ysyneu · Oct 31, 2026 · Oct 31, 2026 · Oct 31, 2026 · Oct 31, 2026 · Oct 31, 2026
diff --git a/docs.json b/docs.json
@@ -1503,6 +1503,10 @@
       "source": "/en/rum/error-tracking/erro-reporting/web",
       "destination": "/en/rum/error-tracking/error-reporting/web"
     },
+    {
+      "source": "/en/rum/quickstart/faq",
+      "destination": "/en/rum/sdk/web/faq"
+    },
     {
       "source": "/account/info",
       "destination": "/zh/api-reference/platform/account/account-read-info"

diff --git a/en/ai-sre/im.mdx b/en/ai-sre/im.mdx
@@ -5,7 +5,7 @@ keywords: ["AI SRE", "IM", "Slack", "Lark", "DingTalk", "WeCom", "war room", "@m
 sidebarTitle: IM platform
 ---
 
-> Activate AI SRE separately; it does not require an On-call subscription or a member license. Every plan can create IM applications for AI conversations. Using an application for On-call notifications, including escalation policies and on-call reminders, still requires an active On-call Professional plan.
+> Activate AI SRE separately; it does not require an On-call subscription or a member license. Every plan can create IM applications for AI conversations. Using an application for On-call notifications, including escalation policies and on-call reminders, still requires an active On-call Pro plan.
 
 ## Overview
 
@@ -49,10 +49,10 @@ IM interaction requires that you have already connected the corresponding platfo
 
 ## AI SRE settings in IM integrations
 
-Open the corresponding IM integration under **On-call → Integration Center → Integration List → Instant Messaging** and configure its AI SRE behavior under **Enhanced features**. Of the three switches below, the first two are on by default and the last one is off by default:
+Open the corresponding IM integration under **On-call → Integration Center → Integration List → Instant Messaging** and configure its AI SRE behavior under **Advanced Features**. Of the three switches below, the first two are on by default and the last one is off by default:
 
 - **Allow AI SRE conversations in IM**: available without enabling War Room. It controls both entry points — **group @mentions** and **direct chats with the bot**; in Slack it also controls the `/fd` command. Turning it off makes group @mentions and direct chats with the bot (and, in Slack, `/fd`) silent. In WeCom's Third-party App mode, only direct chats with the bot are available; group @mentions require Custom App Integration mode.
-- **Use thread replies in normal group chats**: available only for Feishu/Lark and Slack. When enabled, each normal-group thread has an independent session; War Rooms still receive replies directly in the group.
+- **AI SRE uses thread replies in regular group chats**: available only for Feishu/Lark and Slack. When enabled, each normal-group thread has an independent session; War Rooms still receive replies directly in the group.
 - **Allow AI to reply proactively**: available only on Slack, Lark / Feishu and Microsoft Teams; DingTalk and WeCom have no such switch. When enabled, AI reads messages in the connected group chats that **do not mention it** and replies only when it judges a reply worthwhile; @mentions always get a reply. A message it reads but judges not worth answering gets neither a receipt nor a reply. Each group can opt out with `/ambient off` (see [/ambient command](#ambient-command)).
 
 <Note>
@@ -76,7 +76,7 @@ In a connected IM group with **Allow AI SRE conversations in IM** on, **@mention
 </Steps>
 
 <Tip>
-The **reply mode** is configurable (off / first / all), controlling whether AI SRE @mentions the person who asked, and whether it replies **in-thread** or in the main channel. In a busy large group, in-thread replies keep the investigation discussion focused without flooding the channel.
+In normal group chats on Feishu / Lark and Slack, whether AI SRE replies inside the thread is set by **AI SRE uses thread replies in regular group chats** under **Advanced Features** of the IM integration (on by default). In a busy large group, enabling it gives each thread its own session, so the investigation discussion stays focused without flooding the channel.
 </Tip>
 
 ### Attachments and images
@@ -98,22 +98,10 @@ Per turn, the attachment quota is counted by type. The current message's attachm
 
 ### Processing receipt
 
-Once the bot has your message, it first puts an emoji reaction on **the message you sent**, as an immediate "received, working on it" signal. The emoji is picked at random from a small set for each platform:
-
-| Platform | Emoji |
-| --- | --- |
-| Slack | eyes, hourglass_flowing_sand |
-| Lark / Feishu | Typing, OneSecond |
-| DingTalk | Platform built-in emotions: 专注, 忙疯了 |
-
-On Slack this sits alongside a native "is working on it" status, which the bot also shows.
-
-The reaction is removed once the answer is delivered.
+Once the bot has your message, it puts an emoji reaction on **the message you sent** as a "received, working on it" signal (WeCom has no emoji API, so it posts a placeholder message that the task checklist card and the final answer then replace in place). The reaction is removed once the answer is delivered. Slack also shows a native "is working on it" status.
 
 With **Allow AI to reply proactively** on, a receipt is added only to the message AI decides to answer: a message it read but judged not worth answering gets neither a receipt nor a reply.
 
-WeCom has no emoji API, so its "processing" receipt is a placeholder message, such as a random "On it…". The task checklist card and the final answer then replace it in place.
-
 ### How a reply reaches the chat
 
 Once you hand AI SRE an investigation, every message that appears in the group is one of two kinds:
@@ -187,7 +175,15 @@ On the automation channel, nobody is watching and no reply will arrive. The agen
 
 ## In-session switch commands
 
-IM sessions have no picker UI like the console. Instead, three slash commands let you adjust session bindings and proactive replies **mid-conversation**. Console sessions don't support these commands: their environment and team bindings are fixed at creation, and proactive replies are configured only in IM groups.
+IM sessions have no picker UI like the console. Instead, slash commands let you adjust session bindings and proactive replies **mid-conversation**. Console sessions don't support these commands: their environment and team bindings are fixed at creation, and proactive replies are configured only in IM groups. On Slack, write a command as `/fd <command>`, for example `/fd stop`.
+
+| Command | What it does |
+| --- | --- |
+| `/new [message]` | Starts a fresh conversation and resets the context; with a message, starts from it. Not available in groups with thread replies on; open a new top-level @mention instead |
+| `/stop` | Stops the current analysis |
+| `/help` | Lists the commands |
+
+The next three switch bindings and proactive replies.
 
 ### /env — Switch Runner environment
 
@@ -260,7 +256,7 @@ Once an AI SRE reply lands in a group chat, anyone in the group can rate it —
 Whether you start a session from IM or the console, it's **the same AI SRE**. It handles messages one at a time and streams output. It compacts context automatically in long conversations and supports optional team and environment bindings. The only difference is the entry point —
 
 - **Console**: ask questions one at a time in the **Chat** workspace and view the full tool-call and sub-session panels. Environment and team bindings are fixed at creation and cannot be changed.
-- **IM**: @mention it in the group where your team already works; findings are posted back to the thread. Use `/env` and `/scope` to switch bindings mid-conversation, and `/ambient` to control whether the group gets proactive replies. Great for grabbing a quick analysis at the incident scene, then diving deeper in the console.
+- **IM**: @mention it in the group where your team already works; findings are posted back to the thread. Use `/env` and `/scope` to switch bindings mid-conversation, `/ambient` to control whether the group gets proactive replies, and `/stop` to stop the current analysis at any time. Great for grabbing a quick analysis at the incident scene, then diving deeper in the console.
 
 For more about sessions, see [Conversations](/en/ai-sre/sessions).
 

diff --git a/en/ai-sre/knowledge.mdx b/en/ai-sre/knowledge.mdx
@@ -55,7 +55,7 @@ After reading `DUTY.md`, the agent decides which `@references` to expand based o
 | Constraint | Value | Notes |
 | --- | --- | --- |
 | File content | Plain text (UTF-8) | Validated by **content**, not extension: a file saves as long as it contains no NUL bytes and decodes as valid UTF-8. So `.py`, `.sql`, and even an extension-less `Dockerfile` can be uploaded alongside `.md` `.yaml` `.json` `.txt` `.sh`; conversely, a file with a `.txt` extension but binary content is rejected |
-| Per-file size limit | 1 MiB | Files exceeding this cannot be saved |
+| Per-file size limit | 1 MiB; 32 KB for `DUTY.md` | Files exceeding this cannot be saved. `DUTY.md` is loaded into the context in full on every turn, so its limit is smaller; move detail into other files |
 | Per-knowledge size limit | 5 MiB | The usage bar in the console reflects this quota |
 | File count limit | 100 | No new files can be added once the limit is reached |
 | Subdirectories | Allowed | Paths may contain `/` (for example, `runbooks/api-5xx.md`); path segments cannot start with `.` |

diff --git a/en/ai-sre/overview.mdx b/en/ai-sre/overview.mdx
@@ -76,7 +76,7 @@ After closing:
 
 Billing and gift-credit periods run in consecutive 30-day windows from the first AI SRE activation. Disabling and re-enabling the service does not reset the period or grant that period’s gift credits again. Existing accounts retain their current period and continue with independent 30-day periods when it ends.
 
-IM applications can be created, authorized, and enabled on every plan for AI SRE direct or group conversations. Using an application as an On-call notification target, including escalation policies and on-call reminders, still requires an active On-call Professional plan. Otherwise, selection is disabled, the server rejects the configuration, and restricted notifications from existing configurations are not sent. On-call expiry or downgrade does not interrupt AI SRE conversations.
+IM applications can be created, authorized, and enabled on every plan for AI SRE direct or group conversations. Using an application as an On-call notification target, including escalation policies and on-call reminders, still requires an active On-call Pro plan. Otherwise, selection is disabled, the server rejects the configuration, and restricted notifications from existing configurations are not sent. On-call expiry or downgrade does not interrupt AI SRE conversations.
 
 On-call actions such as acknowledging or resolving an incident retain their existing permission and license requirements. AI SRE analysis does not grant additional incident-management permissions.
 

diff --git a/en/ai-sre/sessions.mdx b/en/ai-sre/sessions.mdx
@@ -286,19 +286,7 @@ As a conversation grows, AI SRE automatically summarizes older history while kee
 
 Progress is shown while compacting; afterwards the **Context** percentage in the chat header drops (hover for token usage).
 
-A summary paraphrases the conversation, but the text before it is not lost: the messages and tool results it replaced are still stored exactly as they were returned. When an investigation depends on an exact value (an ID, a host, a metric value, a threshold, a log line, the text of an error, a command), the agent calls the built-in `session_transcript` tool to write that text into the `.history/<session_id>/` directory of its execution environment, then searches it with `grep` / `read` instead of repeating the summary's wording. If the value really is not there, it says so plainly rather than guessing.
-
-| File | Content |
-| --- | --- |
-| `seg_NNN.md` | The text replaced by the Nth summary |
-| `tail.md` | Everything after the latest summary (always present, may be empty) |
-| `index.md` | How many rows each file covers and its time span |
-
-What gets recorded is **what the agent was given at the time**: images and attachments leave only an `[inline …]` / `[file …]` placeholder, a truncated result keeps only the `file_path` of its full output, and a Subagent's internal steps stay in its own session rather than in these files.
-
-<Note>
-This recall only works for agents that **have the tool**: the main session and a Subagent with full tools can use it, while a restricted Subagent such as a read-only one does not have the tool and can only go by the summary after compaction.
-</Note>
+Compaction only replaces what is sent to the model; the original messages and tool results stay stored. When an investigation depends on an exact value (an ID, a host, a metric value, a threshold, a log line, the text of an error, a command), the agent looks the original text up instead of repeating the summary's wording; if the value really is not there, it says so plainly rather than guessing. Images and attachments leave only a placeholder with no original text, and a truncated large output keeps only the file path of its full result.
 
 ## Choosing a runtime environment
 

diff --git a/en/developer/cli.mdx b/en/developer/cli.mdx
@@ -41,7 +41,6 @@ Read the latest version from the [CDN latest version pointer](https://static.fla
 | `FLASHDUTY_VERSION` | Install a specific version, for example, `v1.5.12` | latest |
 | `FLASHDUTY_INSTALL_DIR` | Custom install directory | the directory of the `flashduty` already on `PATH`, else `/usr/local/bin` (shell); `~\.flashduty\bin` (PowerShell) |
 | `MIRROR_URL` | Override the release asset download mirror prefix used by the installer script; must use `https://` | `https://static.flashcat.cloud/flashduty-cli` |
-| `FLASHDUTY_UPDATE_BASE_URL` | Override the base URL used by `flashduty update` and the automatic update check | `https://static.flashcat.cloud/flashduty-cli` |
 | `INSTALLED_NAME` | Command name to install as, for example, `fduty` | `flashduty` |
 
 A copy installed under another command name uses that name in help output, error messages, and shell completion scripts; `flashduty update` replaces the running binary in place, under its own name and directory, instead of installing a default-named copy elsewhere.
@@ -501,7 +500,7 @@ flashduty rum resource-info [--no-cache]   # View the RUM plan version, quotas,
 flashduty oncall license-list # List people with active On-call licenses in the current account
 ```
 
-This read-only command returns each person's ID, name, and license type: `fixed` is explicitly assigned, while `temporary` is active for the current temporary-license window. The response also carries `release_limited`, which is `true` once the account has used up its license-release quota for the current billing period; while it is `true`, releasing a member's seat fails with the error code `NoLicense`. That quota is the [limit on the number of License releases in each billing period](/en/platform/pricing).
+This read-only command returns each person's ID, name, and license type: `fixed` is explicitly assigned, while `temporary` is active for the current temporary-license window.
 
 ### calendar — Service calendars
 
@@ -694,7 +693,7 @@ Panel runtime and variable resolution take their time window and variable select
 
 #### `prometheus-api-v1-label-{label_name}-values` — Query Prometheus label values
 
-`GET /monit/prometheus/api/v1/label/{label_name}/values` (operationId `monit-prometheus-read-label-values`) carries a path parameter, so it is excluded from code generation and provided by a hand-written command. The command name is derived from the API path: the `monit` group plus the remaining path segments joined by hyphens. It appears under `flashduty monit --help` but is hard to guess, so use it as written here:
+Lists every value of a label on a Prometheus-compatible data source. The command is named `monit prometheus-api-v1-label-{label_name}-values` (visible under `flashduty monit --help`); use it as written here:
 
 ```bash
 flashduty monit prometheus-api-v1-label-{label_name}-values <label_name> --data-source-id <datasource-id>
@@ -960,7 +959,7 @@ inc_def456   High memory usage        Warning    Processing   Staging       2026
 Showing 2 results (page 1, total 2).
 ```
 
-A generated command's list response that carries fields beyond the row array (`items` / `docs` / `list`) — for example `calendar event-list`'s `days` or `oncall license-list`'s `release_limited` — prints an extra line after the row table: `Also in the response: <fields> (use --json to see it).` Those fields never appear in the table; use `--json` or `--output-format toon` to read them.
+A generated command's list response that carries fields beyond the row array (`items` / `docs` / `list`) (for example `calendar event-list`'s `days`) prints an extra line after the row table: `Also in the response: <fields> (use --json to see it).` Those fields never appear in the table; use `--json` or `--output-format toon` to read them.
 </Tab>
 
 <Tab title="JSON (--json / --output-format json)">
@@ -1036,11 +1035,7 @@ For example, export only an incident ID, title, and progress:
 flashduty incident list --json --fields incident_id,title,progress
 ```
 
-When a list projection (`incident list`, `incident similar`, `alert-event list`, `channel escalate-rule-list`, `insight incidents`) exceeds its 16 KiB limit, the CLI handles it in three tiers, with every note going to stderr and stdout left untouched:
-
-1. **Whole page overflows**: only the leading rows that fit are emitted, with values intact. A stderr note reports how many rows were emitted. Narrow `--fields` or lower `--limit` to fit more rows per page.
-2. **A single row overflows the budget**: that row's string values are shortened and end with `...`, and a stderr note names the clipped fields. Matching or filtering on a shortened field misses, so narrow `--fields` or `--limit` to get full values. Identifier fields (keys ending in `_id` or `_key`) are never shortened at any tier.
-3. **A row cannot be reduced enough to fit**: the command fails with an error naming the largest fields (up to 3, with their byte sizes); reduce the fields in `--fields` or lower `--limit` and retry.
+When a list projection (`incident list`, `incident similar`, `alert-event list`, `channel escalate-rule-list`, `insight incidents`) exceeds its 16 KiB limit, the three-tier reduction is the same as in "Generated-command output bound" above, with every note going to stderr and stdout left untouched. The difference is that you narrow the output with `--fields` or `--limit` to fit more rows per page or to get full values. Matching or filtering on a shortened field misses; identifier fields (keys ending in `_id` or `_key`) are never shortened at any tier.
 
 `incident detail` behaves differently when its projection overflows: the detail is a single object, and a truncated value is indistinguishable from a genuinely short one, so silently shortening it would hand you wrong data. A projection over 8 KiB therefore fails the command outright, and the error names the largest fields (up to 3, with their byte sizes). Reduce the fields in `--fields`, or omit `--fields` entirely to get the full detail, which is not subject to the projection limit.