authentication sessions
change, before effects can expose a previous actor’s reply.
Keep actual host execution warnings generic instead of recommending
Sandbox installation or repair. Cover both regressions with source-hook
lifecycle tests and provider notice assertions.
Assisted-by: Codex:gpt-5 [functions]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(addons): declare audited host requests
Declare actual official hostclient operations without inferring requests
from deployment grants. Keep optional settings and egress checks separate
from required workspace and job operations.
Verify all twelve manifests through strict package fixtures and assert
that requests never self-grant. Guard generic provider and Home dispatch
without banning historical routes, native Studio, or deployment policy.
Document the audited operations and unresolved named-user and SQL gaps.
Refresh Sandbox catalog metadata for its existing typed status tool.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(addons): wire exact extension inventories and real provider selection
Run contract, official packaging and root architecture gates through actual report inventories. Exercise two installed execution providers through the real owner resolver and distinguish callback pass-through coverage. Share strict report validation with focused-scope handling and missing/skipped artifact self-tests; document direct evidence and remaining harness limits.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(ui): expire registry reads on auth refresh
Bind registry authority to the actual authentication session epoch.
Same-user refresh now rejects old polls and pending Home navigation
before effect cleanup, even when permissions and metadata stay unchanged.
Exercise both races through the production registry provider harness.
Verify 59 focused tests, 669 total tests, lint, i18n, and the UI build.
Assisted-by: Codex:gpt-5 [functions]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(studio): resolve current execution selection
Use existing principal-scoped chat and agent reads for advisory status.
Revalidate current named credentials instead of requiring historical SQL
revisions. Local-owner mode also works with the existing GORM store.
Remove resolver nonces and historical revision prerequisites. Keep exact
runtime binding and existing status admission hooks. Document current-read
consistency without promising revoke-and-restore detection.
Verify the SQLite regression fails before the fix. Two separate full race
runs pass: application 262 specs (3 skips), auth 257, gateway 115, tools 91.
Cover named chat, API key and session credentials and current-state denial.
Assisted-by: Codex:gpt-5 [functions]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactor(addons): drop selection revision tracking
Use current selection comparisons for advisory status instead of mutation
history. Keep actor, credential and conversation identity explicit in the
model. Hash current inputs at the gateway without exposing raw store data.
Remove unused epochs, revision interfaces and JSON ownership lifetimes.
Preserve current authorization, runtime identity, mutexes and atomic writes.
Document current-read semantics without historical ABA guarantees.
Verify all affected packages with the race detector and auth tag. Check
the trace viewer, prerequisite self-tests and 18 chat-command unit tests.
Assisted-by: Codex:gpt-5 [functions]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(ui): scope Apps reads and provider status
Bind Apps replies and registry ingestion to their originating auth session.
Reject late replies before effect cleanup on refresh or account switch.
Use selected-provider command DTOs in the composer instead of private
Sandbox discovery. Keep unknown isolation unknown and remove specific
add-on installation recommendations from the affected native surfaces.
Test production Apps, registry, switches and composer paths with controlled
cleanup and two arbitrary providers. Update the matching feature docs.
Assisted-by: Codex:gpt-5 [functions]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(ui): guard composer and session publication
Remove the deleted Sandbox variable from the full composer render.
Report unknown command isolation explicitly in the about card.
Bind Apps records and admin action results to their originating actor
and actual authentication epoch before cleanup can run. Reject stale
request admission and verification without changing server authorization.
Add full-component render and pending session-transition regressions.
Enable no-undef for the production composer in normal UI lint.
Assisted-by: Codex:gpt-5 [functions]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(ui): expire cancelled upgrade reconciliation
Bind cancellation reconciliation to the initiating session authority.
Discard status replies after expiry without publishing old outcomes.
Match the exact operation identity before clearing a held action.
Cover pending cancellation reads, expiry before reads, and preservation
of a newer attempt with the same action key.
Assisted-by: Codex:gpt-5 [functions]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(ui): bind background upgrades to auth lifetime
Keep background upgrade authority in AuthProvider, independent of views.
Expire pending observations before auth consumers render or logout waits.
Preserve same-session navigation and exact-operation cleanup.
Cover cancellation, completion, and verification after the origin unmounts
with actual provider transitions and the real upgrade store.
Thread captured authority through Activity retries and document expiry.
Assisted-by: Codex:gpt-5 [functions]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactor(addons): remove implicit sidebar pins
Start every account without implicit Studio or Talk pins. Preserve saved
user selections and durable explicit pins across reopen and frontends.
Remove startup seeding, seed metadata APIs, and first-install exceptions.
Apply equal retention to all absent IDs without dropping database tables.
Keep store initialization, cached errors, and the leader sweep unchanged.
Verify genuine RED regressions before removal. Race checks pass for all
42 pin specs, 10 focused application specs, and 10 pin endpoint specs.
Update pin documentation; renamed specs have no exact inventory entries.
Assisted-by: Codex:gpt-5 [functions]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(addons): declare typed model destinations
Let installed addons own model launch destinations without teaching core
about addon identities or private routes. Keep native chat and completion
outside the declaration vocabulary.
Validate strict keys, unique capabilities, declared pages and SDK route
bounds. Carry cloned typed metadata through Apps using the shared
contract type, and add owning Studio, Talk, Face and Voice declarations.
Verify strict contract RED before implementation, then 1276 passing
specs across contract, Apps, packages, runtime, protocol, config and manager.
Verify 178 packaging and architecture specs and exact carrier inventories.
Frontend dispatch and route cleanup remain a separate milestone.
Assisted-by: Codex:gpt-5 [functions]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactor(ui): resolve declared model launch actions
Resolve installed model actions through the shared addon registry. Keep
native chat and completion launches, and never promote absent providers.
Refresh actor-filtered Apps before navigation and reject stale authority,
provider metadata, generation, immutable entry and destination claims.
Use named menu choices for collisions without loading addon modules.
Remove unreleased addon-specific redirects and migrate browser fixtures
to canonical declared pages. Preserve native chat handoff and addon-local
navigation adapters. Update user documentation and historical plans.
Verify three production UI consumers fail against their previous code,
then pass all 13 mocked-HTTP browser regressions. Verify 696 host unit
cases, full quiet lint, targeted no-undef, locales, inline styles and build.
Full backend/browser integration remains outside these mocked-HTTP checks.
Assisted-by: Codex:gpt-5 [functions]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(addons): validate Ginkgo hooks before focus
Ginkgo emits null container hierarchies for suite hooks. Require hooks\nto pass before applying focus only to It cases. Normalize null\nhierarchies without weakening exact required-case comparisons.\n\nRun reporter regressions in prerequisites. Register the declared uiOnly\ntool case and remove an update fixture case excluded by the existing\nmanager focus. Both inventories match the complete CI case output.\n\nVerify 12 reporter regressions, 39 prerequisite cases, three existing\nreports, and fresh runtime, tools and focused update manager suites.
Assisted-by: Codex:gpt-5 [functions]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(addons): restore Go CI contract checks
Align route fixtures with explicit pins and declared network controls.
Keep network enforcement unknown instead of inferring it from isolation.
Propagate viewer output errors and select output paths with CLI arguments.
Check test writes and use Ginkgo assertions without copying atomic state.
Register the three migrated binding cases in the exact suite inventory.
Document two narrow security false positives for administrator file access
and symbolic credentials in reducer traces. Focused race tests pass.
The available golangci-lint reports zero issues in affected packages.
Assisted-by: OpenAI ChatGPT [functions]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(ui): align browser coverage with addon contracts
The generic provider refactor removes implicit install advice and private
Sandbox discovery. Update browser fixtures to use the installed command
metadata and typed execution observations without restoring those paths.
Keep command warnings, consent, disabled switches and privacy assertions.
Home now holds a live command consumer. Exercise polling shutdown on a
route without that consumer, after its lazy transition finishes. Preserve
the bounded cadence, error backoff and disable-stop assertions.
Restore the remembered-voices link through the addon's compatibility
router. Cover native migrations and NotFound for removed generator aliases.
Validation: 293 affected browser cases and three native service cases pass.
The gallery command passes all 74 inventoried cases. Full UI units, quiet
lint, locale parity, production build and diff checks pass.
Assisted-by: OpenAI ChatGPT [functions]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(addons): bind status to owner provider policy
Resolve typed status with the same current owner pins as execution.
Fail closed on owner policy outages and fingerprint authoritative pins.
Exercise CAS updates, conflicts, stale bindings, and policy outages.
Retain host settings when the named-account fixture replaces its gateway.
Refresh exact gateway and Apps inventories from passing reports.
Validation: the new regression fails before the fix. All 16 focused
binding and policy cases pass. Gateway passes 361 exact cases and Apps
passes 265 exact cases across their configured package reports.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactor(addons): share qualified tool identities
Use one formatter and contract-component parser for add-on identities.
Keep callable names bounded to 64 characters while recognizing long
unavailable stand-ins without granting dispatch authority.
Validate selected execution names and their provider ID at the owner
binding boundary. The real adapter already emits canonical identities.
Update exact importer and case inventories from passing reports.
Migrate the binding backend test to Ginkgo and check shutdown errors
reported by lint in the affected packages.
Validation: behavioral RED proves malformed stand-in acceptance and
plain selected-name acceptance. Affected full race suites pass: tools
94 and Studio 638, with zero skips. Application passes 275 of 278;
three existing PostgreSQL cases skip without their configured URL. All 12 owner-binding cases
pass and match the exact inventory. Scoped golangci-lint reports no issues.
Assisted-by: Codex:gpt-5 golangci-lint
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactor(addons): share execution declarations
Share pure declaration predicates across manifest validation, gateway
observations, and owner bindings. Keep authorization and exact-runtime
admission checks local. Reuse the strict manifest schema validator so
raw status definitions fail closed without changing manifest acceptance.
Share the workspace-operation prefix scan without changing grant sources.
Add declaration parity and workspace-prefix tables and update exact
inventories from passing reports.
Validation: two new gateway cases fail before the fix; all 14 pass after.
Race tests pass: contract 245, gateway 136, tools 94, and focused
application binding/workspace cases 22. Scoped golangci-lint: 0 issues.
Assisted-by: Codex:gpt-5 golangci-lint
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(addons): retain document skill cases
Match the contract inventory to the passing report after rebasing.\nKeep the new document-provider case and updated reserved-name cases.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: OpenAI:gpt-6.1-sol
* test(addons): follow owner-managed upgrades
Accepted upgrades belong to the owner and cannot be cancelled by UI.
Exercise observer expiry during reads, completion and verification.
Supply the real upgrade store to source-executed auth harnesses so
logout reaches its synchronous authority invalidation.
Match whole-package inventories to fresh Manager and gateway reports.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* fix(addons): run accepted upgrades on the owner
HTTP cancellation during a verified backup can prevent package commit.
Accept browser upgrades durably before replying and execute them under the
owner lifecycle, with bounded admission and same-operation polling.
Keep synchronous lifecycle callers unchanged. Reuse the publication and
data recovery journals rather than replay interrupted migration. Expose
real stages and safe terminal causes, and recover browser observers after
reload without resubmitting work.
Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(addons): isolate upgrade observers by session
Reset action identities when the principal changes and restore pending
identities before polling. A different account must never submit an ID
owned by the previous account.
Clear stored upgrade observers directly in logout before navigation.
Cleanup also handles a fresh store with no bound principal.
Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactor(addons): use lifecycle phase constants
Share named lifecycle phases between the journal and upgrade reducer.
Use typed events in transitions and trace tests instead of repeating wire
literals. Keep operation DTOs, serialized values and rule labels unchanged.
Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(addons): verify accepted upgrades to completion
Preserve typed pin refusals before accepting an upgrade and report the
same transition conflict while execution holds the manager lock.
Poll accepted operations in HTTP and real-process acceptance tests before
asserting publication or failure. Exercise reload and truthful stages in
the rendered Activity test, retaining version details without cancellation
controls or estimated percentages. Register the new verification cases.
Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(addons): await the Tables upgrade receipt
An accepted upgrade can still serve its previous generation. Poll the
same operation through another frontend until it reaches a terminal state
before checking the new version, retained data, grants and backup.
Verify that a repeated submission returns the same completed receipt.
Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(addons): poll the winning upgrade operation
Concurrent submissions return acceptance before publication. Observe the
winning browser session and operation until completion before asserting
the installed generation. Keep the losing transition conflict check and
require the winning ID to replay the same terminal receipt.
Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(ui): model authoritative owner settings
Host controls now read and patch revisioned owner policy through dispatch.
Update rendered fixtures to serve that strict envelope rather than local
runtime settings. Keep private confirmation browser-only, send per-key
provider changes, and keep node-local audit retention outside owner forms.
Preserve the skill default in the tools fixture so an unpinned choice
matches the provider the owner reports.
Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(ui): assert the owner policy write envelope
Verify that the private-network switch sends no owner write before its
confirmation phrase. After confirmation, assert the actual dispatch action,
operation identity, expected revision and policy-only patch.
Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(addons): cover shutdown and lifecycle exclusion
Exercise owner shutdown during the real backup path and verify Close
joins cleanup before releasing storage. Cover synchronous disable while
an upgrade is accepted, including the journal guard before reconciliation.
Document that accepted upgrades have no UI cancellation control. Register
the new lifecycle cases in the canonical suite inventory.
Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
Stefan Walcz