Extend load_user_commands() to scan workspace-local command directories
in addition to the global ~/.deepseek/commands/. Precedence model
mirrors skills_directories(): project-local shadows global by name.

Scanned directories (in precedence order):
  1. <workspace>/.deepseek/commands/
  2. <workspace>/.claude/commands/   (Claude Code interop)
  3. <workspace>/.cursor/commands/   (Cursor interop)
  4. ~/.deepseek/commands/           (user-global fallback)

Workspace context threaded through:
  - try_dispatch_user_command (has App reference)
  - user_commands_matching (new workspace parameter)
  - all_command_names_matching (new workspace parameter)
  - slash_completion_hints (new workspace parameter)

Closes Hmbown#1259

Files inside .deepseek/, .cursor/, .claude/, and .agents/ were invisible
to @-mention Tab-completion when those directories were listed in
.gitignore (the common case). The walk_for_completions and
build_file_index paths now walk these directories separately with
gitignore disabled, merging results into the main candidate list.

Also excludes .deepseek/snapshots/ from the dot-dir walk so the snapshot
side repo (which can reach hundreds of GB, see Hmbown#1112) is never indexed.

The fix applies to:
  - @-mention Tab-completion (walk_for_completions)
  - Fuzzy file resolution (build_file_index)
  - Ctrl+P file picker (collect_candidates)

…mbown#1250, Hmbown#1256)

MCP servers are allowed by spec to paginate list responses. The old
implementation made a single request and stopped, silently dropping
subsequent pages. Servers that paginate at fewer items than their
total tool count (e.g. gbrain at 5 per page) would appear to expose
only those first few tools.

All four discovery methods now follow nextCursor until the server
signals no more pages, accumulating results across all pages:
  - discover_tools
  - discover_resources
  - discover_resource_templates
  - discover_prompts

Thanks to Liu-Vince for the original diagnosis and fix (PR Hmbown#1256).

Adds a disk-space guard before each snapshot: if the snapshot directory
exceeds MAX_SNAPSHOT_SIZE_MB (500 MB), the oldest snapshots are pruned
aggressively to stay under PRUNE_TARGET_MB (400 MB). If pruning cannot
get under the limit, the history is wiped so the next snapshot starts
fresh.

The guard runs in snapshot() before git add/write-tree/commit-tree so
disk pressure is relieved BEFORE taking another snapshot.

Includes dir_size_mb() helper and regression tests.

Thanks to Giggitycountless for the original max_size_mb proposal
(PR Hmbown#1131).

Hmbown#1118, Hmbown#1129)

Adds a directive to the ## Language section telling the model that
project context (AGENTS.md, auto-generated instructions, file trees,
skill descriptions) is NOT a language signal. Chinese filenames in a
repo should not bias the model toward Chinese replies when the user
writes in English.

Previously clear_todos() only cleared the plan_state — the SharedTodoList
was never touched. Now it clears both: the todo list (via try_lock on
self.todos) and the plan state. The caller in commands/core.rs already
called clear_todos() on /clear; it just had nothing to clear.

Version bump: 0.8.23 → 0.8.24 in workspace Cargo.toml.

CHANGELOG entries for:
  - Workspace-local slash commands (Hmbown#1259)
  - @-completion for gitignored dot-dirs
  - MCP paginated discovery via nextCursor (Hmbown#1250, Hmbown#1256, credit Liu-Vince)
  - Snapshot disk-space cap at 500 MB (Hmbown#1112, credit Giggitycountless)
  - /clear resets Todos sidebar (Hmbown#1258)
  - Language directive strengthened against project-context bias
  - Known issue: Windows flicker (Hmbown#1260, Hmbown#1251) — viewport-reset escape
    sequence on Windows conhost, investigation in progress

…tion (Hmbown#1196)

Merge of PR Hmbown#1196 by wplll. Adds:

Cache-aware prompt layering:
  - PromptBuilder struct separates prompt construction from inspection
  - System prompt split into named layers with stability classification
  - Layers classified as static/history/dynamic for cache debugging

/cache inspect command:
  - SHA-256 hashes of each rendered prompt layer
  - Base static prefix hash vs full request prefix hash
  - Static prefix stability status across turns
  - First-divergence tracking from previous request

Wire payload optimization:
  - Tool result budget: large outputs compacted before API request
  - Tool result dedup: repeated outputs replaced by compact refs
  - Turn metadata dedup: repeated <turn_meta> blocks deduplicated
  - Wire-only: local session messages remain unchanged

Project context pack:
  - Deterministic workspace summary injected into stable prefix
  - Configurable via [context] project_pack = false

Cache warmup and improved footer cache display.
Thanks to wplll for the contribution.

中止 implies a temporary pause that can be resumed; 终止 means a
definitive end, which matches the English "Abort the turn" / "abort"
semantics of this action.

Update both the option label ("终止本轮") and the Esc key footer hint
("Esc：终止") in the approval/elevation widget.

Fixes Hmbown#1273

Pre-existing gap exposed during v0.8.24 testing: when the user clicks
away (Cmd+Tab, opens the screenshot tool, etc.) and clicks back, some
terminals drop the application's mouse-tracking mode. The
\`FocusGained\` handler at \`ui.rs::1599\` already re-pushed keyboard
enhancement flags to recover IME state — extend the same recovery to
\`EnableMouseCapture\` so wheel scroll keeps working after a focus
round-trip. Gated on \`app.use_mouse_capture\` so explicit
\`--no-mouse-capture\` users aren't re-enabled against their will.

…fault

CHANGELOG additions:
- Top-line credit summary: wplll, Liu-Vince, Giggitycountless,
  SamhandsomeLee, barjatiyasaurabh, tyculw, hongyuatcufe, ljlbit.
- New "Added" section properly documenting Hmbown#1196 (cache-aware
  diagnostics, /cache inspect, /cache warmup, payload optimization,
  Project Context Pack). Calls out that the Pack is default-on, adds
  ~1–10 KB to every prompt, and how to opt out via
  [context] project_pack = false.
- Per-item issue reporter credits across the Fixed section.
- Removed Hmbown#1129 from the i18n entry — that's a separate bug we did
  not actually fix (wrong env var name in HTTP system prompt).

README updates: rewrote the "What's New" section in both README.md
and README.zh-CN.md to v0.8.24 with all the same credits and the
project_pack opt-out note.

…ersion to 0.8.24

Bugfix + community PR release. See CHANGELOG.md for full notes.

  Size the config key column from the available setting keys so long keys like
  paste_burst_detection remain fully visible without pushing the value and scope
  columns out of alignment.

  Add a regression test covering long config keys and scope column alignment.

  Add direct POST-based MCP transport for Streamable HTTP servers while keeping
  the existing SSE endpoint-discovery path as a fallback. Parse both JSON and
  text/event-stream responses so servers like DeepWiki can be validated and used.

…mbown#1290)

Closes Hmbown#1288. Long setting keys like `paste_burst_detection` were pushing Value and Scope columns out of alignment because the layout used a fixed 19-char minimum. Now the key column width is computed from the actual rows (with 19 as a floor) and shared between the header and each row. Header divider widens accordingly. Tests added.

Thanks @reidliu41.

Closes Hmbown#1273. 中止 implies a temporarily-stoppable action; 终止 is the definitive 'end the turn' semantics that matches the English 'Abort the turn'. Updates two strings in the approval dialog (`option_abort` and the footer controls hint).

Thanks @Liu-Vince.

Closes Hmbown#1278. The docs page sets per-section `scroll-mt-32` (8rem) on each anchor section to clear the sticky nav, but the global `[id] { scroll-margin-top: 5rem }` rule loaded later with the same specificity, so 5rem won. Wrapping the global rule in `:where(...)` drops its specificity to 0, letting the page-level Tailwind utility win while still providing a fallback for anchors elsewhere on the site.

Thanks @Wenjunyun123.

…mbown#1300)

Closes Hmbown#1266 (DeepWiki at https://mcp.deepwiki.com/mcp). URL-based MCP servers now try the modern Streamable HTTP transport first — POST JSON-RPC to the base URL with `Accept: application/json, text/event-stream`, accept either JSON or SSE response — and fall back to the older SSE endpoint-discovery flow on incompatible status codes (404/405/406/415/501). Existing SSE servers keep working via the fallback. Single-file change in `crates/tui/src/mcp.rs` with a tokio-based end-to-end test that exercises the full handshake.

Thanks @reidliu41.