Repository navigation
fix(ci): the upgrade check counts entities of every type - #512
Merged
Merged
Conversation
Since #395 the entity-types upgrade step types Terms such as Monday as Dates, which the entities list leaves out unless asked for, so the check read them as gone. It now lists the quiet types too: an entity may change type in an upgrade, but none may go. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_013sC1p4dJXjteytbxDXnk5g
adeelahmad
pushed a commit
that referenced
this pull request
Oct 17, 2026
Ported from #512 so this PR's upgrade check passes while that lands: the entity-types step re-types weekday Terms as Dates, which the default entity list leaves out, so the check read them as gone. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B
19 of 22 tasks
adeelahmad
pushed a commit
that referenced
this pull request
Oct 17, 2026
Ported from #512 so this PR's upgrade check passes while that lands: the entity-types step re-types weekday Terms as Dates, which the default entity list leaves out, so the check read them as gone. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B
adeelahmad
pushed a commit
that referenced
this pull request
Oct 17, 2026
Ported from #512 so this PR's upgrade check passes while that lands: the entity-types step re-types weekday Terms as Dates, which the default entity list leaves out, so the check read them as gone. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B
adeelahmad
pushed a commit
that referenced
this pull request
Oct 17, 2026
Ported from #512 so this PR's upgrade check passes while that lands: the entity-types step re-types weekday Terms as Dates, which the default entity list leaves out, so the check read them as gone. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AjJqXgjj1cNdKGRQbX5frb
This was referenced Oct 17, 2026
20 of 22 tasks
adeelahmad
pushed a commit
that referenced
this pull request
Oct 17, 2026
Brings in #512, the fix for the upgrade check's entity count. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01YHrWfYDCaCbKKDX4w9at9C
adeelahmad
added a commit
that referenced
this pull request
Oct 17, 2026
…ings (#495) * feat(assistant): run Python and bash in an OpenShell sandbox per conversation The assistant gets run_python, run_bash, sandbox_files and import_sandbox_file once an admin turns on Settings > Code sandbox (sandbox.enabled, off by default) and points Lens at an NVIDIA OpenShell gateway. Each conversation gets its own sandbox (lens-chat-<id>) with none of Lens's data or keys, no egress unless sandbox.network allows the package registries or public addresses, and its files kept between runs. Attachments go in by id; a file comes out only through an import_files approval. With the network on, a run after outside text asks first. Idle sandboxes are stopped and unused ones deleted by the routines loop, and deleting a conversation deletes its sandbox. OpenShell's Python client is the `sandbox` extra, fetched as a component when the sandbox is turned on; tests run it against a fake gRPC gateway. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * test(notes): keep the daily notes test from failing on 2026-10-17 The last check asked for 2026-10-17's note after the call without a date had made today's note, so on that day it found the note the deleted root had left behind. It now asks for a day no earlier call makes. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * feat(assistant): start the code sandbox's OpenShell gateway from Settings The Docker Compose install gets a sandbox profile: openshell-init makes the gateway's certificates once, openshell-key copies the client's to a volume only Lens reads, and openshell-gateway runs NVIDIA OpenShell 0.1.4 with the Docker driver (no capabilities, read-only, telemetry off). Lens signs in to it over mutual TLS. Settings > Code sandbox > Run the gateway on this machine asks the upgrade agent to start it (action=services, profile=sandbox) and turns the sandbox on at openshell-gateway:17670, after a preflight (the Compose install, a 64-bit machine, Landlock 3). Off deletes every sandbox first. The same over GET/PUT /api/v1/admin/sandbox and the MCP tools sandbox_gateway and set_sandbox_gateway. An agent that knows only monitoring says to start it by hand, with the line to run. The network setting web becomes hosts: OpenShell resolves only names its policy lists, so the sandbox reaches the package registries and the names an admin lists in sandbox.hosts, at public addresses only. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * docs(threat-model): the code sandbox's gateway profile and its hosts network Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * fix(ci): the upgrade check counts entities of every type Ported from #512 so this PR's upgrade check passes while that lands: the entity-types step re-types weekday Terms as Dates, which the default entity list leaves out, so the check read them as gone. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B --------- Co-authored-by: Adeel Ahmad <noreply@anthropic.com>
adeelahmad
added a commit
that referenced
this pull request
Oct 17, 2026
) * fix(assistant): let the assistant's tools be imported first Importing app.domain.ai_tools on its own failed: it imported automations, which loads the actions, and the agent's action subclasses Toolbox before ai_tools had defined it. Running one test file (tests/api/test_chats.py) hit it. ai_tools now imports automations last. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * feat(chat): each answer records what produced it Every answer keeps `meta`: the model and the host name of its server, the tools offered and asked for, the scope it answered in (after auto-scope), its limits and what it used, how it ended (answered, direct, limit, fallback, stopped, error), tool results that read like instructions to an AI, how long it took, Lens's version, and tokens and cost from the ledger rows that name it. Questions keep how they were sent (web, api, voice, room, automation) and their options. The answer's id is taken once the question is saved and the answer runs in activity.scope(chat:<cid>, chat_message:<mid>), in the web chat, chat rooms and the automations' agent; the streamed answer holds the scope across its steps (activity.scoped). App completions keep no messages, so their record comes back in lens.record. The stream sends `meta` before `done`; GET /chats/{cid}/messages/{mid} returns one message with its record and ledger rows. Each tool step keeps its time and whether it failed. The web app shows it all from an i in the answer's header (a sheet on a phone); old answers say they weren't recorded. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * test(notes): keep the daily notes test from failing on 2026-10-17 The last check asked for 2026-10-17's note after the call without a date had made today's note, so on that day it found the note the deleted root had left behind. It now asks for a day no earlier call makes. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * feat(chat): choose tools, a tool-call limit and a scope per answer Group the assistant's tools (GET /chats/tools lists the groups and tools a person has, what each does and why a group is missing), offer an answer only the tools picked (an admin's switch still wins), stop at a tool-call limit up to the new ai.max_tool_calls setting, and narrow one answer to its own namespaces. A conversation keeps its choice and new ones start with the last. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * docs(chat): choosing tools, namespaces and a limit; regenerate the client Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * feat(chat): a choice made as a conversation starts is the latest choice Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * fix(chat): setting the server up keeps every tool, whatever the latest choice Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * test(entities): wait for the typed search before counting merge options The find box empties while the list for what was typed loads, so on a busy runner the first list could pass the wait and then vanish. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * test(settings): the AI section's server values include ai.max_tool_calls Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * fix(chat): find_resources belongs to the archive's tools Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * docs(chat): a new built-in tool joins a tool group Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * fix(ci): the upgrade check counts entities of every type Ported from #512 so this PR's upgrade check passes while that lands: the entity-types step re-types weekday Terms as Dates, which the default entity list leaves out, so the check read them as gone. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B --------- Co-authored-by: Adeel Ahmad <noreply@anthropic.com>
21 of 23 tasks
adeelahmad
added a commit
that referenced
this pull request
Oct 17, 2026
…load the files it makes (#497) * feat(assistant): run Python and bash in an OpenShell sandbox per conversation The assistant gets run_python, run_bash, sandbox_files and import_sandbox_file once an admin turns on Settings > Code sandbox (sandbox.enabled, off by default) and points Lens at an NVIDIA OpenShell gateway. Each conversation gets its own sandbox (lens-chat-<id>) with none of Lens's data or keys, no egress unless sandbox.network allows the package registries or public addresses, and its files kept between runs. Attachments go in by id; a file comes out only through an import_files approval. With the network on, a run after outside text asks first. Idle sandboxes are stopped and unused ones deleted by the routines loop, and deleting a conversation deletes its sandbox. OpenShell's Python client is the `sandbox` extra, fetched as a component when the sandbox is turned on; tests run it against a fake gRPC gateway. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * test(notes): keep the daily notes test from failing on 2026-10-17 The last check asked for 2026-10-17's note after the call without a date had made today's note, so on that day it found the note the deleted root had left behind. It now asks for a day no earlier call makes. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * feat(assistant): start the code sandbox's OpenShell gateway from Settings The Docker Compose install gets a sandbox profile: openshell-init makes the gateway's certificates once, openshell-key copies the client's to a volume only Lens reads, and openshell-gateway runs NVIDIA OpenShell 0.1.4 with the Docker driver (no capabilities, read-only, telemetry off). Lens signs in to it over mutual TLS. Settings > Code sandbox > Run the gateway on this machine asks the upgrade agent to start it (action=services, profile=sandbox) and turns the sandbox on at openshell-gateway:17670, after a preflight (the Compose install, a 64-bit machine, Landlock 3). Off deletes every sandbox first. The same over GET/PUT /api/v1/admin/sandbox and the MCP tools sandbox_gateway and set_sandbox_gateway. An agent that knows only monitoring says to start it by hand, with the line to run. The network setting web becomes hosts: OpenShell resolves only names its policy lists, so the sandbox reaches the package registries and the names an admin lists in sandbox.hosts, at public addresses only. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * docs(threat-model): the code sandbox's gateway profile and its hosts network Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * feat(chat): show the code sandbox's runs in the conversation and download the files it makes Each run_python or run_bash step carries the start of its stdout, the end of its stderr and how it ended; the web app shows it folded under the answer with the code. share_sandbox_file copies a file out of the sandbox, kept encrypted with the conversation, as a download button on the answer (GET /api/v1/chats/{cid}/files/{fid}), deleted with the conversation or the account. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * fix(ci): the upgrade check counts entities of every type Ported from #512 so this PR's upgrade check passes while that lands: the entity-types step re-types weekday Terms as Dates, which the default entity list leaves out, so the check read them as gone. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B --------- Co-authored-by: Adeel Ahmad <noreply@anthropic.com>
adeelahmad
added a commit
that referenced
this pull request
Oct 18, 2026
* fix(assistant): let the assistant's tools be imported first Importing app.domain.ai_tools on its own failed: it imported automations, which loads the actions, and the agent's action subclasses Toolbox before ai_tools had defined it. Running one test file (tests/api/test_chats.py) hit it. ai_tools now imports automations last. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * feat(chat): each answer records what produced it Every answer keeps `meta`: the model and the host name of its server, the tools offered and asked for, the scope it answered in (after auto-scope), its limits and what it used, how it ended (answered, direct, limit, fallback, stopped, error), tool results that read like instructions to an AI, how long it took, Lens's version, and tokens and cost from the ledger rows that name it. Questions keep how they were sent (web, api, voice, room, automation) and their options. The answer's id is taken once the question is saved and the answer runs in activity.scope(chat:<cid>, chat_message:<mid>), in the web chat, chat rooms and the automations' agent; the streamed answer holds the scope across its steps (activity.scoped). App completions keep no messages, so their record comes back in lens.record. The stream sends `meta` before `done`; GET /chats/{cid}/messages/{mid} returns one message with its record and ledger rows. Each tool step keeps its time and whether it failed. The web app shows it all from an i in the answer's header (a sheet on a phone); old answers say they weren't recorded. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * test(notes): keep the daily notes test from failing on 2026-10-17 The last check asked for 2026-10-17's note after the call without a date had made today's note, so on that day it found the note the deleted root had left behind. It now asks for a day no earlier call makes. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * feat(chat): choose tools, a tool-call limit and a scope per answer Group the assistant's tools (GET /chats/tools lists the groups and tools a person has, what each does and why a group is missing), offer an answer only the tools picked (an admin's switch still wins), stop at a tool-call limit up to the new ai.max_tool_calls setting, and narrow one answer to its own namespaces. A conversation keeps its choice and new ones start with the last. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * docs(chat): choosing tools, namespaces and a limit; regenerate the client Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * feat(chat): a choice made as a conversation starts is the latest choice Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * fix(chat): setting the server up keeps every tool, whatever the latest choice Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * test(entities): wait for the typed search before counting merge options The find box empties while the list for what was typed loads, so on a busy runner the first list could pass the wait and then vanish. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * test(settings): the AI section's server values include ai.max_tool_calls Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * fix(chat): find_resources belongs to the archive's tools Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * docs(chat): a new built-in tool joins a tool group Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * fix(ci): the upgrade check counts entities of every type Ported from #512 so this PR's upgrade check passes while that lands: the entity-types step re-types weekday Terms as Dates, which the default entity list leaves out, so the check read them as gone. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * feat(chat): deep research, a plan to approve and a cited report A goal (/research, research: true, POST /chats/{cid}/research, the assistant's and MCP's start_research) gets one planning call: follow-up questions and a plan with a labelled estimate, waiting as an approval of the assistant's (tool research). Approved in the web app, the inbox or with a yes in a chat room (an API key or an app only declines, unless research.agents_skip_review), it runs in the background: claimed by one process with a heartbeat, resumed from the last finished stage, one run per person, within its tool calls, research.max_minutes and budgets, stoppable. Gather uses only the plan's sources' read tools; write and check renumber citations and rewrite or mark unsupported claims. The report saves as a note (chat links) or makes a podcast. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B --------- Co-authored-by: Adeel Ahmad <noreply@anthropic.com>
adeelahmad
added a commit
that referenced
this pull request
Oct 18, 2026
* feat(automations): more operators for conditions Match trees gain in, not_in, starts_with, ends_with, matches, between, before, after, within, weekday, time_between and changed. Time and state come from env (now, timezone, state), never from globals. Patterns are refused when they could backtrack without end, read at most 20,000 characters and give up after 50 ms (the regex module's timeout). changed keeps the last value seen per automation, trigger and key in a new automation_state table, tidied hourly. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AjJqXgjj1cNdKGRQbX5frb * fix(automations): drop an automation's oldest state first, to the microsecond Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AjJqXgjj1cNdKGRQbX5frb * docs(automations): list the condition operators as built, with their checks Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AjJqXgjj1cNdKGRQbX5frb * fix(ci): the upgrade check counts entities of every type Ported from #512 so this PR's upgrade check passes while that lands: the entity-types step re-types weekday Terms as Dates, which the default entity list leaves out, so the check read them as gone. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AjJqXgjj1cNdKGRQbX5frb --------- Co-authored-by: Adeel Ahmad <noreply@anthropic.com>
adeelahmad
added a commit
that referenced
this pull request
Oct 18, 2026
…p, with ready-made MCP servers (#491) * feat(assistant): turn the MCP runner and a browser on from the web app, with ready-made MCP servers The host upgrade agent's services action now takes a profile (mcp, browser or monitoring, a fixed list) and turn=on|off, so the web app, the API (GET /admin/services, PUT /admin/services/{profile}) and the MCP tools services and set_service can start or stop any of Lens's optional containers; the old monitoring=on|off request still works. The new browser profile runs Playwright MCP in a hardened container on an internal network whose only way out is browser-proxy, netguard run on its own (public addresses, ports 80 and 443, a byte budget per connection). Add MCP server gains Ready-made: Browser (one click once its container answers, browser_run_code_unsafe off) and GitHub (a field for the token). ${NAME} values get their own fields, and a spec with keep: true reuses one MCP session between calls. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * test(sources): give the routing rules preview time to show on a busy machine The preview waits 600 ms after the last keystroke, and findByText gives up after 1 s, so the test failed when the machine was busy. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * fix(browser): give the browser's home in memory to the user it runs as The tmpfs at /home/node was root's, so Playwright couldn't make its profile there and every navigation failed with EACCES. Mount it with node's uid and gid (1000), in both compose files. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * fix(ci): the upgrade check counts entities of every type Ported from #512 so this PR's upgrade check passes while that lands: the entity-types step re-types weekday Terms as Dates, which the default entity list leaves out, so the check read them as gone. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B --------- Co-authored-by: Adeel Ahmad <noreply@anthropic.com>
adeelahmad
added a commit
that referenced
this pull request
Oct 18, 2026
…a live progress card (#517) * fix(assistant): let the assistant's tools be imported first Importing app.domain.ai_tools on its own failed: it imported automations, which loads the actions, and the agent's action subclasses Toolbox before ai_tools had defined it. Running one test file (tests/api/test_chats.py) hit it. ai_tools now imports automations last. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * feat(chat): each answer records what produced it Every answer keeps `meta`: the model and the host name of its server, the tools offered and asked for, the scope it answered in (after auto-scope), its limits and what it used, how it ended (answered, direct, limit, fallback, stopped, error), tool results that read like instructions to an AI, how long it took, Lens's version, and tokens and cost from the ledger rows that name it. Questions keep how they were sent (web, api, voice, room, automation) and their options. The answer's id is taken once the question is saved and the answer runs in activity.scope(chat:<cid>, chat_message:<mid>), in the web chat, chat rooms and the automations' agent; the streamed answer holds the scope across its steps (activity.scoped). App completions keep no messages, so their record comes back in lens.record. The stream sends `meta` before `done`; GET /chats/{cid}/messages/{mid} returns one message with its record and ledger rows. Each tool step keeps its time and whether it failed. The web app shows it all from an i in the answer's header (a sheet on a phone); old answers say they weren't recorded. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * test(notes): keep the daily notes test from failing on 2026-10-17 The last check asked for 2026-10-17's note after the call without a date had made today's note, so on that day it found the note the deleted root had left behind. It now asks for a day no earlier call makes. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * feat(chat): choose tools, a tool-call limit and a scope per answer Group the assistant's tools (GET /chats/tools lists the groups and tools a person has, what each does and why a group is missing), offer an answer only the tools picked (an admin's switch still wins), stop at a tool-call limit up to the new ai.max_tool_calls setting, and narrow one answer to its own namespaces. A conversation keeps its choice and new ones start with the last. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * docs(chat): choosing tools, namespaces and a limit; regenerate the client Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * feat(chat): a choice made as a conversation starts is the latest choice Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * fix(chat): setting the server up keeps every tool, whatever the latest choice Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * test(entities): wait for the typed search before counting merge options The find box empties while the list for what was typed loads, so on a busy runner the first list could pass the wait and then vanish. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * test(settings): the AI section's server values include ai.max_tool_calls Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * fix(chat): find_resources belongs to the archive's tools Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * docs(chat): a new built-in tool joins a tool group Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * fix(ci): the upgrade check counts entities of every type Ported from #512 so this PR's upgrade check passes while that lands: the entity-types step re-types weekday Terms as Dates, which the default entity list leaves out, so the check read them as gone. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * feat(chat): deep research, a plan to approve and a cited report A goal (/research, research: true, POST /chats/{cid}/research, the assistant's and MCP's start_research) gets one planning call: follow-up questions and a plan with a labelled estimate, waiting as an approval of the assistant's (tool research). Approved in the web app, the inbox or with a yes in a chat room (an API key or an app only declines, unless research.agents_skip_review), it runs in the background: claimed by one process with a heartbeat, resumed from the last finished stage, one run per person, within its tool calls, research.max_minutes and budgets, stoppable. Gather uses only the plan's sources' read tools; write and check renumber citations and rewrite or mark unsupported claims. The report saves as a note (chat links) or makes a podcast. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B * feat(chat): deep research in the web app, a plan card to approve and a live progress card The composer's Deep research switch (and /research) sends a goal; its answer is a plan card: the follow-up questions with answers to tap, the sub-questions to reword, add or remove, where it looks, a tool-call stepper with the estimate, and Enter approves it (or revises it once a question is answered), with Decline. Approved, it becomes a progress card read from GET /research/{id}, so it survives a reload: stage, sub-questions ticked off, sources, tool calls, cost and minutes, Go on anyway when a budget holds it, and Stop. The report saves as a note (picking the namespace when there are several), reads aloud, makes a podcast or exports as Markdown. Notes open chat: links, and Settings > AI assistant > Deep research holds the research limits. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HXPWXcSCQb9hWPr7xkZu7B --------- Co-authored-by: Adeel Ahmad <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Requested by Adeel · project thread
Description
Before: since #395 merged, the Upgrade check fails on every pull request that changes the backend ("entities: Friday, Monday gone"). #395's entity-types upgrade step retypes Terms such as Monday as Dates, and
GET /entitiesleaves Dates and Numbers out unless asked for, so the check read them as lost.After: the check also lists the quiet types (
types=DATE,NUMBER), so an entity may change type in an upgrade but none may go. v0.13.0 hides the same quiet types, so the before and after lists are built the same way.Motivation and Context
Unblocks the Upgrade check on every open backend PR. The same commit is in #408 (9c46640, verified locally there); split out so it lands without waiting on #408's conflicts.
Types of changes
Checklist:
pre-commit run --files ci/upgrade/lens_upgrade.pypasses).Done questions (AGENTS.md)
typesfilter ofGET /entities.Generated by Claude Code