Add spawn_supervised(name, location, future) to utils.rs that wraps
futures in AssertUnwindSafe + catch_unwind, logs panics via tracing::error!,
and writes crash dumps to ~/.deepseek/crashes/.
Add process-level panic hook to main.rs that writes crash dumps before
the default hook fires.
Convert persistence_actor::spawn_persistence_actor as the first
spawn_supervised caller to prove the wiring. Remaining 34 tokio::spawn
sites marked as follow-up for a focused PR.
Also fix save_mcp_config in main.rs to use write_atomic (missed in #355).
Replaces synchronous disk writes on the UI thread with a dedicated
persistence actor task. The UI now try_sends a PersistRequest and
returns immediately — keyboard input is never gated on write completion.
Changes:
- New persistence_actor module with bounded-coalescing actor
- Actor spawns at TUI startup; global singleton so no App struct change
- All persist_checkpoint/persist_session_snapshot/clear_checkpoint calls
replaced with persistence_actor::persist(PersistRequest::...)
- Dropped redundant TurnStarted persist (nothing changed between
SendMessage's checkpoint and TurnStarted)
- Fixed collapsible_if clippy lint
This is the P0 fix for the post-send terminal freeze caused by
serialising 500KB+ sessions to disk on the UI thread.
Closes the gate the maintainer set for v0.8.5: every / command, /help,
and /settings should look perfect in both English and Chinese before
multi-agent work begins. v0.8.4 shipped Phase 1a/b/c (88 MessageIds)
but four mixed-language gaps remained:
1. **Keybinding descriptions** (41 entries) — the help overlay showed
translated section labels (Phase 1c) over English description text.
`KeybindingEntry` now carries `description_id: MessageId` instead
of a raw `&'static str`; all 41 descriptions translated to
en/ja/zh-Hans/pt-BR.
2. **Settings: header** — `Settings::display` now takes a `Locale`
and resolves the title via `MessageId::SettingsTitle`. The
field-name keys (auto_compact, calm_mode, etc.) intentionally stay
English — they are the literal TOML keys users edit.
3. **/home dashboard** — entirely English before. ~25 lines of section
headers, mode tips, and quick-action hints translated. Path
interpolations route through `display_path` (privacy invariant).
4. **/help <topic>** text command — the inline labels `Usage:` and
`Aliases:` plus the `Unknown command:` fallback all use tr().
Also adds three buffer-render tests confirming the help overlay /
settings / home dashboard render in zh-Hans without missing markers
or English bleed-through.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Closes the gate the maintainer set for v0.8.5: every / command, /help,
and /settings should look perfect in both English and Chinese before
multi-agent work begins. v0.8.4 shipped Phase 1a/b/c (88 MessageIds)
but four mixed-language gaps remained:
1. **Keybinding descriptions** (41 entries) — the help overlay showed
translated section labels (Phase 1c) over English description text.
`KeybindingEntry` now carries `description_id: MessageId` instead
of a raw `&'static str`; all 41 descriptions translated to
en/ja/zh-Hans/pt-BR.
2. **Settings: header** — `Settings::display` now takes a `Locale`
and resolves the title via `MessageId::SettingsTitle`. The
field-name keys (auto_compact, calm_mode, etc.) intentionally stay
English — they are the literal TOML keys users edit.
3. **/home dashboard** — entirely English before. ~25 lines of section
headers, mode tips, and quick-action hints translated. Path
interpolations route through `display_path` (privacy invariant).
4. **/help <topic>** text command — the inline labels `Usage:` and
`Aliases:` plus the `Unknown command:` fallback all use tr().
Also adds three buffer-render tests confirming the help overlay /
settings / home dashboard render in zh-Hans without missing markers
or English bleed-through.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* 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 protocol-recovery contract tests `include_str!`-ed `engine.rs` and
asserted the fake-wrapper markers (`[TOOL_CALL]`, `<function_calls>`,
…) appeared as string literals in that file. The recent engine
decomposition refactor (commits f0fad7aa..a64bc9bb) split engine.rs
into `engine/streaming.rs`, `engine/turn_loop.rs`, `engine/dispatch.rs`,
`engine/tool_setup.rs`, `engine/tool_execution.rs`,
`engine/tool_catalog.rs`, `engine/context.rs`, `engine/approval.rs`,
`engine/capacity_flow.rs`, and `engine/lsp_hooks.rs`. The marker
literals followed the code into those files, so the original
single-file `include_str!` no longer saw them and 4 protocol-recovery
tests went red.
Switch to an `ENGINE_SOURCES: &[&str]` array of `include_str!`s across
engine.rs + every submodule, with a small `any_engine_source_contains`
helper. Test bodies are otherwise unchanged. The file-size sanity
check on `engine.rs` (>10_000 bytes) still passes — engine.rs is still
~65k bytes after the refactor.
Same regression coverage as before; just survives the new file layout.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
@whereiszebra (issue #258) downloaded just \`deepseek-macos-arm64\` from
the GitHub Release, ran it, hit:
error: deepseek-tui binary not found at /path/to/deepseek-tui.
Build workspace default members to install it, or set DEEPSEEK_TUI_BIN
to its absolute path.
…spent 11 minutes figuring out they also needed \`deepseek-tui-macos-arm64\`
sitting next to it, and self-closed with: "Release page does not document
that both deepseek-macos-arm64 and deepseek-tui-macos-arm64 must be
downloaded together."
The dispatcher's error was the wrong message for the population that hits
it most often — direct GitHub Release downloaders. "Build workspace default
members" is meaningless if you didn't clone the repo. \`DEEPSEEK_TUI_BIN\`
is also not what they need.
New message lists the three concrete install paths that actually work for a
fresh user — npm, cargo, or grab BOTH binaries from the same release
page — and keeps the env var override as a final fallback for power
users. No logic change; just better text. Existing
\`locate_sibling_tui_binary_honours_env_override\` test still passes.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The tests set \$HOME to drive `dirs::home_dir()`. On Unix that's the
contract dirs uses; on Windows dirs reads %USERPROFILE% first, so
setting HOME has no effect and the tests fail.
The `display_path` function itself is platform-identical — it
delegates to `dirs::home_dir()` for the home prefix and uses
`std::path::MAIN_SEPARATOR` for the separator after the tilde. The
contraction logic is exercised on macOS/Linux which is sufficient
coverage for an abstraction whose platform detail is delegated.
If we want Windows-specific assertion coverage in the future, it should
either set USERPROFILE alongside HOME or accept an injected home dir.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
CI on PR #256 flagged two minor lint hits in the privacy lane:
- skills/mod.rs: rustfmt wanted the new regression test's
`let rendered = …` line collapsed to one chain.
- main.rs:1614: `selected_skills_dir` is already `&PathBuf`, so
passing `&selected_skills_dir` is a `&&PathBuf` and clippy's
`needless_borrow` triggers under `-D warnings`.
No behavior change; same coverage and outputs. Re-runs locally:
cargo fmt --all -- --check → clean
cargo clippy --workspace --all-targets --all-features --locked -- -D warnings → clean
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Anywhere the TUI, doctor stdout, setup stdout, or onboarding shows a
file path, it used to print the absolute form (e.g. /Users/<name>/...).
On macOS/Linux the home-directory segment reveals the OS account name,
which is often the same as a public handle — undesirable for users who
share screenshots, screencasts, or paste doctor output into a public
help request.
Adds `crate::utils::display_path` that contracts a leading $HOME to `~`
and falls through unchanged otherwise. Used at every viewer-visible site:
doctor: workspace, config.toml, MCP config, all skills dirs,
selected skills dir, tools dir, plugins dir
setup: workspace, skills/tools/plugins paths and status output
TUI: context inspector header, trust-directory onboarding,
shell-job cwd (sidebar + detail pager), subagent task header
Persisted state, audit log, session checkpoints, and LLM-bound system
prompts intentionally keep the absolute path — those need full fidelity
to resolve correctly across processes and the LLM provider sees
absolute paths anyway by virtue of the workspace summary.
`display_path` has 4 tests covering: home contraction, bare-`~` for
home itself, untouched-when-unrelated, and a username-prefix regression
guard (so `/Users/alice2/...` doesn't get rewritten when $HOME is
`/Users/alice`).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`render_available_skills_context` rendered each skill's file path as
`<skills_dir>/<frontmatter-name>/SKILL.md`. The directory name and the
frontmatter `name` can differ — community installs and manually-placed
skills routinely have this drift — and when they do, the model is told
the file lives at a path that does not exist, so it can't open the
SKILL.md it needs to actually use the skill.
`Skill` now carries a `path: PathBuf` populated by `discover()` from the
real directory entry. Renderer uses it directly. Adds a regression test
that creates a skill at `weird-dir-name/SKILL.md` with `name: friendly-name`
and asserts the rendered prompt contains the real path and not the
fabricated one.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Acceptance list called for tests of no-config / healthy / disabled /
failed servers. Healthy and failed already had a single dense
test (`command_palette_includes_mcp_discovery_and_failed_servers`);
no-config is implicit in the existing call sites that pass `None`
for the snapshot. Disabled was the actual gap — adds one focused
case asserting the `[disabled]` state tag appears in the rendered
description so users can see disabled servers in the palette
without opening the MCP manager.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Surfaces the deepseek-tui-cli crates.io version next to the existing
CI and npm badges in both English and Simplified Chinese READMEs.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The architecture promises that session_manager, runtime_threads, and
task_manager reject persisted state from a newer schema_version on
load, so a downgraded binary fails loud instead of silently truncating
or corrupting data. Existing tests covered:
- session_manager::test_checkpoint_rejects_newer_schema
- task_manager (newer task schema rejection)
- runtime_threads::store_load_thread_rejects_newer_schema_version
Adds the missing coverage for the other persistence paths:
- session_manager::test_load_session_rejects_newer_schema
- session_manager::test_load_offline_queue_rejects_newer_schema
- runtime_threads::store_load_turn_rejects_newer_schema_version
- runtime_threads::store_load_item_rejects_newer_schema_version
Each writes a JSON file with schema_version = CURRENT + 1 (or 999),
loads through the public API, and asserts the error message contains
"newer than supported".
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The render-skills test asserted `rendered.contains("test-skill/SKILL.md")`
which only matched on Unix; Windows uses backslashes via Path::display(),
so the assertion failed only in CI on windows-latest.
Build the expected substring through PathBuf::display() so the assertion
matches the platform-correct separator.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Bumps workspace, all internal path-deps, and npm wrapper (version +
deepseekBinaryVersion) from 0.8.1 → 0.8.2. Lockfile re-locked offline
to keep the registry index untouched.
Triggers auto-tag.yml on push, which creates v0.8.2 and fires
release.yml to build cross-platform binaries and draft the GitHub
Release. npm publish remains manual per CLAUDE.md release runbook.
Note: npm registry already has 0.8.2 published (with binaryVersion
0.8.1 from an earlier checkpoint). That release keeps working unchanged
because v0.8.1 binaries stay on GitHub. Repo state aligns to 0.8.2 so
the version-drift gate passes; next npm publish (which will need to be
0.8.3 since 0.8.2 is taken) will pick up binaryVersion=0.8.2 and pull
the new binaries.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
5770a574 added crates/tui/src/bin/deepseek.rs as a shim that calls
deepseek_tui_cli::run_cli() so `cargo install deepseek-tui` would also
install the canonical `deepseek` command. But the cli crate already
declares an identically-named bin target, so workspace builds emit two
artifacts to target/release/deepseek(.exe) -- cargo prints `output
filename collision` and on Windows the second linker hits LNK1104:
cannot open file deepseek.exe (the first hold has not released).
The cli crate stays the single source of `deepseek`. Workspace default
members still produce both binaries (deepseek from cli, deepseek-tui
from tui), no collision. Cargo install path: `cargo install
deepseek-tui-cli` for the canonical `deepseek` command, `cargo install
deepseek-tui` for the TUI binary; npm wrapper unaffected.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Add a model-visible skills block to the system prompt (progressive
disclosure: lists name/description/path, never inlines SKILL.md bodies)
with a 12k-char prompt budget and a 512-char per-description cap.
EngineConfig gains skills_dir, threaded through the three construction
sites (TUI app, exec agent, runtime thread manager).
README skills section is rewritten to document the discovery order,
the SKILL.md frontmatter contract, and the install/update/uninstall/
trust commands. Adds Simplified Chinese README cross-link and full
README.zh-CN.md translation (DeepSeek went viral in CN -- discoverability
matters).
Tests cover happy path, empty/missing dir → None, oversize description
truncation with U+2026 marker, internal-whitespace collapse, and the
overflow-budget omission notice.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The wrapper re-downloaded the SHA-256 manifest from the GitHub release on every
invocation of `deepseek` / `deepseek-tui`, so any GitHub flake, captive portal,
proxy, or offline state broke every command — not just install.
Now ensureBinary returns immediately when the binary exists and its `.version`
marker matches. The manifest fetch is lazy and only runs when a download is
actually needed (first install or DEEPSEEK_TUI_FORCE_DOWNLOAD=1).
Bumps wrapper to 0.8.2; deepseekBinaryVersion stays on 0.8.1 (no new Rust
release required).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Bumps the workspace/npm wrapper to 0.8.0 and fixes completed background shell jobs retaining live process handles, which could cause Too many open files, checkpoint save failures, shell spawn failures, and lag around send/close/Esc. Also includes Windows REPL bootstrap timeout hardening and Cargo/TUNA mirror install docs.
Includes:
- Post-turn freeze fix (reorder maybe_advance_cycle before TurnComplete)
- Enter/steering fix (QueueFollowUp when model is streaming)
- Esc fanout hardening (idempotent finalize methods)
- cargo fmt pass on new code
- CHANGELOG, README, and version bump across workspace + npm
- fix(#234): reorder cycle advancement before TurnComplete so the engine
loop doesn't block the terminal after the turn signal. User sees the
'↻ context refreshing...' status chip during briefing generation
instead of a frozen terminal with no feedback.
- fix(#250): Enter during streaming queues a follow-up (visible queued
text) instead of claiming to 'steer' a message that never reaches the
model. During tool-execution phases Enter correctly steers the active
turn via rx_steer, which is already drained before each API call.
- fix(#243): hardened Esc during sub-agent fanout — added idempotency
test proving finalize_active_cell_as_interrupted is safe when
TurnComplete arrives after Esc.
- close(#249): unicode search panic fix confirmed in v0.7.8, closing.
- feat: both fixes implemented by live sub-agents (agent_spawn) —
proving the sub-agent system works end-to-end.
* wip(v0.7.7): handoff baseline of partial sub-agent stabilization
Captures uncommitted work-in-progress on the v0.7.7 stabilization lane
so subsequent fixes have a stable starting point. Subsequent commits
finish the canonical SubAgentJob/SwarmJob model, fix sidebar/transcript/
footer agreement, copy/paste/cancel contract, checklist rendering, shell
summary preservation, monotonic spend, and version provenance.
Refs #235#236#237#238#239#240#241#242#243#244#245
* release: bump workspace version to 0.7.7 (#245)
Refs #245
* fix(v0.7.7): canonical swarm card binding, monotonic spend, checklist + shell summary
- Add `swarm_card_index: HashMap<swarm_id, history_index>` so overlapping
fanouts each project to their own FanoutCard. Eliminates the screenshot
contradiction where a stale background swarm's progress clobbered a
newer card (#236, #238).
- Suppress fanout-class tools (`agent_swarm`, `spawn_agents_on_csv`,
`rlm`, `agent_spawn`) from `active_tool_status_label` so the footer no
longer reports "tool agent_swarm · 1 active" while sidebar+card show
the actual worker counts (#236, #238).
- Add `App::displayed_session_cost` + `displayed_cost_high_water` so the
visible session+sub-agent total is monotonic across reconciliation
events (cache discounts, provisional → final). New tests: monotonicity
under negative reconciliation; duplicate dedup keeps display steady (#244).
- Preserve high-signal summary lines from the truncated tail of shell
output: `test result:`, `failures:`, `error[E…]`, `Finished`,
`Compiling`, panic markers. Stops the agent re-running cargo gates
just to see pass/fail under truncation (#242).
- Render `checklist_write` / `todo_*` results as a purpose-built
checklist card with completed/total + percent header, per-item status
markers, and a collapsing affordance for long lists. Plumbed through
the existing `GenericToolCell` so no new variant threading is needed (#241).
Refs #236#238#241#242#244
* fix(v0.7.7): Esc clears active tool entries optimistically (#243)
When Esc cancels the foreground turn we now finalize the active cell
immediately rather than waiting for the engine's TurnComplete echo to
drain. This stops the footer "tool ... · X active" chip from briefly
contradicting the cancelled state, and frees the composer for the next
message.
Background `block:false` swarms are intentionally NOT killed here — they
remain durable, tracked through `swarm_jobs` and `swarm_card_index` so
their FanoutCard updates as workers land. Subsequent `swarm_status` /
`swarm_result` / `swarm_cancel` tool calls see the canonical store.
New focused test verifies: after Esc, `active_cell` is None, the
background swarm record is preserved, and `is_loading` is cleared so
the composer can submit immediately.
Refs #243
* fix(v0.7.7): Windows .exe lookup + post-turn snapshot detach (#247, #234)
#247 — npm-distributed Windows package failed at runtime because the
Rust dispatcher's `delegate_to_tui` / `delegate_simple_tui` looked for a
sibling named exactly "deepseek-tui", while the actual file shipped by
`scripts/install.js` is `deepseek-tui.exe`. Replace both lookups with
`locate_sibling_tui_binary`, which:
- Honours `DEEPSEEK_TUI_BIN` for explicit overrides
- Tries `deepseek-tui{EXE_SUFFIX}` first (`.exe` on Windows, "" elsewhere)
- Falls back to suffix-less `deepseek-tui` on Windows so users who
applied the issue's manual workaround still launch successfully
- Emits a platform-correct error path in the bail message
Tests: `sibling_tui_candidate_picks_platform_correct_name`,
`sibling_tui_candidate_windows_falls_back_to_suffixless` (windows-only),
`locate_sibling_tui_binary_honours_env_override`.
#234 — Detach the post-turn workspace snapshot so `git add -A && git
commit` no longer pins the engine loop after `Event::TurnComplete`.
The snapshot still runs on `tokio::task::spawn_blocking`, but the
engine no longer awaits its `JoinHandle`, so the UI accepts input
(text, copy, paste, selection) without waiting for the bookkeeping to
finish. Cycle advance and pre-turn snapshot remain awaited — they are
correctness-sensitive and the cycle path already emits a status chip
("↻ context refreshing…") so the user has visible feedback.
Refs #234#247
* chore(v0.7.7): bump npm package version 0.7.6 → 0.7.7
Required by `scripts/release/check-versions.sh` ("Version drift" CI
gate); the workspace was bumped to 0.7.7 but `npm/deepseek-tui/package.json`
still reported 0.7.6, blocking PR #246 from going green.
Refs #245
- Bump workspace version to 0.7.6 (Cargo.toml + all crate internal dep pins)
- Bump npm wrapper version and deepseekBinaryVersion to 0.7.6
- Add v0.7.6 changelog entry: localization, paste burst, history search,
pending input preview, grouped /config editor, searchable help overlay,
Alt+↑ edit-last-queued, composer attachment management
- Update README with v0.7.6 features (localization, paste, history search)
- Archive v0.7.5 implementation plan to docs/archive/
- Update Cargo.lock
Hunter Bown