fix(chat): link a person's own profile editor instead of attempting an agent write (#19943)

## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work
> - People talk to their agents in chat. The chat guidance tells the
agent which links to give back.
> - A person can ask the agent to change their own display name. Only
the person can do this, in their profile settings.
> - The chat guidance did not say where that page is. The agent searched
the API and tried the human-only profile endpoint. The product correctly
refused it. The reply then gave only vague "profile/account settings"
directions.
> - This pull request tells chat where the personal profile editor is,
and that agent credentials cannot change a person's profile.
> - The benefit is a reply with a link that the person can open to make
the change.

## Linked Issues or Issue Description

**What happened**
In chat, a person wrote "Change my display name to Alex Chen." The agent
spent about four minutes on API searches. It tried `PATCH
/api/auth/profile`, and the product refused it. The reply told the
person to use their "profile/account settings" but gave no link.

**Expected behavior**
The agent does not try to change the person's profile. It links the
person's profile editor at
`/<prefix>/company/settings/instance/profile`, so the person can change
the name.

**Steps to reproduce**
1. Sign in as a person in an authenticated deployment.
2. Open chat with the CEO agent.
3. Send "Change my display name to Alex Chen."
4. See that the reply has no link to the profile editor.

## What Changed

- `server/src/services/agent-conversations.ts`: the chat directive now
says that a person's own name and avatar change only in their profile
settings at `/<prefix>/company/settings/instance/profile`. It says that
agent credentials cannot edit a person's profile, and that renaming an
agent, member record or company does not change it. The agent links that
page instead of trying the change.
- `server/src/__tests__/agent-conversations.test.ts`: a regression test
checks the directive and the built chat prompt.

## Verification

- `cd server && pnpm exec vitest run
src/__tests__/agent-conversations.test.ts -t "chat prompt policy"`: 10
passed.
- The chat eval case `navigation-preferences.edit-profile` checks this
end to end. It requires a link to the profile editor, and the person
follows that link to save the new name.

## Risks

- Low risk. This is a guidance change only. It adds no permission and
changes no route.
- Deployments that hide the Profile settings page get a link to a hidden
page. The page gate still applies.

## Model Used

- Anthropic Claude Opus 5.5 (`claude-opus-5-5`), with tool use and code
execution.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

server/src/__tests__/agent-conversations.test.ts

@@ -1028,6 +1028,13 @@ describe("chat prompt policy", () => {
     expect(prompt).toContain("/<prefix>/agents/<agentId>/runs/<runId>");
   });
 
+  it("routes a person's own profile change to their profile settings instead of an agent write", () => {
+    expect(AGENT_CHAT_DIRECTIVE).toContain("only they can change them in their profile settings at /<prefix>/company/settings/instance/profile");
+    expect(AGENT_CHAT_DIRECTIVE).toContain("link that page instead of attempting the change");
+    const prompt = buildPaperclipTaskMarkdown({ issue: { id: "chat", identifier: null, title: "Chat", workMode: "ask", conversationAgentId: "agent" } });
+    expect(prompt).toContain("/<prefix>/company/settings/instance/profile");
+  });
+
   it("gives chat replies a usable route for both task and approval sources", () => {
     expect(AGENT_CHAT_DIRECTIVE).toContain("/<prefix>/issues/<identifier>");
     expect(AGENT_CHAT_DIRECTIVE).toContain("For approval links, use /<prefix>/approvals/<approvalId>");

server/src/services/agent-conversations.ts

@@ -114,6 +114,8 @@ For task links, use the company-prefixed relative path /<prefix>/issues/<identif
 
 When a reply concerns a specific agent, such as one you paused, resumed, configured, or reported on, link its profile at /<prefix>/agents/<urlKey or id> using the agent's returned urlKey or id. A profile link is not a mention: use agent:// only when you intend to notify that agent.
 
+A person's own display name and avatar belong to their account, and only they can change them in their profile settings at /<prefix>/company/settings/instance/profile. Agent credentials cannot edit a person's profile, and renaming an agent, a member record or the company does not change it. When the person asks to change their own name or avatar, link that page instead of attempting the change.
+
 For status updates, distinguish recorded task status from active execution and verified progress. Read the latest relevant comments and run outcome before explaining a blocker or claiming work is underway. Use the advertised API tools for another task's details when needed. A completed dependency does not prove a block is stale; report the assignee's recorded reason. Agent configuration may be redacted: an empty configuration object without configuration-read permission does not prove settings are disabled or at their defaults. If the evidence is unavailable, say what you could verify and what remains unknown rather than guessing or recommending a status change.
 
 Keep discussion here and leave the conversation available for the next message. Link handed-off tasks in your reply; do not make this conversation blocked by their completion or wait for them. Paperclip will bring completed handed-off tasks back as a new input here so you can explain the result and link it without another user message. After creating an assigned task, let its own run execute the work; do not create its deliverables or change its execution status from this chat. Reply normally and end your turn; Paperclip manages the conversation waiting state. Do not change its status, create a review confirmation just to finish a reply, mark it complete, or poll for another reply. An accepted plan authorizes handoff to execution tasks, never implementation on this conversation. Honor normal approvals. Ask mode is non-mutating. Plan mode supports research and writing/revising the plan; hand off for execution only through the normal authorized workflow.`;