Honor low_motion in the default tool transcript path and align composer cursor padding with the rendered placeholder. Add focused regression tests for both behaviors.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix: address PR #4 follow-ups

Honor low_motion in the default tool transcript path and align composer cursor padding with the rendered placeholder. Add focused regression tests for both behaviors.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* lint: remove redundant imports in empty_state test, reuse create_test_app

The test had inner `use` statements for Config, App, TuiOptions, and
PathBuf that duplicated the module-level test imports. It also manually
constructed App instead of calling the existing create_test_app() helper.

* fix: replace useless format!("{text}") with text.to_string() in details_affordance_line

* test: pin composer_density in cursor test to avoid sensitivity to loaded settings

Settings::load() may return a non-default composer_density on some CI
environments. Explicitly set ComposerDensity::Comfortable so the
expected cursor position is deterministic across all platforms.

* fix: make tool low_motion test robust against coarse Windows timers

Use a 2× cycle offset so the animated frame index is 2 (maximally
distant from 0), giving 1800 ms of headroom before the animation could
wrap back to index 0. The previous 1× offset left only ~15 ms of
margin, causing flaky failures on Windows where Instant resolution is
approximately 15.6 ms.

* fix: correct headroom comment in tool animation test (3600ms, not 1800ms)

* fix: resolve lint, parity, and Windows test failures

- Fix rustfmt line-length issue in history.rs tool animation test
- Settings::path() now respects DEEPSEEK_CONFIG_PATH for Windows test compat
- doctor_check_mcp_server recognizes Unix-style absolute paths on Windows
- Use checked_sub for Instant arithmetic in web_run tests to prevent
  underflow on freshly-booted Windows CI runners

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: expand ~ in DEEPSEEK_CONFIG_PATH when resolving settings path

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

Keep legacy /normal and settings fallback behavior mapped to Agent, align docs around the three visible modes, and include the current TUI and onboarding refinements in this worktree.

* fix: address PR #4 follow-ups

Honor low_motion in the default tool transcript path and align composer cursor padding with the rendered placeholder. Add focused regression tests for both behaviors.


* lint: remove redundant imports in empty_state test, reuse create_test_app

The test had inner `use` statements for Config, App, TuiOptions, and
PathBuf that duplicated the module-level test imports. It also manually
constructed App instead of calling the existing create_test_app() helper.

* fix: replace useless format!("{text}") with text.to_string() in details_affordance_line

* test: pin composer_density in cursor test to avoid sensitivity to loaded settings

Settings::load() may return a non-default composer_density on some CI
environments. Explicitly set ComposerDensity::Comfortable so the
expected cursor position is deterministic across all platforms.

* fix: make tool low_motion test robust against coarse Windows timers

Use a 2× cycle offset so the animated frame index is 2 (maximally
distant from 0), giving 1800 ms of headroom before the animation could
wrap back to index 0. The previous 1× offset left only ~15 ms of
margin, causing flaky failures on Windows where Instant resolution is
approximately 15.6 ms.

* fix: correct headroom comment in tool animation test (3600ms, not 1800ms)

* fix: resolve lint, parity, and Windows test failures

- Fix rustfmt line-length issue in history.rs tool animation test
- Settings::path() now respects DEEPSEEK_CONFIG_PATH for Windows test compat
- doctor_check_mcp_server recognizes Unix-style absolute paths on Windows
- Use checked_sub for Instant arithmetic in web_run tests to prevent
  underflow on freshly-booted Windows CI runners


* fix: expand ~ in DEEPSEEK_CONFIG_PATH when resolving settings path

---------

- Wire 120 FPS FrameRateLimiter into run_event_loop via
  time_until_next_draw + mark_emitted
- Add low_motion support: 30 FPS cap via LOW_MOTION_MIN_FRAME_INTERVAL
- Add AdaptiveChunkingPolicy::set_low_motion() to force Smooth mode
- Add StreamingState::set_low_motion() to propagate to all block policies
- Tool spinner already freezes on first frame when low_motion is set

TODO_BACKEND.md §3, TODO_FIXES.md #4

* fix(pricing): extend V4 Pro 75% discount expiry to 2026-05-31 15:59 UTC

DeepSeek extended the promotional discount past the original 2026-05-05
cutoff. Without this update the TUI would have started showing 4× the
actual billed cost on May 6.

Source: https://api-docs.deepseek.com/quick_start/pricing — "extended
until 2026/05/31 15:59 UTC".

Adds a regression test pinning the new active window so a future revert
to the May 5 date trips the suite immediately.

Closes #267

* chore: remove stale TODO(integrate) markers from already-integrated modules

Five `// TODO(integrate)` comments and one matching "Not yet integrated"
note were misleading anyone grepping for integration work. Each module
is in fact wired up:

- execpolicy/mod.rs       → tools/shell.rs:1322 (load_default_policy)
- sandbox/mod.rs          → tools/shell.rs:28, main.rs:2647, tui/approval.rs:30
- sandbox/policy.rs       → main.rs:2752, tui/approval.rs:30 (SandboxPolicy)
- command_safety.rs       → tools/shell.rs:1321, tools/tasks.rs:13,
                            tools/approval_cache.rs:26
- tui/streaming/mod.rs    → tui/app.rs:38 (StreamingState)

The remaining TODO at mcp.rs:1771 covers a separate "wire legacy sync API
into CLI subcommands or remove" decision and is left in place.

Closes #266

* docs(release): add install + dual-binary template to GitHub Release page

Closes #265.

The Release page used the auto-generated commit-title body. New users
hitting the Release page from Twitter / npm-search had no on-page
guidance that the dispatcher (`deepseek`) and the TUI runtime
(`deepseek-tui`) ship as two binaries that must coexist; #258 was an
external user spending 11 minutes figuring this out and #272 was the
follow-on confusion.

The new body covers:
- npm wrapper as the recommended install
- `cargo install deepseek-tui-cli deepseek-tui --locked` (both crates)
- Manual download with a per-platform table showing both artifacts
- sha256 verify using the existing `deepseek-artifacts-sha256.txt`
- Changelog link

* feat(debug): add /cache command surfacing per-turn DeepSeek cache hit/miss

Step 1 of #263. Without per-turn telemetry the prefix-cache audit is
unfounded speculation; the rest of the issue's investigation steps
depend on this surface.

The DeepSeek API already returns `prompt_cache_hit_tokens` and
`prompt_cache_miss_tokens` per turn, and we already store the *latest*
on App. This adds a 50-turn ring (`turn_cache_history`) populated at
the same site as `last_prompt_cache_*_tokens`, plus a `/cache [count]`
slash command that renders a fixed-width table of the last N turns
with per-turn ratios and a session aggregate. Default count is 10;
larger values clamp to the ring size.

Edge cases the formatter handles:

- No telemetry yet → friendly "no turns recorded" message
- `cache_hit_tokens = None` (provider didn't report) → row renders all
  em-dashes and is excluded from session aggregates so one missing-
  telemetry turn can't make the average ratio look broken.
- `cache_hit_tokens = Some, cache_miss_tokens = None` → infer miss as
  `input − hit` and mark the cell with `*`. Footer documents the
  asterisk.
- Ring at cap (50) → push evicts oldest.

Tests cover all four paths plus the cap.

* test(prompts): add cache-prefix stability harness for #263 step 2

The DeepSeek prefix-cache only hits while the byte prefix of each
request matches the prior call. Anything in the cached prefix that
varies turn-to-turn for unchanged inputs is a cache buster.

Adds a focused harness next to the production surface so the property
is regression-guarded:

1. `first_divergence(a, b)` helper that returns the first divergent
   byte position with a `±32 byte` window of context, used by the
   custom assertion `assert_byte_identical`. Future suspect tests can
   reuse this to surface "where" rather than just "fail".

2. `compose_prompt_is_byte_stable_across_calls` — sweeps every
   (mode, personality) pair and pins that two consecutive calls
   produce identical bytes. Rules out suspect #4 (mode-prompt churn).

3. `system_prompt_for_mode_with_context_is_byte_stable_for_unchanged_workspace`
   — the call site `engine.rs::build_tool_context` actually invokes,
   pinned for an empty workspace across all three modes.

4. `system_prompt_with_working_set_summary_is_byte_stable_for_constant_summary`
   — pins that the surrounding prompt construction faithfully embeds
   the working_set summary it's given without injecting extra
   non-determinism. (The actual working_set summary stability lives
   in `working_set.rs` and is the next investigation target — see
   issue note in PR description.)

Foundation for the suspect-by-suspect bisection in the rest of #263.

* fix(secrets): never overwrite the secrets file when load_unlocked errors

`FileKeyringStore::set` and `delete` did
`self.load_unlocked().unwrap_or_default()`, which wiped every existing
secret if the read failed for any reason other than \"file is missing\":

- file mode != 0600 (`InsecurePermissions`) — easy on headless / CI
  environments where a permissive umask got applied
- corrupt JSON
- transient I/O error

In all of those, the next `store_unlocked` overwrote the file with an
empty-or-single-entry blob and reset perms to 0600, silently losing
every other provider's key.

Switch both call sites to `?`. `load_unlocked` already returns
`Ok(default)` for a missing file, so the first-write-creates-the-file
ergonomic is preserved (covered by the new
`file_store_set_still_creates_file_when_missing` test).

Adds four regression tests:

- set: insecure perms surface InsecurePermissions and leave the file
  byte-identical.
- delete: same.
- set: corrupt JSON surfaces the parse error and leaves the file
  byte-identical.
- set: missing file path still works (idempotence guard).

Closes #281

* fix(cache): make tool catalog byte-stable across calls and sessions

DeepSeek's KV prefix cache hits on the longest matching byte prefix of
the request. Two places in the tool-array path were silently introducing
divergence:

1. `ToolRegistry::to_api_tools()` iterated `self.tools.values()` directly.
   Rust's default `HashMap` is seeded with `RandomState` per process, so
   every `deepseek` launch produced a different tool order — the cross-
   session resume case (the one with the biggest cache wins) never hit.

2. `active_tool_list_from_catalog()` filtered the catalog `Vec` by the
   active set in catalog order. When ToolSearch activated a previously-
   deferred tool mid-conversation, the new tool appeared at its catalog
   index, shifting every later tool's byte offset and busting the cached
   prefix from there onwards.

Fixes:

- `to_api_tools()` now sorts by tool name before emitting the API tool
  array. Stable across calls AND across launches.
- `build_model_tool_catalog()` sorts each partition (built-ins first,
  contiguous; MCP tools after, also alphabetical). Mirrors Claude Code's
  `assembleToolPool` strategy where they explicitly call out cache
  stability as the reason: "a flat sort would interleave MCP tools into
  built-ins and invalidate all downstream cache keys whenever an MCP
  tool sorts between existing built-ins."
- `active_tool_list_from_catalog()` puts always-loaded tools in catalog
  order at the head and deferred-but-now-active tools at the tail. A
  deferred-tool activation during ToolSearch no longer shifts earlier
  tools' positions.

Adds three regression tests:

- `to_api_tools_emits_alphabetical_order_regardless_of_registration_order`
- `model_tool_catalog_sorts_each_partition_for_prefix_cache_stability`
- `active_tool_list_pushes_deferred_activations_to_the_tail`

Refs #263. Findings produced by reading reference Claude Code source
side-by-side with our request-building flow; full delta analysis in
the PR description.

* fix(sandbox): elevate Agent-mode shell sandbox to allow network access

The seatbelt-default policy is `WorkspaceWrite { network_access: false }`,
which on macOS emits `(deny default)` with no `(allow network-outbound)` /
`(allow system-socket)`. Every outbound socket call from a sandboxed
shell command — including `getaddrinfo` for DNS — gets denied by the
kernel. Symptom: "DNS resolution failed" for any URL the model tries to
reach via curl, yt-dlp, package managers, etc.

Engine.build_tool_context only elevated the policy in Yolo mode, leaving
Agent mode (the default) stuck on the strict default. That's tighter
than competitors (Claude Code, Codex) without buying any safety the
application-level NetworkPolicy or the approval flow doesn't already
provide.

Switch the elevation to a `match` so:

- Plan       → no elevation (read-only investigation; shell tool not registered)
- Agent      → WorkspaceWrite { network_access: true, … }
- Yolo       → WorkspaceWrite { network_access: true, … } (unchanged)

Adds `agent_and_yolo_modes_elevate_shell_sandbox_to_allow_network` so a
future revert to the no-network default trips CI immediately.

Closes #273

* fix(skills): treat bare github.com/<owner>/<repo> URLs as GitHubRepo

Closes #269.

`/skill install https://github.com/obra/superpowers` failed on every
platform with `invalid gzip header`. Root cause: `InstallSource::parse`
matched any `https://`-prefixed spec as `DirectUrl`, so the installer
downloaded the HTML repo page (200 OK, `text/html`) and tried to
gzip-decode HTML. The user reported it from Win11 + PowerShell but the
parse path is platform-independent.

Recognize bare GitHub repo URLs in `InstallSource::parse`:

- `https://github.com/<owner>/<repo>`
- `https://github.com/<owner>/<repo>/`
- `https://github.com/<owner>/<repo>.git`
- `https://github.com/<owner>/<repo>.git/`
- `https://www.github.com/<owner>/<repo>`
- `http://github.com/<owner>/<repo>` (legacy)

…all route to the existing `GitHubRepo` source, which already produces
`https://github.com/<repo>/archive/refs/heads/{main,master}.tar.gz`
candidates with proper fallback. URLs with a third path segment
(`/archive/...`, `/blob/...`, `/tree/...`) keep going through
`DirectUrl` because the user picked that exact path.

Adds two regression tests: one asserting the seven recognised forms
all canonicalize to `github:obra/superpowers`, and one pinning the
sub-resource paths to `DirectUrl`.

* fix(cache): drop volatile fields from working_set summary block (#280) (#287)

The working-set summary lands inside the system prompt before the
historical conversation, so any byte that drifts there cache-misses
everything that follows in DeepSeek's KV prefix cache. Two sources of
turn-over-turn drift are removed:

1. The rendered line is now `- {path} ({kind})`. The previous form
   interpolated `entry.touches` and `self.turn - entry.last_turn`,
   both of which advance on every user message even when no new
   paths are observed.

2. A new `sorted_for_prompt` helper sorts by (touches DESC, path ASC)
   instead of the turn-aware `sorted_entries`. The recency bonus in
   `score_entry` crosses bucket boundaries as turns advance, so even
   without rendering `last seen` the order — and which entries cross
   the `max_prompt_entries` cutoff — drifted. Compaction pinning
   still uses `sorted_entries` because it genuinely wants recency.

Adds a regression test that observes a fixed message set, calls
`summary_block` before and after `next_turn()`, and asserts the two
outputs are byte-identical. The shared `first_divergence` /
`assert_byte_identical` helpers (from #279) move from `prompts::tests`
into `test_support` so working_set tests can reuse them.

Closes #280.

* fix(cache): memoise tool catalog so descriptions stay byte-stable (#289)

`to_api_tools` previously re-sampled `tool.description()` and
`tool.input_schema()` on every call. Native tools return `&'static str`
and a `json!` literal, so the bytes were stable in practice — but the
`McpToolAdapter` returns `self.tool.description.as_deref()`, which can
drift when the upstream MCP server reconnects with a different
description string. Any drift mid-session rewrites the tool catalog
that lands in the cached prefix and busts every byte that follows.

Adds an `api_cache: OnceLock<Vec<Tool>>` field on `ToolRegistry`. The
first `to_api_tools` call materialises the catalog; subsequent calls
return a clone of the cached vector. Mutations (`register`, `remove`,
`clear`) reset the field so the next read rebuilds. Mirrors
reference-cc's `getToolSchemaCache` (`utils/api.ts:119–208`).

Tests:
- `to_api_tools_pins_description_bytes_across_calls` registers a tool
  whose `description()` advances through a script of pre-built strings
  on each call. After the cache is populated, the second `to_api_tools`
  read returns the original description because `description()` is no
  longer invoked. Without the cache the second read would return the
  next script entry.
- `register_invalidates_api_tools_cache` registers a tool, snapshots,
  registers another, snapshots again, and asserts the second snapshot
  reflects both tools (cache rebuilt) and that the varying tool's
  description advanced (proving the rebuild actually re-sampled).
- `remove_and_clear_invalidate_api_tools_cache` covers the other two
  invalidation paths.

* fix(cache): sort project_tree and summarize_project output (#290)

Both helpers walked the workspace via `ignore::WalkBuilder::build()`
and emitted entries in the OS readdir order — non-deterministic across
filesystems (htree-hash on ext4, insertion-order on APFS, etc.). Their
output lands in the fallback branch of the system prompt's project
context (when the workspace has no AGENTS.md / CLAUDE.md) and inside
the `project_map` tool surface, both of which feed the cached prefix.

`summarize_project` now sorts the collected key-files list before the
type-detection logic and the fallback `Project with key files: …` join.

`project_tree` collects `(rel_path, is_dir)` tuples, sorts by full
path, and only then formats the indented tree. Sorting by full path
preserves the visual tree shape — `"src" < "src/lib.rs"` because the
shorter string compares less — while making siblings deterministic.

Tests cover sibling order, parent-before-children invariant, byte
stability across two consecutive calls, and the fallback `Project
with key files:` branch (the only branch where the joined order
escapes into output without further sorting downstream).

* fix(client): unique fallback id for parallel streaming tool calls (#291)

When a streamed tool_call delta omits the `id` field, the chat-completion
decoder used to fall back to the literal string `"tool_call"` for every
call. With the V4 API's native parallel tool calls (multiple tool_calls
in one delta), every parallel call ended up with the same fallback id —
downstream tool-result routing then matched the first call's result
twice and the second call hung waiting for an answer that never arrived.

The fallback now indexes by the assigned `content_block` position,
producing `"call_0"`, `"call_1"`, … within a single response. Upstream-
supplied ids are still forwarded verbatim; only the fallback path
changes.

Tests pin both invariants:
- `decoder_assigns_unique_fallback_ids_to_parallel_tool_calls_missing_id`
  feeds two tool calls without `id` in one delta and asserts they get
  distinct ids.
- `decoder_preserves_upstream_tool_call_id_when_present` keeps the
  forward-as-is path honest.

* fix(cache): place handoff and working_set after static prompt blocks (#292)

* fix(cache): drop volatile fields from working_set summary block (#280)

The working-set summary lands inside the system prompt before the
historical conversation, so any byte that drifts there cache-misses
everything that follows in DeepSeek's KV prefix cache. Two sources of
turn-over-turn drift are removed:

1. The rendered line is now `- {path} ({kind})`. The previous form
   interpolated `entry.touches` and `self.turn - entry.last_turn`,
   both of which advance on every user message even when no new
   paths are observed.

2. A new `sorted_for_prompt` helper sorts by (touches DESC, path ASC)
   instead of the turn-aware `sorted_entries`. The recency bonus in
   `score_entry` crosses bucket boundaries as turns advance, so even
   without rendering `last seen` the order — and which entries cross
   the `max_prompt_entries` cutoff — drifted. Compaction pinning
   still uses `sorted_entries` because it genuinely wants recency.

Adds a regression test that observes a fixed message set, calls
`summary_block` before and after `next_turn()`, and asserts the two
outputs are byte-identical. The shared `first_divergence` /
`assert_byte_identical` helpers (from #279) move from `prompts::tests`
into `test_support` so working_set tests can reuse them.

Closes #280.

* fix(cache): place handoff and working_set after static prompt blocks

`system_prompt_for_mode_with_context_and_skills` previously interleaved
volatile content into the static prefix:

  1. mode prompt           static
  2. project context       static
  3. working_set_summary   ← volatile
  4. skills_block          static
  5. handoff_block         ← volatile
  6. ## Context Management static
  7. COMPACT_TEMPLATE      static

Anything past byte (3) cache-missed every time the working-set drifted
or `/compact` rewrote `.deepseek/handoff.md` — including the static
`## Context Management` and `## Compaction Handoff` blocks behind them.

New order keeps every static block in the cached prefix and pushes the
two volatile blocks to the end:

  1. mode prompt
  2. project context (or fallback automap)
  3. skills block
  4. ## Context Management (Agent / Yolo only)
  5. COMPACT_TEMPLATE
  ── volatile boundary ──
  6. handoff block
  7. working-set summary

Adds a doc comment on the function describing the volatile-content-last
invariant so future contributors don't reintroduce churn into the
prefix. Adds two regression tests:

- `system_prompt_with_handoff_file_is_byte_stable_when_file_is_unchanged`
  pins the handoff path with a fixture file.
- `handoff_and_working_set_appear_after_static_blocks` asserts the
  ordering invariant directly so a future reorder fails loudly.

Reference: Claude Code's own prompt builder marks this same boundary
with a `SYSTEM_PROMPT_DYNAMIC_BOUNDARY` constant; we don't introduce
the abstraction yet but match the principle.

* feat(i18n): localize slash command help (Phase 1a, #285) (#294)

Adds 44 new MessageIds, one per slash command, and translations to all
four shipped locales (en/ja/zh-Hans/pt-BR). Refactors CommandInfo so the
English description now lives in localization.rs (single source of
truth) instead of being duplicated on the struct, and threads the
active Locale through the three render surfaces:

- crates/tui/src/tui/views/help.rs (the ?/F1/Ctrl+/ help overlay)
- crates/tui/src/tui/command_palette.rs (Ctrl+K palette)
- crates/tui/src/commands/core.rs (the /help text command)

Usage strings (e.g. /cache [count]) stay English by design — they're
placeholder syntax, not natural language.

The existing locale-coverage test
(`shipped_first_pack_has_no_missing_core_messages`) already iterates
ALL_MESSAGE_IDS across Locale::shipped(), so the 44 new IDs are
automatically required to be present in all four locale arms or CI
fails.

This is the first of several incremental Phase 1 PRs. Phase 1b covers
the debug commands (/tokens /cost /cache), 1c the footer hints, and
1d doctor output. Phases 2–3 cover onboarding and error surfaces.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(i18n): localize /tokens /cost /cache debug output (Phase 1b, #285) (#295)

Adds 13 new MessageIds covering the report templates and the
sub-strings shared across them, with translations for all four
shipped locales (en/ja/zh-Hans/pt-BR):

- CmdTokensReport, CmdTokensContextWithWindow, CmdTokensContextUnknownWindow
- CmdTokensCacheBoth, CmdTokensCacheHitOnly, CmdTokensCacheMissOnly
- CmdTokensNotReported
- CmdCostReport
- CmdCacheNoData, CmdCacheHeader, CmdCacheTotals, CmdCacheFootnote, CmdCacheAdvice

Each template uses {placeholder} substitution via String::replace
rather than format!, since format! requires a literal — the
locale-resolved &'static str isn't one. The placeholder convention
({active}, {hit}, {miss}, …) means a translator can re-order or
restructure a sentence freely without changing the call site.

Helpers `token_count`, `active_context_summary`, `cache_summary`, and
`format_cache_history` now take `Locale` so each can resolve their
templates from the same source of truth.

The English templates byte-match the previous hardcoded format strings
so the existing 16 debug-command tests pass unchanged.

Column headers in the cache table (`turn   in    out   hit   miss …`)
are intentionally NOT localized — the body rows are formatted with
fixed column widths and translating the header words would break
alignment. Numbers, ratios, and the model id stay in English form.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(i18n): localize footer state + help section labels (Phase 1c, #285) (#296)

Adds 11 new MessageIds covering visible footer chrome and the help-overlay
section headings, with translations for all four shipped locales:

Footer:
- FooterWorking — animated `working` / `working.` / … pulse
- FooterAgentSingular / FooterAgentsPlural — the sub-agent count chip
- FooterPressCtrlCAgain — the quit-confirmation toast

Help overlay sections (`?` / `F1` / `Ctrl+/`):
- HelpSectionNavigation, HelpSectionEditing, HelpSectionActions,
  HelpSectionModes, HelpSectionSessions, HelpSectionClipboard,
  HelpSectionHelp

`KeybindingSection::label` now takes Locale and returns tr(locale, …).
`footer_working_label` and `footer_agents_chip` likewise take Locale; the
two production callsites in tui/ui.rs pass `app.ui_locale`.

The mode chip itself (agent / yolo / plan) intentionally stays English —
those are brand/acronym labels, and translating them would mean explaining
to maintainers what `代理` means in a bug report.

The keybinding catalog DESCRIPTIONS (41 entries) are not translated in this
PR — those are technical prose that would dwarf the rest of i18n work and
can ship in v0.8.5. Section labels are translated so the help overlay
groups read as expected in any locale.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test(commands): smoke-test that every / command dispatches to a handler (#299)

Adds two parallel-safe smoke tests in `crates/tui/src/commands/mod.rs`
that iterate the COMMANDS registry and verify every command — and every
declared alias — dispatches to a real handler. A dispatch miss surfaces
as the fall-through `Unknown command:` error message in `execute`,
which used to be invisible until a user typed the command and saw the
"did you mean" suggestion fire on a registered command.

The tests build a workspace-isolated app via `tempfile::TempDir` so
side-effecting handlers (`/init` writing AGENTS.md, `/save` and
`/export` writing files) do not pollute `crates/tui/` when CI runs from
there. `/save` and `/export` get an explicit tempdir-relative path
because their no-arg defaults still resolve relative to `cwd`.

`/restore` is skipped — it shells out to git for the snapshot repo and
its own dedicated tests in `commands/restore.rs` already serialize on
the global env mutex via `scoped_home`. The existing coverage there is
sufficient.

Closes a gap surfaced when verifying that the v0.8.4 i18n refactor
(#294, #295, #296) did not silently break any slash-command dispatch.
All 44 commands and their aliases pass (16 aliases on top of the
44 names; `/restore` is the only skip).

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore(release): bump version to 0.8.4 (#297)

CHANGELOG entry covers the v0.8.4 work landed since 0.8.3:

- Localization Phase 1 (#285) — slash command help (#294), debug command
  output (#295), footer state and help-overlay section labels (#296).
  Adds 68 new MessageIds across all four shipped locales (en/ja/zh-Hans/pt-BR).

- Cache-prefix stability (#263) — five companion fixes (#287, #288→#292,
  #289, #290, #291) that keep the DeepSeek prefix cache stable across turns.

- Plus the items already in [Unreleased]: agent-mode network exec (#272),
  /skill GitHub URL parsing (#269), and the V4 Pro discount expiry extension
  (#267).

Bumps:
- Cargo.toml workspace version 0.8.3 → 0.8.4
- npm/deepseek-tui/package.json version + deepseekBinaryVersion 0.8.3 → 0.8.4
- Cargo.lock regenerated from the new workspace version.

Phase 1d (doctor output), Phase 2 (onboarding/init/missing-companion),
and Phase 3 (tool errors / sandbox denials / approvals) deferred to v0.8.5.
The shipped Phase 1 surfaces (slash commands, debug telemetry, footer
chrome) cover the highest-traffic UI paths Chinese users see first.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(release): bump internal path-dep versions + repair doc link (#301)

CI on PR #300 (release feat/v0.8.4 → main) flagged two regressions
introduced by the 0.8.4 version bump:

1. Version drift — path-dependency `version = "0.8.3"` references
   inside the workspace crates (10 crates: agent, app-server, cli,
   config, core, execpolicy, hooks, mcp, tools, tui) did not move with
   the workspace `[workspace.package] version = "0.8.4"`. The CI guard
   `scripts/release/check-versions.sh` requires they match.

2. Broken intra-doc-link `[crate::localization::english]` in the
   CommandInfo doc comment — `english` is private. Replaced with a
   reference to the public `description_for` accessor and the public
   `tr()` function.

Verified with:
- scripts/release/check-versions.sh — Version state OK.
- RUSTDOCFLAGS=-Dwarnings cargo doc --workspace --no-deps — green.
- cargo fmt + clippy + test all green.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

The DeepSeek prefix-cache only hits while the byte prefix of each
request matches the prior call. Anything in the cached prefix that
varies turn-to-turn for unchanged inputs is a cache buster.

Adds a focused harness next to the production surface so the property
is regression-guarded:

1. `first_divergence(a, b)` helper that returns the first divergent
   byte position with a `±32 byte` window of context, used by the
   custom assertion `assert_byte_identical`. Future suspect tests can
   reuse this to surface "where" rather than just "fail".

2. `compose_prompt_is_byte_stable_across_calls` — sweeps every
   (mode, personality) pair and pins that two consecutive calls
   produce identical bytes. Rules out suspect Hmbown#4 (mode-prompt churn).

3. `system_prompt_for_mode_with_context_is_byte_stable_for_unchanged_workspace`
   — the call site `engine.rs::build_tool_context` actually invokes,
   pinned for an empty workspace across all three modes.

4. `system_prompt_with_working_set_summary_is_byte_stable_for_constant_summary`
   — pins that the surrounding prompt construction faithfully embeds
   the working_set summary it's given without injecting extra
   non-determinism. (The actual working_set summary stability lives
   in `working_set.rs` and is the next investigation target — see
   issue note in PR description.)

Foundation for the suspect-by-suspect bisection in the rest of Hmbown#263.

- Wire 120 FPS FrameRateLimiter into run_event_loop via
  time_until_next_draw + mark_emitted
- Add low_motion support: 30 FPS cap via LOW_MOTION_MIN_FRAME_INTERVAL
- Add AdaptiveChunkingPolicy::set_low_motion() to force Smooth mode
- Add StreamingState::set_low_motion() to propagate to all block policies
- Tool spinner already freezes on first frame when low_motion is set

TODO_BACKEND.md §3, TODO_FIXES.md Hmbown#4

* fix(pricing): extend V4 Pro 75% discount expiry to 2026-05-31 15:59 UTC

DeepSeek extended the promotional discount past the original 2026-05-05
cutoff. Without this update the TUI would have started showing 4× the
actual billed cost on May 6.

Source: https://api-docs.deepseek.com/quick_start/pricing — "extended
until 2026/05/31 15:59 UTC".

Adds a regression test pinning the new active window so a future revert
to the May 5 date trips the suite immediately.

Closes Hmbown#267

* chore: remove stale TODO(integrate) markers from already-integrated modules

Five `// TODO(integrate)` comments and one matching "Not yet integrated"
note were misleading anyone grepping for integration work. Each module
is in fact wired up:

- execpolicy/mod.rs       → tools/shell.rs:1322 (load_default_policy)
- sandbox/mod.rs          → tools/shell.rs:28, main.rs:2647, tui/approval.rs:30
- sandbox/policy.rs       → main.rs:2752, tui/approval.rs:30 (SandboxPolicy)
- command_safety.rs       → tools/shell.rs:1321, tools/tasks.rs:13,
                            tools/approval_cache.rs:26
- tui/streaming/mod.rs    → tui/app.rs:38 (StreamingState)

The remaining TODO at mcp.rs:1771 covers a separate "wire legacy sync API
into CLI subcommands or remove" decision and is left in place.

Closes Hmbown#266

* docs(release): add install + dual-binary template to GitHub Release page

Closes Hmbown#265.

The Release page used the auto-generated commit-title body. New users
hitting the Release page from Twitter / npm-search had no on-page
guidance that the dispatcher (`deepseek`) and the TUI runtime
(`deepseek-tui`) ship as two binaries that must coexist; Hmbown#258 was an
external user spending 11 minutes figuring this out and Hmbown#272 was the
follow-on confusion.

The new body covers:
- npm wrapper as the recommended install
- `cargo install deepseek-tui-cli deepseek-tui --locked` (both crates)
- Manual download with a per-platform table showing both artifacts
- sha256 verify using the existing `deepseek-artifacts-sha256.txt`
- Changelog link

* feat(debug): add /cache command surfacing per-turn DeepSeek cache hit/miss

Step 1 of Hmbown#263. Without per-turn telemetry the prefix-cache audit is
unfounded speculation; the rest of the issue's investigation steps
depend on this surface.

The DeepSeek API already returns `prompt_cache_hit_tokens` and
`prompt_cache_miss_tokens` per turn, and we already store the *latest*
on App. This adds a 50-turn ring (`turn_cache_history`) populated at
the same site as `last_prompt_cache_*_tokens`, plus a `/cache [count]`
slash command that renders a fixed-width table of the last N turns
with per-turn ratios and a session aggregate. Default count is 10;
larger values clamp to the ring size.

Edge cases the formatter handles:

- No telemetry yet → friendly "no turns recorded" message
- `cache_hit_tokens = None` (provider didn't report) → row renders all
  em-dashes and is excluded from session aggregates so one missing-
  telemetry turn can't make the average ratio look broken.
- `cache_hit_tokens = Some, cache_miss_tokens = None` → infer miss as
  `input − hit` and mark the cell with `*`. Footer documents the
  asterisk.
- Ring at cap (50) → push evicts oldest.

Tests cover all four paths plus the cap.

* test(prompts): add cache-prefix stability harness for Hmbown#263 step 2

The DeepSeek prefix-cache only hits while the byte prefix of each
request matches the prior call. Anything in the cached prefix that
varies turn-to-turn for unchanged inputs is a cache buster.

Adds a focused harness next to the production surface so the property
is regression-guarded:

1. `first_divergence(a, b)` helper that returns the first divergent
   byte position with a `±32 byte` window of context, used by the
   custom assertion `assert_byte_identical`. Future suspect tests can
   reuse this to surface "where" rather than just "fail".

2. `compose_prompt_is_byte_stable_across_calls` — sweeps every
   (mode, personality) pair and pins that two consecutive calls
   produce identical bytes. Rules out suspect Hmbown#4 (mode-prompt churn).

3. `system_prompt_for_mode_with_context_is_byte_stable_for_unchanged_workspace`
   — the call site `engine.rs::build_tool_context` actually invokes,
   pinned for an empty workspace across all three modes.

4. `system_prompt_with_working_set_summary_is_byte_stable_for_constant_summary`
   — pins that the surrounding prompt construction faithfully embeds
   the working_set summary it's given without injecting extra
   non-determinism. (The actual working_set summary stability lives
   in `working_set.rs` and is the next investigation target — see
   issue note in PR description.)

Foundation for the suspect-by-suspect bisection in the rest of Hmbown#263.

* fix(secrets): never overwrite the secrets file when load_unlocked errors

`FileKeyringStore::set` and `delete` did
`self.load_unlocked().unwrap_or_default()`, which wiped every existing
secret if the read failed for any reason other than \"file is missing\":

- file mode != 0600 (`InsecurePermissions`) — easy on headless / CI
  environments where a permissive umask got applied
- corrupt JSON
- transient I/O error

In all of those, the next `store_unlocked` overwrote the file with an
empty-or-single-entry blob and reset perms to 0600, silently losing
every other provider's key.

Switch both call sites to `?`. `load_unlocked` already returns
`Ok(default)` for a missing file, so the first-write-creates-the-file
ergonomic is preserved (covered by the new
`file_store_set_still_creates_file_when_missing` test).

Adds four regression tests:

- set: insecure perms surface InsecurePermissions and leave the file
  byte-identical.
- delete: same.
- set: corrupt JSON surfaces the parse error and leaves the file
  byte-identical.
- set: missing file path still works (idempotence guard).

Closes Hmbown#281

* fix(cache): make tool catalog byte-stable across calls and sessions

DeepSeek's KV prefix cache hits on the longest matching byte prefix of
the request. Two places in the tool-array path were silently introducing
divergence:

1. `ToolRegistry::to_api_tools()` iterated `self.tools.values()` directly.
   Rust's default `HashMap` is seeded with `RandomState` per process, so
   every `deepseek` launch produced a different tool order — the cross-
   session resume case (the one with the biggest cache wins) never hit.

2. `active_tool_list_from_catalog()` filtered the catalog `Vec` by the
   active set in catalog order. When ToolSearch activated a previously-
   deferred tool mid-conversation, the new tool appeared at its catalog
   index, shifting every later tool's byte offset and busting the cached
   prefix from there onwards.

Fixes:

- `to_api_tools()` now sorts by tool name before emitting the API tool
  array. Stable across calls AND across launches.
- `build_model_tool_catalog()` sorts each partition (built-ins first,
  contiguous; MCP tools after, also alphabetical). Mirrors Claude Code's
  `assembleToolPool` strategy where they explicitly call out cache
  stability as the reason: "a flat sort would interleave MCP tools into
  built-ins and invalidate all downstream cache keys whenever an MCP
  tool sorts between existing built-ins."
- `active_tool_list_from_catalog()` puts always-loaded tools in catalog
  order at the head and deferred-but-now-active tools at the tail. A
  deferred-tool activation during ToolSearch no longer shifts earlier
  tools' positions.

Adds three regression tests:

- `to_api_tools_emits_alphabetical_order_regardless_of_registration_order`
- `model_tool_catalog_sorts_each_partition_for_prefix_cache_stability`
- `active_tool_list_pushes_deferred_activations_to_the_tail`

Refs Hmbown#263. Findings produced by reading reference Claude Code source
side-by-side with our request-building flow; full delta analysis in
the PR description.

* fix(sandbox): elevate Agent-mode shell sandbox to allow network access

The seatbelt-default policy is `WorkspaceWrite { network_access: false }`,
which on macOS emits `(deny default)` with no `(allow network-outbound)` /
`(allow system-socket)`. Every outbound socket call from a sandboxed
shell command — including `getaddrinfo` for DNS — gets denied by the
kernel. Symptom: "DNS resolution failed" for any URL the model tries to
reach via curl, yt-dlp, package managers, etc.

Engine.build_tool_context only elevated the policy in Yolo mode, leaving
Agent mode (the default) stuck on the strict default. That's tighter
than competitors (Claude Code, Codex) without buying any safety the
application-level NetworkPolicy or the approval flow doesn't already
provide.

Switch the elevation to a `match` so:

- Plan       → no elevation (read-only investigation; shell tool not registered)
- Agent      → WorkspaceWrite { network_access: true, … }
- Yolo       → WorkspaceWrite { network_access: true, … } (unchanged)

Adds `agent_and_yolo_modes_elevate_shell_sandbox_to_allow_network` so a
future revert to the no-network default trips CI immediately.

Closes Hmbown#273

* fix(skills): treat bare github.com/<owner>/<repo> URLs as GitHubRepo

Closes Hmbown#269.

`/skill install https://github.com/obra/superpowers` failed on every
platform with `invalid gzip header`. Root cause: `InstallSource::parse`
matched any `https://`-prefixed spec as `DirectUrl`, so the installer
downloaded the HTML repo page (200 OK, `text/html`) and tried to
gzip-decode HTML. The user reported it from Win11 + PowerShell but the
parse path is platform-independent.

Recognize bare GitHub repo URLs in `InstallSource::parse`:

- `https://github.com/<owner>/<repo>`
- `https://github.com/<owner>/<repo>/`
- `https://github.com/<owner>/<repo>.git`
- `https://github.com/<owner>/<repo>.git/`
- `https://www.github.com/<owner>/<repo>`
- `http://github.com/<owner>/<repo>` (legacy)

…all route to the existing `GitHubRepo` source, which already produces
`https://github.com/<repo>/archive/refs/heads/{main,master}.tar.gz`
candidates with proper fallback. URLs with a third path segment
(`/archive/...`, `/blob/...`, `/tree/...`) keep going through
`DirectUrl` because the user picked that exact path.

Adds two regression tests: one asserting the seven recognised forms
all canonicalize to `github:obra/superpowers`, and one pinning the
sub-resource paths to `DirectUrl`.

* fix(cache): drop volatile fields from working_set summary block (Hmbown#280) (Hmbown#287)

The working-set summary lands inside the system prompt before the
historical conversation, so any byte that drifts there cache-misses
everything that follows in DeepSeek's KV prefix cache. Two sources of
turn-over-turn drift are removed:

1. The rendered line is now `- {path} ({kind})`. The previous form
   interpolated `entry.touches` and `self.turn - entry.last_turn`,
   both of which advance on every user message even when no new
   paths are observed.

2. A new `sorted_for_prompt` helper sorts by (touches DESC, path ASC)
   instead of the turn-aware `sorted_entries`. The recency bonus in
   `score_entry` crosses bucket boundaries as turns advance, so even
   without rendering `last seen` the order — and which entries cross
   the `max_prompt_entries` cutoff — drifted. Compaction pinning
   still uses `sorted_entries` because it genuinely wants recency.

Adds a regression test that observes a fixed message set, calls
`summary_block` before and after `next_turn()`, and asserts the two
outputs are byte-identical. The shared `first_divergence` /
`assert_byte_identical` helpers (from Hmbown#279) move from `prompts::tests`
into `test_support` so working_set tests can reuse them.

Closes Hmbown#280.

* fix(cache): memoise tool catalog so descriptions stay byte-stable (Hmbown#289)

`to_api_tools` previously re-sampled `tool.description()` and
`tool.input_schema()` on every call. Native tools return `&'static str`
and a `json!` literal, so the bytes were stable in practice — but the
`McpToolAdapter` returns `self.tool.description.as_deref()`, which can
drift when the upstream MCP server reconnects with a different
description string. Any drift mid-session rewrites the tool catalog
that lands in the cached prefix and busts every byte that follows.

Adds an `api_cache: OnceLock<Vec<Tool>>` field on `ToolRegistry`. The
first `to_api_tools` call materialises the catalog; subsequent calls
return a clone of the cached vector. Mutations (`register`, `remove`,
`clear`) reset the field so the next read rebuilds. Mirrors
reference-cc's `getToolSchemaCache` (`utils/api.ts:119–208`).

Tests:
- `to_api_tools_pins_description_bytes_across_calls` registers a tool
  whose `description()` advances through a script of pre-built strings
  on each call. After the cache is populated, the second `to_api_tools`
  read returns the original description because `description()` is no
  longer invoked. Without the cache the second read would return the
  next script entry.
- `register_invalidates_api_tools_cache` registers a tool, snapshots,
  registers another, snapshots again, and asserts the second snapshot
  reflects both tools (cache rebuilt) and that the varying tool's
  description advanced (proving the rebuild actually re-sampled).
- `remove_and_clear_invalidate_api_tools_cache` covers the other two
  invalidation paths.

* fix(cache): sort project_tree and summarize_project output (Hmbown#290)

Both helpers walked the workspace via `ignore::WalkBuilder::build()`
and emitted entries in the OS readdir order — non-deterministic across
filesystems (htree-hash on ext4, insertion-order on APFS, etc.). Their
output lands in the fallback branch of the system prompt's project
context (when the workspace has no AGENTS.md / CLAUDE.md) and inside
the `project_map` tool surface, both of which feed the cached prefix.

`summarize_project` now sorts the collected key-files list before the
type-detection logic and the fallback `Project with key files: …` join.

`project_tree` collects `(rel_path, is_dir)` tuples, sorts by full
path, and only then formats the indented tree. Sorting by full path
preserves the visual tree shape — `"src" < "src/lib.rs"` because the
shorter string compares less — while making siblings deterministic.

Tests cover sibling order, parent-before-children invariant, byte
stability across two consecutive calls, and the fallback `Project
with key files:` branch (the only branch where the joined order
escapes into output without further sorting downstream).

* fix(client): unique fallback id for parallel streaming tool calls (Hmbown#291)

When a streamed tool_call delta omits the `id` field, the chat-completion
decoder used to fall back to the literal string `"tool_call"` for every
call. With the V4 API's native parallel tool calls (multiple tool_calls
in one delta), every parallel call ended up with the same fallback id —
downstream tool-result routing then matched the first call's result
twice and the second call hung waiting for an answer that never arrived.

The fallback now indexes by the assigned `content_block` position,
producing `"call_0"`, `"call_1"`, … within a single response. Upstream-
supplied ids are still forwarded verbatim; only the fallback path
changes.

Tests pin both invariants:
- `decoder_assigns_unique_fallback_ids_to_parallel_tool_calls_missing_id`
  feeds two tool calls without `id` in one delta and asserts they get
  distinct ids.
- `decoder_preserves_upstream_tool_call_id_when_present` keeps the
  forward-as-is path honest.

* fix(cache): place handoff and working_set after static prompt blocks (Hmbown#292)

* fix(cache): drop volatile fields from working_set summary block (Hmbown#280)

The working-set summary lands inside the system prompt before the
historical conversation, so any byte that drifts there cache-misses
everything that follows in DeepSeek's KV prefix cache. Two sources of
turn-over-turn drift are removed:

1. The rendered line is now `- {path} ({kind})`. The previous form
   interpolated `entry.touches` and `self.turn - entry.last_turn`,
   both of which advance on every user message even when no new
   paths are observed.

2. A new `sorted_for_prompt` helper sorts by (touches DESC, path ASC)
   instead of the turn-aware `sorted_entries`. The recency bonus in
   `score_entry` crosses bucket boundaries as turns advance, so even
   without rendering `last seen` the order — and which entries cross
   the `max_prompt_entries` cutoff — drifted. Compaction pinning
   still uses `sorted_entries` because it genuinely wants recency.

Adds a regression test that observes a fixed message set, calls
`summary_block` before and after `next_turn()`, and asserts the two
outputs are byte-identical. The shared `first_divergence` /
`assert_byte_identical` helpers (from Hmbown#279) move from `prompts::tests`
into `test_support` so working_set tests can reuse them.

Closes Hmbown#280.

* fix(cache): place handoff and working_set after static prompt blocks

`system_prompt_for_mode_with_context_and_skills` previously interleaved
volatile content into the static prefix:

  1. mode prompt           static
  2. project context       static
  3. working_set_summary   ← volatile
  4. skills_block          static
  5. handoff_block         ← volatile
  6. ## Context Management static
  7. COMPACT_TEMPLATE      static

Anything past byte (3) cache-missed every time the working-set drifted
or `/compact` rewrote `.deepseek/handoff.md` — including the static
`## Context Management` and `## Compaction Handoff` blocks behind them.

New order keeps every static block in the cached prefix and pushes the
two volatile blocks to the end:

  1. mode prompt
  2. project context (or fallback automap)
  3. skills block
  4. ## Context Management (Agent / Yolo only)
  5. COMPACT_TEMPLATE
  ── volatile boundary ──
  6. handoff block
  7. working-set summary

Adds a doc comment on the function describing the volatile-content-last
invariant so future contributors don't reintroduce churn into the
prefix. Adds two regression tests:

- `system_prompt_with_handoff_file_is_byte_stable_when_file_is_unchanged`
  pins the handoff path with a fixture file.
- `handoff_and_working_set_appear_after_static_blocks` asserts the
  ordering invariant directly so a future reorder fails loudly.

Reference: Claude Code's own prompt builder marks this same boundary
with a `SYSTEM_PROMPT_DYNAMIC_BOUNDARY` constant; we don't introduce
the abstraction yet but match the principle.

* feat(i18n): localize slash command help (Phase 1a, Hmbown#285) (Hmbown#294)

Adds 44 new MessageIds, one per slash command, and translations to all
four shipped locales (en/ja/zh-Hans/pt-BR). Refactors CommandInfo so the
English description now lives in localization.rs (single source of
truth) instead of being duplicated on the struct, and threads the
active Locale through the three render surfaces:

- crates/tui/src/tui/views/help.rs (the ?/F1/Ctrl+/ help overlay)
- crates/tui/src/tui/command_palette.rs (Ctrl+K palette)
- crates/tui/src/commands/core.rs (the /help text command)

Usage strings (e.g. /cache [count]) stay English by design — they're
placeholder syntax, not natural language.

The existing locale-coverage test
(`shipped_first_pack_has_no_missing_core_messages`) already iterates
ALL_MESSAGE_IDS across Locale::shipped(), so the 44 new IDs are
automatically required to be present in all four locale arms or CI
fails.

This is the first of several incremental Phase 1 PRs. Phase 1b covers
the debug commands (/tokens /cost /cache), 1c the footer hints, and
1d doctor output. Phases 2–3 cover onboarding and error surfaces.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(i18n): localize /tokens /cost /cache debug output (Phase 1b, Hmbown#285) (Hmbown#295)

Adds 13 new MessageIds covering the report templates and the
sub-strings shared across them, with translations for all four
shipped locales (en/ja/zh-Hans/pt-BR):

- CmdTokensReport, CmdTokensContextWithWindow, CmdTokensContextUnknownWindow
- CmdTokensCacheBoth, CmdTokensCacheHitOnly, CmdTokensCacheMissOnly
- CmdTokensNotReported
- CmdCostReport
- CmdCacheNoData, CmdCacheHeader, CmdCacheTotals, CmdCacheFootnote, CmdCacheAdvice

Each template uses {placeholder} substitution via String::replace
rather than format!, since format! requires a literal — the
locale-resolved &'static str isn't one. The placeholder convention
({active}, {hit}, {miss}, …) means a translator can re-order or
restructure a sentence freely without changing the call site.

Helpers `token_count`, `active_context_summary`, `cache_summary`, and
`format_cache_history` now take `Locale` so each can resolve their
templates from the same source of truth.

The English templates byte-match the previous hardcoded format strings
so the existing 16 debug-command tests pass unchanged.

Column headers in the cache table (`turn   in    out   hit   miss …`)
are intentionally NOT localized — the body rows are formatted with
fixed column widths and translating the header words would break
alignment. Numbers, ratios, and the model id stay in English form.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(i18n): localize footer state + help section labels (Phase 1c, Hmbown#285) (Hmbown#296)

Adds 11 new MessageIds covering visible footer chrome and the help-overlay
section headings, with translations for all four shipped locales:

Footer:
- FooterWorking — animated `working` / `working.` / … pulse
- FooterAgentSingular / FooterAgentsPlural — the sub-agent count chip
- FooterPressCtrlCAgain — the quit-confirmation toast

Help overlay sections (`?` / `F1` / `Ctrl+/`):
- HelpSectionNavigation, HelpSectionEditing, HelpSectionActions,
  HelpSectionModes, HelpSectionSessions, HelpSectionClipboard,
  HelpSectionHelp

`KeybindingSection::label` now takes Locale and returns tr(locale, …).
`footer_working_label` and `footer_agents_chip` likewise take Locale; the
two production callsites in tui/ui.rs pass `app.ui_locale`.

The mode chip itself (agent / yolo / plan) intentionally stays English —
those are brand/acronym labels, and translating them would mean explaining
to maintainers what `代理` means in a bug report.

The keybinding catalog DESCRIPTIONS (41 entries) are not translated in this
PR — those are technical prose that would dwarf the rest of i18n work and
can ship in v0.8.5. Section labels are translated so the help overlay
groups read as expected in any locale.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test(commands): smoke-test that every / command dispatches to a handler (Hmbown#299)

Adds two parallel-safe smoke tests in `crates/tui/src/commands/mod.rs`
that iterate the COMMANDS registry and verify every command — and every
declared alias — dispatches to a real handler. A dispatch miss surfaces
as the fall-through `Unknown command:` error message in `execute`,
which used to be invisible until a user typed the command and saw the
"did you mean" suggestion fire on a registered command.

The tests build a workspace-isolated app via `tempfile::TempDir` so
side-effecting handlers (`/init` writing AGENTS.md, `/save` and
`/export` writing files) do not pollute `crates/tui/` when CI runs from
there. `/save` and `/export` get an explicit tempdir-relative path
because their no-arg defaults still resolve relative to `cwd`.

`/restore` is skipped — it shells out to git for the snapshot repo and
its own dedicated tests in `commands/restore.rs` already serialize on
the global env mutex via `scoped_home`. The existing coverage there is
sufficient.

Closes a gap surfaced when verifying that the v0.8.4 i18n refactor
(Hmbown#294, Hmbown#295, Hmbown#296) did not silently break any slash-command dispatch.
All 44 commands and their aliases pass (16 aliases on top of the
44 names; `/restore` is the only skip).

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore(release): bump version to 0.8.4 (Hmbown#297)

CHANGELOG entry covers the v0.8.4 work landed since 0.8.3:

- Localization Phase 1 (Hmbown#285) — slash command help (Hmbown#294), debug command
  output (Hmbown#295), footer state and help-overlay section labels (Hmbown#296).
  Adds 68 new MessageIds across all four shipped locales (en/ja/zh-Hans/pt-BR).

- Cache-prefix stability (Hmbown#263) — five companion fixes (Hmbown#287, Hmbown#288→Hmbown#292,
  Hmbown#289, Hmbown#290, Hmbown#291) that keep the DeepSeek prefix cache stable across turns.

- Plus the items already in [Unreleased]: agent-mode network exec (Hmbown#272),
  /skill GitHub URL parsing (Hmbown#269), and the V4 Pro discount expiry extension
  (Hmbown#267).

Bumps:
- Cargo.toml workspace version 0.8.3 → 0.8.4
- npm/deepseek-tui/package.json version + deepseekBinaryVersion 0.8.3 → 0.8.4
- Cargo.lock regenerated from the new workspace version.

Phase 1d (doctor output), Phase 2 (onboarding/init/missing-companion),
and Phase 3 (tool errors / sandbox denials / approvals) deferred to v0.8.5.
The shipped Phase 1 surfaces (slash commands, debug telemetry, footer
chrome) cover the highest-traffic UI paths Chinese users see first.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(release): bump internal path-dep versions + repair doc link (Hmbown#301)

CI on PR Hmbown#300 (release feat/v0.8.4 → main) flagged two regressions
introduced by the 0.8.4 version bump:

1. Version drift — path-dependency `version = "0.8.3"` references
   inside the workspace crates (10 crates: agent, app-server, cli,
   config, core, execpolicy, hooks, mcp, tools, tui) did not move with
   the workspace `[workspace.package] version = "0.8.4"`. The CI guard
   `scripts/release/check-versions.sh` requires they match.

2. Broken intra-doc-link `[crate::localization::english]` in the
   CommandInfo doc comment — `english` is private. Replaced with a
   reference to the public `description_for` accessor and the public
   `tr()` function.

Verified with:
- scripts/release/check-versions.sh — Version state OK.
- RUSTDOCFLAGS=-Dwarnings cargo doc --workspace --no-deps — green.
- cargo fmt + clippy + test all green.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

🔴 Fix Hmbown#1 (Embedder blocks async runtime):
- Pre-warm embedder in init_vector_db() via warmup_embedder()
- Model downloaded during startup, not first retrieval
- Eliminates 5-10s UI freeze on first embed call

🔴 Fix Hmbown#2 (Compaction summary pollution):
- store_compaction_summary_to_vector_db() now extracts only
  the summary section from the SystemPrompt, stripping
  boilerplate headers and workflow context
- Uses regex extraction between ## Summary and ## Workflow markers

🔴 Fix Hmbown#3 (No vector index → full table scan):
- New ensure_vector_index() in LanceDbBackend
- Checks list_indices() for existing IVF-PQ index on embedding column
- Creates missing index via table.create_index(["embedding"], Index::Auto)
- Called from ensure_tables() for all three tables

🔴 Fix Hmbown#4 (Compaction threshold regression for non-vector users):
- Added MINIMUM_AUTO_COMPACTION_TOKENS_WITHOUT_VECTOR = 500K
- should_compact() now accepts vector_db_enabled: bool
- Non-vector users keep 500K floor; vector users use 50K floor
- auto_floor_tokens=0 (explicit disable by tests) bypasses both floors
- token_threshold default restored to 800K (fallback only;
  real values come from compaction_threshold_for_model_and_effort)

🟡 Fix Hmbown#7 (No score threshold → noise injection):
- search_memories() and search_summaries() now filter
  results where score < 0.4 before returning
- Prevents low-quality retrieval from polluting system prompt

Tests: 62/62 compaction ✓, 17/17 vector_db ✓

🔴 Hmbown#1 Embedder blocks async runtime:
  - Pre-warm embedder in init_vector_db() via warmup_embedder()
  - Model downloaded at startup, eliminating 5-10s UI freeze

🔴 Hmbown#2 Compaction summary boilerplate pollution:
  - store_compaction_summary_to_vector_db() now extracts only
    the actual summary section using regex, stripping headers
    and workflow context from embeddings

🔴 Hmbown#3 No vector index → full table scan:
  - New ensure_vector_index() checks list_indices() for IVF-PQ
  - Creates missing index via create_index(["embedding"], Auto)
  - Called from ensure_tables() for all 3 tables

🔴 Hmbown#4 Compaction threshold regression:
  - Added MINIMUM_AUTO_COMPACTION_TOKENS_WITHOUT_VECTOR = 500K
  - should_compact() accepts vector_db_enabled: bool
  - Non-vector users keep 500K floor; vector users get 50K
  - auto_floor_tokens=0 bypasses both (test compatibility)
  - token_threshold default restored to 800K

🟡 Hmbown#7 Score threshold filtering added:
  - search_memories() and search_summaries() filter score < 0.4

Tests: 62/62 compaction ✓, 17/17 vector_db ✓, 99/100 engine ✓

… precision

- resolve_path: normalise .. components; reject workspace escapes (Hmbown#1,Hmbown#5)
- tool_read_file: clamp start_line >= 1 to prevent underflow panic (Hmbown#4)
- tool_edit_file: use replacen(.., 1) to avoid mass-replacement bugs (Hmbown#6,Hmbown#8)

…trol, verify fast-path, naming

- combined_hash now hashes full tool JSON (name + description + schema),
  not just tool names, so schema/description changes are detected (Hmbown#1).
- build_messages preserves cache_control from SystemPrompt::Blocks so
  DeepSeek context-cache breakpoints are not lost (Hmbown#2).
- FrozenPrefix::verify() compares raw text before hashing to avoid
  redundant SHA-256 computation (Hmbown#3).
- build_messages uses self.message_count() for vector capacity (Hmbown#4).
- Strict-mode error message no longer references nonexistent
  /prefix-unfreeze command — suggests restart or config toggle (Hmbown#5).