Two items added in this stabilization pass that weren't yet in the
changelog:
- SessionManager::prune_sessions_older_than (#406 phase-1)
- doctor --json memory block (#489 follow-up)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
#406 asks for an auto-archive system for old session state. The full
design needs prior-art survey + retention-policy decisions that are
explicitly out of scope for v0.8.8. This commit ships the **building
block** — a tested public method that removes session files older
than a given Duration — so phase 2 can wire it into a config-knob
boot prune without re-litigating the implementation.
\`\`\`rust
pub fn prune_sessions_older_than(
&self,
max_age: std::time::Duration,
) -> std::io::Result<usize> { ... }
\`\`\`
Behaviour:
- Compares against the metadata's \`updated_at\` (not filesystem
mtime — the user may have rsynced \`~/.deepseek\`; fs mtimes can
lie about real session age).
- Returns the count pruned; failures on individual files are
logged at WARN and skipped, not propagated, so one bad record
doesn't block the rest.
- Skips the checkpoint subdirectory entirely. Top-level
\`<session_id>.json\` files are the only candidates;
\`checkpoints/latest.json\` and friends are owned by the
checkpoint subsystem and live with stricter durability rules.
- Marked \`#[allow(dead_code)]\` with a comment pointing at #406
phase 2 — the helper exists today, the production wiring lands
next.
### Tests
5 new tests in \`session_manager::tests\`:
- empty directory returns zero
- all-fresh records survive
- all-stale records get removed
- mixed directory removes only the stale ones
- checkpoint subdirectory is left alone (file untouched, count is
still 1 for the top-level stale record)
### Verification
cargo fmt --all -- --check ✓
cargo clippy --workspace --all-targets --all-features --locked -- -D warnings ✓
cargo test --workspace --all-features --locked ✓ 1861 + supporting
Refines #406 — phase 1 (helper + tests) shipped. Issue stays open
for the v0.8.9 phase-2 work that decides the retention policy and
boot-prune wiring.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Catalogues the 24 v0.8.8 issues shipped across PRs #514 / #515 /
#517 / #518 / #519 in the standard Keep-a-Changelog format,
organized into Added / Changed / Fixed buckets with issue
cross-references.
Captured:
- Added (10): memory MVP + remember tool, inline diff, OSC 8,
retry banner, MCP chip, project config overlay,
Implementer/Verifier roles, two doc files, competitive analysis
- Changed (8): sub-agent cap, RwLock, output summarization,
agent_list session boundary, concise todos, compact agent_spawn,
Plan panel, RLM family
- Fixed (8): self-update arch, Option+Backspace word delete,
offline queue scope, display_path Windows, footer theme color,
panic-exit keyboard flags, CI workflow cleanup, plus the v0.8.8
release-base fix
Plus a Releases callout reminding maintainers that the npm wrapper
publish stays manual and the GitHub release automation depends on
the \`RELEASE_TAG_PAT\` secret.
The dated section header lands when the actual version-bump
commit fires \`auto-tag.yml\`. This commit just populates the
[Unreleased] body so contributors get a clean summary while the
PRs are still in review.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Operators ask "is memory on?" and "where does it live?" without
wanting to boot the TUI. Adds a \`memory\` block to the JSON doctor
report:
\`\`\`json
"memory": {
"enabled": false, // honours DEEPSEEK_MEMORY env
"path": "/Users/you/.deepseek/memory.md", // expanded path
"file_present": false // does the file exist on disk?
}
\`\`\`
The \`enabled\` field reads \`DEEPSEEK_MEMORY\` directly so it stays
correct on this stabilization branch even though the dedicated
\`Config::memory_enabled()\` accessor lives on the memory-MVP branch
(#518). When both PRs land, the duplicated env-parse can collapse to
a single method call — TODO comment marks the spot.
Verified:
- \`deepseek doctor --json\` shows \`enabled: false\` by default
- \`DEEPSEEK_MEMORY=on deepseek doctor --json\` shows \`enabled: true\`
- All gates green (1856 main + supporting)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The memory MVP shipped in PR #518 added three surfaces (\`# \` quick-add,
\`/memory\` slash command, \`remember\` model tool) plus the opt-in
toggle, but the only user-facing reference today is the one-line
mention of \`memory_path\` in CONFIGURATION.md and the \`#489\` cross-
reference in SUBAGENTS.md. This commit adds a dedicated user-facing
doc covering the whole feature.
Coverage:
- Why opt-in by default
- How to enable (env var + config.toml)
- What the system prompt block looks like
- Three ways to add to memory:
1. \`# foo\` composer prefix (#492)
2. \`/memory\` slash command (#491) — show / path / clear / edit
3. \`remember\` tool (#489) — model-callable, auto-approved
- File format — timestamped Markdown bullets, hand-editable
- What stays out of memory — secrets / transient state / long
instructions / conversation snippets
- Privacy and scope — per-user, never uploaded, provider-agnostic
- Configuration reference — settings table with defaults and overrides
Cross-link added in CONFIGURATION.md so the existing \`memory_path\`
mention now points at the full feature doc.
No Rust code changed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The role taxonomy expansion in #404 added Implementer + Verifier as
distinct postures alongside General / Explore / Plan / Review /
Custom. The issue body explicitly lists \`docs/AGENTS.md or
docs/SUBAGENTS.md\` as a target file; this commit creates that file.
Coverage:
- Role taxonomy table — stance, write/shell access, typical use per
role.
- "When to pick which role" — narrative guidance the model can read
if the role choice isn't obvious.
- Alias map — every accepted spelling routed to a canonical role,
matching what \`SubAgentType::from_str\` accepts.
- Concurrency cap — the 10-by-default value, the
\`[subagents].max_concurrent\` knob, and the running-only
semantics (#509).
- Lifecycle — Pending → Running → terminal states, plus
\`Interrupted\` after a process restart.
- Session boundaries (#405) — \`session_boot_id\` mechanics,
default current-session filter, \`include_archived=true\` escape
hatch, pre-#405 record handling.
- Output contract — the SUMMARY/CHANGES/EVIDENCE/RISKS/BLOCKERS
format every sub-agent must produce.
- Memory + \`remember\` integration (#489) — sub-agents inherit the
parent's memory file when memory is enabled and can append durable
notes.
- Implementation notes — source path, persisted state file,
is_running semantics, RwLock pattern.
Cross-link added in \`docs/TOOL_SURFACE.md\` so the sub-agent section
points to this doc.
No Rust code changed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The "Invalid sub-agent type" error message lists the accepted type
strings so the model can self-correct. The list still showed the
original 5 names plus their aliases — adding the new types' canonical
names and aliases keeps the error helpful when the model misspells.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The existing taxonomy (General / Explore / Plan / Review / Custom)
covered "do something" / "go look" / "think first" / "grade work" /
"explicit allowlist" but had no distinct posture for two of the most
common patterns:
- **Implementer** — "land this change with the minimum surrounding
edit". Distinct from General's flexible posture and Plan's
no-execution stance.
- **Verifier** — "run the test suite and report pass/fail with
evidence". Distinct from Review's read-and-grade stance.
Per the issue body's guidance ("avoid a large undifferentiated role
list") this PR adds **only those two**. Researcher and ReleaseManager
stay open as v0.8.9 candidates if user demand surfaces.
### What's wired
- Two new \`SubAgentType\` variants: \`Implementer\`, \`Verifier\`.
- New prompt constants \`IMPLEMENTER_AGENT_PROMPT\` and
\`VERIFIER_AGENT_PROMPT\` with role-specific posture (write-the-
minimum-edit / run-the-tests-don't-fix-them).
- \`from_str\` accepts the obvious aliases:
\`implementer\` / \`implement\` / \`implementation\` / \`builder\`
for Implementer; \`verifier\` / \`verify\` / \`verification\` /
\`validator\` / \`tester\` for Verifier. Case-insensitive like the
existing aliases.
- \`as_str\` round-trips: every variant's label parses back to the
same variant via \`from_str\`. Test pins this so a future role
addition can't accidentally drop the round-trip.
- Deprecated \`allowed_tools()\` advisory list updated:
Implementer carries write/edit/patch + shell + checklist tools;
Verifier carries read + shell + run_tests + diagnostics but
**no** write tools.
- \`crates/tui/src/tui/views/mod.rs\` agent-type sort order extended
to include the new variants; \`format_agent_type\` now delegates to
\`as_str\` so future additions land in one place.
### Tests
- 6 new tests in \`tools::subagent::tests\`:
- alias coverage for Implementer (4 aliases) and Verifier (5)
- round-trip via \`as_str\` for **all** variants — guards against
forgetting to register a new variant in either direction
- distinct-prompts guard: catches the copy-paste bug where two new
variants would inherit the same prompt as General
- Implementer's advisory list contains write tools
- Verifier's advisory list contains test-runner tools but NO writes
### Verification
cargo fmt --all -- --check ✓
cargo clippy --workspace --all-targets --all-features --locked -- -D warnings ✓
cargo test --workspace --all-features --locked ✓ 1856 + supporting
Closes#404 (minimal-taxonomy interpretation per the issue body).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The Plan panel used to render a blunt "No active plan" line whenever
the model hadn't called \`update_plan\` yet — even when the panel had a
goal or a cycle counter to show above it. That made the panel look
broken on every fresh session.
Per the audit posted on the issue (option 1 of three), this PR keeps
the Plan panel as the **single source of truth for the \`update_plan\`
tool's output** and drops the placeholder when the panel is fully
quiet, replacing it with a one-line hint that explains what the panel
tracks. When a goal or cycle counter is already showing above, the
empty-steps body collapses entirely so the section doesn't look
ambiguous next to populated content.
The panel's role is documented in a doc comment on
\`render_sidebar_plan\` so the next person doesn't have to re-derive it
from the issue tracker.
### What's wired
- \`render_sidebar_plan\` checks "anything above" (goal +
cycle_count) before deciding whether to emit the empty-state hint.
If either is showing, the empty steps body adds nothing.
- New \`plan_panel_empty_hint(width)\` helper composes the hint
string with proper width-aware truncation.
- New module-level doc comment explains the Plan panel's role
(update_plan output + /goal + cycle counter) and contrasts it
with Todos.
### Tests
- 3 new tests in \`tui::sidebar::tests\`:
- hint mentions \`update_plan\` and \`/goal\` so the user
understands what populates the panel
- hint truncates correctly to a 16-column sidebar without
overflowing
- regression guard: the hint never re-introduces "no active plan"
wording
### Verification
cargo fmt --all -- --check ✓
cargo clippy --workspace --all-targets --all-features --locked -- -D warnings ✓
cargo test --workspace --all-features --locked ✓ 1850 + supporting
Closes#408 (option 1 of the audit). Options 2 (merge with todos)
and 3 (move to top-row chip) remain open as v0.9.0 design candidates
once #504's right-panel work is on the table.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
\`agent_list\` previously surfaced every persisted sub-agent the manager
had on disk — including agents from prior sessions still hanging around
in \`subagents.v1.json\`. In long-lived sessions this piled up and the
model had to reason past 13 listed agents when only four were live.
Now: each \`SubAgentManager\` assigns a fresh \`session_boot_id\` at
construction. Every agent it spawns is stamped with that id, persisted
alongside the existing fields, and reloaded as-is by future managers.
At list time the manager classifies any agent whose stamp doesn't match
the current id (or that loaded with no stamp at all from pre-#405
records) as \`from_prior_session\`.
\`agent_list\` defaults to the current-session view: prior-session
agents are dropped from the listing **unless** they're still
\`Running\` (which can happen after a process restart — the manager
flagged them as \`Interrupted\` on load). Pass \`include_archived=true\`
to surface every record, with the \`from_prior_session\` flag on each
result so the model can tell live vs archived apart at a glance.
### What's wired
- \`SubAgentManager::current_session_boot_id\` — UUID-derived,
generated in \`new\`.
- \`SubAgent::session_boot_id\` and \`PersistedSubAgent::session_boot_id\` —
the latter \`#[serde(default)]\` for backward compat (pre-#405 records
load with empty string and classify as prior-session).
- \`SubAgentResult::from_prior_session\` — \`#[serde(default,
skip_serializing_if = "is_false")]\` so today's clients reading
archived snapshots see the field, while default-false snapshots
serialize without an extra noisy key.
- \`SubAgentManager::list_filtered(include_archived)\` — the new
user-facing API. \`SubAgent::snapshot()\` still defaults the flag
to \`false\`; \`snapshot_for_listing\` (manager-only) fills it in.
- \`AgentListTool\` accepts \`include_archived: bool\` (default
false) and routes through the filter. The model-facing description
explains the behaviour.
### Tests
- \`session_boot_ids_are_unique_per_manager\` — each manager mints
its own id.
- \`list_filtered_drops_prior_session_terminals_by_default\` — the
three-agent matrix (current running / prior completed / prior
running) collapses to the right two with the right flags.
- \`list_filtered_with_include_archived_returns_everything\` —
archived view returns all records with correct flags.
- \`agents_with_empty_boot_id_classify_as_prior_session\` — pre-#405
records load and behave as expected.
- \`persist_round_trip_preserves_session_boot_id\` — write with one
manager, reload with a fresh manager, confirm the agent flips to
prior-session in the new manager's view.
### Verification
cargo fmt --all -- --check ✓
cargo clippy --workspace --all-targets --all-features --locked -- -D warnings ✓
cargo test --workspace --all-features --locked ✓ 1847 + supporting
Closes#405
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The transcript previously rendered each \`agent_spawn\` call as a 3-4 line
generic tool block (header + name kv + args summary + output JSON) AND
its companion \`DelegateCard\` (header + live action lines + summary).
Four parallel spawns produced ≥16 lines of nearly-identical scaffolding
before the model said anything useful.
In live mode \`agent_spawn\` now renders as a single header line —
\`◐ delegate · agent-abc12 [running]\` — with the agent id pulled from
the tool's JSON output. The DelegateCard remains the source of truth
for live action progress and the final summary; the generic block is no
longer fighting it for attention.
Transcript-mode replay (used by \`/pager\`, session export, and the
detail pager opened with Alt+V) keeps the full multi-line block so
debug history is preserved.
### What's wired
- \`GenericToolCell::lines_with_mode\` early-returns
\`render_agent_spawn_compact\` when \`name == "agent_spawn"\` and
\`mode == RenderMode::Live\`.
- New \`render_agent_spawn_compact\` builds one header line with the
family glyph (Delegate), the spawned agent id (or \`…\`
placeholder while the spawn is in flight), and the tool status.
- New \`extract_agent_id(output)\` parser: deterministic, allocation-free
string scan for \`"agent_id"\` → quoted value. Avoids dragging serde
into a render hot path.
### Tests
- 4 \`extract_agent_id\` tests: typical JSON, extra whitespace, missing
key (None), empty string id (None).
- 4 render tests: live one-liner contains agent id + status with no
args/name kv leaking, pending render uses \`…\` placeholder,
transcript mode keeps the full block, non-spawn tools (read_file)
still render their normal multi-line block.
### Verification
cargo fmt --all -- --check ✓
cargo clippy --workspace --all-targets --all-features --locked -- -D warnings ✓
cargo test --workspace --all-features --locked ✓ 1842 + supporting
Closes#409
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When the model fires \`todo_update\` / \`checklist_update\` repeatedly
during a long run, the live transcript previously dumped the full
checklist card (header + every item + progress) on every call. In
sessions with 20+ items and a dozen status flips the same item list
appears over and over, drowning the actual work.
Now: when a checklist update output starts with the
"Updated todo #N to STATUS" prefix the tool already emits, the live
renderer shows a compact one-line state-change card —
\`Todo #N: <title> → STATUS\` — plus a \`M/N · pct%\` summary in the
header and a \`N items (Alt+V for full list)\` affordance underneath.
The full item list is still reachable via the existing detail pager.
Falls back to the full-card render path for:
- \`todo_write\` / \`checklist_write\` (no "Updated" prefix — first
emission of the list)
- transcript-mode replays (the user wants the full snapshot when
scrolling history)
- malformed prefixes (parse failure → fall through, never crash)
### What's wired
- New \`parse_update_prefix(output)\` parser handles both
\`Updated todo #N to STATUS\` and \`Updated checklist #N to STATUS\`
forms.
- New \`render_checklist_change_card\` builds the compact card. Looks
up the title from the snapshot's items array (id is 1-indexed),
falls back to \`(missing title)\` if the id is out of range.
- \`try_render_as_checklist\` calls the change-card path only in
\`RenderMode::Live\` and only when the parser matches. Pre-existing
cases (writes, transcript replay) keep the full-card behavior.
### Tests
- 4 parser tests: todo form, checklist form, write outputs falling
through, malformed prefixes falling through.
- 2 renderer tests: compact card shows only the changed item (with
assertions that other titles do NOT appear), missing-title path.
### Verification
cargo fmt --all -- --check ✓
cargo clippy --workspace --all-targets --all-features --locked -- -D warnings ✓
cargo test --workspace --all-features --locked ✓ 1834 + supporting
Closes#403
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The project-config overlay (`<workspace>/.deepseek/config.toml` merged
on top of the user's global `~/.deepseek/config.toml`) was already
wired but only carried four string fields: model, api_key, base_url,
reasoning_effort. The use cases users actually file under #485 — "this
repo wants a different sandbox / approval policy / MCP server set / hard
sub-agent cap" — weren't covered.
### What ships
Adds the following keys to the project overlay, all merged with
identical "non-empty wins" semantics for strings:
- `provider` — pick a different backend per repo (e.g. `nvidia-nim` for
an enterprise repo, `deepseek-cn` for a CN-team repo).
- `approval_policy` — `never` / `on-request` / `untrusted` for repos
with strict policies.
- `sandbox_mode` — `read-only` / `workspace-write` / `danger-full-access`.
- `mcp_config_path` — per-repo MCP server set without touching the
user's global file.
- `notes_path` — keep notes in-repo for projects where the notes tool
is part of the dev workflow.
Plus two non-string fields:
- `max_subagents` (positive integer; clamped to `1..=MAX_SUBAGENTS=20`).
- `allow_shell` (bool).
### What stays user-global
`skills_dir`, `hooks`, `[capacity]`, `[retry]`, `[memory]`, etc. — those
are user-shaped settings, not repo-shaped. If a future use case
demands per-project values for any of them, a follow-up PR can extend
the overlay rather than letting the boundary blur.
### Tests
- 8 new tests in `project_config_tests` covering: provider+model,
approval+sandbox, max_subagents+allow_shell, max_subagents
clamping, negative-max_subagents rejection, missing config file
pass-through, malformed TOML pass-through, and empty-string
no-op.
### Docs
- New "Per-project overlay (#485)" section in `docs/CONFIGURATION.md`
with a table of supported keys and the rationale for which fields
stay user-global.
### Verification
cargo fmt --all -- --check ✓
cargo clippy --workspace --all-targets --all-features --locked -- -D warnings ✓
cargo test --workspace --all-features --locked ✓ 1828 + supporting (was 1820)
Closes#485
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds a small `MCP M/N` chip to the footer's right-side auxiliary cluster
so users with MCP servers see at-a-glance health without running `/mcp`.
The chip is color-coded by reachability:
- all configured servers reachable → success (sky)
- some reachable, some failed → warning (amber)
- zero reachable but ≥1 configured → error (red)
- configured but no live snapshot yet → muted (gray, count only)
When zero servers are configured the chip is hidden entirely; users who
don't use MCP see no change.
### What's wired
- New `App::mcp_configured_count`, populated at app boot from
`mcp::load_config(&mcp_config_path)`. Cheap (just reads the JSON
config; no server connections), so it doesn't block startup.
- `app.mcp_snapshot.servers.iter().filter(|s| s.connected).count()`
drives the live-state portion when the user has run `/mcp` at
least once.
- `FooterProps` gains an `mcp: Vec<Span<'static>>` field built by
`footer_mcp_chip(connected, configured)`. Threaded into
`auxiliary_spans` so it participates in the priority-drop pipeline at
narrow widths.
- After any `/mcp` action that returns a snapshot, the count is
refreshed from the snapshot so post-edit state is reflected.
### #499 follow-up: pure render path
Moves the retry-status capture into `FooterProps` (`pub retry:
RetryState`) sampled in `from_app`, instead of pulling from the global
surface inside `render`. The render method is now pure with respect to
its props — fixes a parallel-test race where retry-banner tests and
unrelated footer tests would observe each other's writes through the
process-wide retry surface.
### Tests
- 5 unit tests in `footer_mcp_chip`: hidden when zero, count-only when
no snapshot, success / warning / error colours by reachability.
- Existing retry-banner tests now pin `props.retry` directly rather
than mutating the global surface — no more `test_guard()` needed,
no more parallel-runner flakes.
- All 31 footer tests pass in parallel.
### Verification
cargo fmt --all -- --check ✓
cargo clippy --workspace --all-targets --all-features --locked -- -D warnings ✓
cargo test --workspace --all-features --locked ✓ 1820 + supporting
Closes#502
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When the API client retries a 429 / 5xx / network failure, the TUI
previously went silent during the backoff sleep. The user saw "thinking"
or "ready" with no signal anything was wrong, until the request finally
either succeeded or raised. PR adds a foreground retry banner so the
user sees what's happening and how long until the next attempt.
### What ships
- New `crates/tui/src/retry_status.rs` module exposing a process-wide
`RetryState` (`Idle | Active(banner) | Failed { reason }`) with
`start`, `succeeded`, `failed`, and `clear` helpers. The state is
process-global because the user-facing TUI is one engine per process;
sub-agent retries deliberately don't light up the foreground banner.
- `client::send_with_retry` now flips the state in its retry callback
(`start(attempt+1, delay, reason)`) and on the final outcome
(`succeeded()` on Ok, `failed(reason)` on Err with retries-exhausted,
`clear()` on Err with attempts==1 so non-retryable errors don't pin
the failure row).
- `human_retry_reason` translates the structured `LlmError` into a
short label: rate-limit reasons include the `Retry-After` header
when the upstream provided one ("rate limited (Retry-After 30s)").
- Footer's `render` checks `retry_status::snapshot()` first; when
`Active` it renders `⟳ retry N in Ms — <reason>` in the warning
color; when `Failed` it renders `× failed: <reason>` in the error
color. Banner takes precedence over the toast and the regular
status line.
- `Engine::handle_user_message` calls `retry_status::clear()` right
after emitting `TurnStarted` so the previous turn's failure row
doesn't bleed into a new turn.
### Tests
- 4 unit tests in `retry_status::tests` covering idle default, the
active → succeeded round-trip, the failed-state pin, and a
past-deadline saturation.
- 2 footer rendering tests asserting the banner / failure-row text
appears in the rendered buffer.
- All tests touching the global retry surface serialize through
`retry_status::test_guard()` so cargo's parallel runner can't observe
a torn read.
### Verification
cargo fmt --all -- --check ✓
cargo clippy --workspace --all-targets --all-features --locked -- -D warnings ✓
cargo test --workspace --all-features --locked ✓ 1815 + supporting (was 1809 on stabilization base)
cargo test -p deepseek-tui --bin deepseek-tui --locked retry ✓ 28 passed
Closes#499
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`display_path_with_home` joined the `~` prefix with `MAIN_SEPARATOR_STR`
but called `rest.display()` for the suffix, which preserves whatever
separators the input carried. On Windows that produced mixed-separator
output like `~\projects/foo` for any path that came in with forward
slashes — visible in the tests that #506 added to lock down the
contract (the tests passed locally on Unix but failed on the
windows-latest CI runner).
Walk `rest.components()` and join each `Normal` component with
`MAIN_SEPARATOR_STR`. Pure-Rust, no extra deps, behavior is
byte-identical on Unix because the input separator was already `/`.
Verified locally:
- `cargo test -p deepseek-tui --locked display_path` ✓ (5 passed)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Bundles the v0.8.8 stabilization fixes that were already implemented in the
working tree, plus the workflow/doc reconciliation called out in #507.
### Sub-agent runtime fixes
- **#509** Default sub-agent cap raised to 10 (configurable via
`[subagents].max_concurrent` in `config.toml`, hard ceiling 20). The
running-count calculation now ignores non-running, no-handle, and finished
handles so completed agents stop counting against the cap.
- **#510** `SharedSubAgentManager` is now `Arc<RwLock<...>>`; the read paths
that previously held a `Mutex` for inspection now take a read lock,
eliminating the multi-agent fan-out UI freeze.
- **#511** `compact_tool_result_for_context` summarizes `agent_result` /
`agent_wait` payloads before they are folded into the parent context.
- **#512** RLM tool cards map to `ToolFamily::Rlm` and render `rlm`, not
`swarm`. Stale "swarm" wording cleaned in docs/comments/tests.
- **#513** (foreground stopgap only) Foreground RLM work is visible in the
Agents sidebar projection. Full async RLM lifecycle remains v0.8.9 — the
issue stays open with a refined scope.
### TUI / UX fixes
- **#487** Offline composer queue is now session-scoped; legacy unscoped
queues fail closed.
- **#488** Composer Option+Backspace deletes by word; cross-platform key
routing helpers added.
- **#443/#444** Keyboard enhancement flags pop on normal AND panic exit; the
raw-mode startup probe is now bounded by a configurable timeout.
- **#449** Production footer reads statusline colors from `app.ui_theme`
rather than the bespoke palette.
- **#506** `display_path_with_home` no longer mutates `HOME` in tests; the
flake on shared-env CI is gone.
### Self-update / packaging
- **#503** `update.rs` arch mapping uses release-asset naming (`arm64`/`x64`)
instead of the raw Rust constants. The platform-asset selector also rejects
`.sha256` siblings as primary binaries. Tests now live alongside the source
in `mod tests` (the `#[path]`-based integration test was removed because it
duplicated test runs and forced a `pub(crate)` helper that no real caller
used).
- **`Max 5 in flight` wording updated** in `agent_spawn` description,
`prompts/base.md`, and `docs/TOOL_SURFACE.md` so the model sees the real
default cap (10) and the configuration knob name.
### CI / release docs (#507)
- Pruned three duplicated/dead workflows: `crates-publish.yml`, `parity.yml`,
`publish-npm.yml`. Their gates already run in `ci.yml` for every push/PR.
- `release.yml` build job now allows `parity` to be skipped (it only runs on
tag push), unblocking `workflow_dispatch` reruns. The job still fails
closed on a real parity failure.
- `RELEASE_RUNBOOK.md` reconciled: crate publishing is documented as the
manual `scripts/release/publish-crates.sh` flow (no automated workflow);
references to the deleted workflows removed.
- `CLAUDE.md` notes the `RELEASE_TAG_PAT` requirement for the auto-tag →
release.yml chain (without it, the tag is created but `release.yml` does
not fire) and documents the `workflow_dispatch` parity-skip behavior.
### Docs
- `docs/COMPETITIVE_ANALYSIS.md` added — capability matrix vs OpenCode and
Codex CLI, gap analysis, and recommended implementation order.
### Verification (this branch)
- `cargo fmt --all -- --check` ✓
- `cargo check --workspace --all-targets --locked` ✓
- `cargo clippy --workspace --all-targets --all-features --locked -- -D warnings` ✓
- `cargo test --workspace --all-features --locked` ✓ (1809 + supporting)
- Parity gates ✓ (snapshot, parity_protocol, parity_state)
- `cargo build --release --locked -p deepseek-tui-cli -p deepseek-tui` ✓
- Lockfile drift guard ✓
- `deepseek doctor --json` clean
- `deepseek eval` (offline harness) success=true, 0 tool errors
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
deepseek update fails on every platform because the arch mapping uses
the Rust ARCH constant ('aarch64'/'x86_64') instead of the release
artifact naming ('arm64'/'x64'). Until v0.8.8 ships the fix, users
need to update via npm or cargo.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
GitHub READMEs don't render JS, so use the static shields.io BMC badge
in your custom #5F7FFF color instead of the script tag. FUNDING.yml
adds the native Sponsor button to the repo sidebar.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The selection-tightening from 7125172f restricted copy/select to user
and assistant cell bodies only, which made it impossible to copy text
from system notes, thinking blocks, or tool output. Drop the
body-start gate so the rendered transcript block is selectable in full.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Merge the v0.8.6 feature batch and release hardening.\n\nIncludes the full #373-#380/#382-#402 milestone scope, version bump to 0.8.6, secure /share temp-file handling, Windows-safe self-update replacement, and CI portability fixes.\n\nRemote PR checks passed on the final head before merge.
* feat: add config UI support for TUI and web modes
- Introduced a new `config_ui.rs` module to handle configuration UI for TUI and web.
- Updated `TuiOptions` and `App` structures to include `config_path` and `config_profile`.
- Implemented functions to build and apply configuration documents.
- Added tests to ensure the new configuration UI behaves as expected.
- Integrated web configuration session handling into the event loop.
- Updated various modules to accommodate the new configuration options and UI.
* refactor(tui): remove local path reference for schemaui dependency
Remove the local file system path reference for schemaui in favor of
using the published crate from the registry. This change updates the
Cargo.toml to use only the version specification and adds the source
and checksum information to Cargo.lock.
* fix: add AGENTS.md guide and improve config error handling
- Add comprehensive AGENTS.md file with project instructions for AI
assistants, including build commands, dependencies, and GitHub
operations guidance
- Introduce is_error field to CommandResult struct for better error
tracking
- Refactor config application logic to properly handle errors using
the new is_error flag
- Add test utilities for WebConfigSession to support testing
- Optimize web config event polling by extracting drain logic into
separate function
- Add unit tests for session-only config application and engine sync
requirements
* fix(security): add SSRF protection to fetch_url (#261)
Block private, link-local, and cloud metadata IPs in fetch_url HTTP requests. Co-authored-by: JasonOA888
* test(portability): inject paths instead of mutating HOME (Windows fix)
CI's `Test (windows-latest)` job failed because both my new tests
(composer_history and the spawn_supervised crash-dump test) mutated
HOME to redirect `dirs::home_dir()`. That works on macOS / Linux but
not on Windows, where dirs::home_dir() reads USERPROFILE / queries
SHGetKnownFolderPath rather than HOME.
Fix: refactor both modules to expose path-injecting helpers so tests
never need to touch the env var:
- composer_history: split load_history / append_history into thin
wrappers around load_history_from(&Path) / append_history_to(&Path).
Tests use the *_to / *_from form with a tempdir path.
- utils::write_panic_dump: same pattern — write_panic_dump_to(&Path)
takes the crash dir directly. The spawn_supervised end-to-end test
splits into two: one verifies panic-doesn't-propagate (no on-disk
side effect needed), one verifies write_panic_dump_to writes the
expected log format.
Production callers continue to use the env-driven default (`HOME`/
`USERPROFILE` via `dirs::home_dir()`) so no behavior change. Tests
work identically on every platform now.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(tui): clear chat area each frame so stale cells don't bleed into sidebar
ChatWidget's render path was `Paragraph::new(lines).render(content_area, buf)`
with no Block and no Clear — ratatui's Paragraph only writes cells that
contain text, leaving any cell the current frame's paragraph doesn't
touch holding the *previous* frame's contents. With wide tool output
(`gh pr list`, `git log`) emitting ISO-8601 timestamps like
`2026-05-02T07:29:24Z`, then a subsequent shorter-paragraph frame, the
old timestamp tails (`:24Z`, `7:29:24Z`, etc.) persisted on the right
edge of the chat area, visually colliding with the section headers in
the sidebar (`Plan` rendering as `:24Zan`, `Agents` as `:24Zents`).
Fix: render `Clear` over the full content_area before drawing the
Paragraph. Cheap (one buffer-fill per frame) and guarantees stale cells
can never persist into the next frame's render.
Reported in v0.8.5 testing right after install. The other v0.8.5
bordered widgets (composer, sidebar sections, footer) already render
into a Block with a solid background style, so they were never
affected — only the chat area used a bare Paragraph.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(theme): vendor + theme schemaui to deepseek navy palette (config UI)
The schemaui-0.12.0 crate the contributor brought in via #365 ships
hardcoded Color::Gray / Color::DarkGray / Color::White / Color::Yellow
references across its rendering components. Visually it clashed with
the rest of deepseek-tui — the editor area read as gray-on-black on a
TUI that's otherwise navy ink + sky accents. Two ship-day options
weren't acceptable: defaulting back to the legacy modal lost the new
editor's UX, and living with gray was off-brand.
This commit forks schemaui at 0.12.0 into vendor/schemaui-0.12.0 and
themes the rendering layer to match deepseek-tui's palette. The patch
is wired in via a workspace-level [patch.crates-io] override so the
deepseek-tui Cargo.toml continues to depend on `schemaui = "0.12.0"`
and would automatically resolve back to crates.io if we ever drop the
override (e.g. once upstream lands a ColorTheme API).
Changes inside the vendored fork:
- New `src/deepseek_palette.rs` with the brand RGB values:
SURFACE_INK / SURFACE_RAISED for backgrounds, BORDER_DIM /
BORDER_ACTIVE for chrome, TEXT_PRIMARY / TEXT_MUTED / TEXT_DIM,
ACCENT_SKY / ACCENT_BLUE / ACCENT_PURPLE, and STATUS_OK / WARN /
ERROR. Values mirror crates/tui/src/palette.rs in the workspace.
- `src/lib.rs` exposes the palette module under `cfg(feature = "tui")`.
- `src/tui/view/frame.rs::draw` paints a navy backdrop across the
full frame area before any child widget renders, so any cell that
doesn't get explicitly written reads as ink instead of the terminal
default.
- `tabstrip.rs`, `overlay.rs`, `popup.rs`, `body.rs`, `sections.rs`,
`footer.rs`, `help.rs`, `fields.rs`: every Color::Gray / DarkGray /
White / Yellow / Cyan / Blue / Magenta / Red / Green / LightBlue
swapped out for a deepseek_palette token, plus explicit `bg(...)`
fills on the top-level Block styles and Paragraph wrappers.
- `Cargo.toml` adds an empty `[workspace]` so the vendored crate
builds standalone (its dev-deps don't drift into ours).
Workspace-level changes:
- `Cargo.toml` adds `[patch.crates-io] schemaui = { path =
"vendor/schemaui-0.12.0" }`. Production deepseek-tui builds pick up
the themed fork transparently.
- `.gitignore` excludes `vendor/.../web/ui/node_modules/` (15 MB of
npm artefacts the Rust build doesn't need) and the vendored
Cargo.lock (regenerated locally per build).
Verification:
- cargo build --workspace --all-features: clean
- cargo clippy --workspace --all-targets --all-features --locked: clean
- cargo test --workspace: 1777 passed, 0 failed
- /config inside `deepseek` now opens a navy-themed editor matching
the rest of the TUI; tabs, body panel, footer, popup, and help
overlay all read on brand.
Future work tracked separately: upstream a `with_theme(ColorTheme)`
builder API to schemaui so we can drop the fork. Until then, sync the
fork against new schemaui releases when we want their fixes.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* Revert "feat(theme): vendor + theme schemaui to deepseek navy palette"
This reverts ed597ccc — vendoring 28,913 lines of schemaui to recolor
a config editor was the wrong tradeoff. Maintenance cost for a
cosmetic match wasn't worth it, and the recolor wasn't even fully
working (terminal-default bg kept bleeding through Style::default()
calls in the form fields).
The simpler path: keep the schemaui-driven editor available as
`/config tui` for users who want the form-style UX, but make bare
`/config` open the legacy native modal that already matches the
deepseek-tui navy chrome by inheritance. No fork, no vendored copy,
no ongoing sync burden.
Changes:
- `git rm -r vendor/schemaui-0.12.0/` (28,913 lines gone)
- Drop `[patch.crates-io]` from workspace Cargo.toml — schemaui
resolves back to crates.io v0.12.0 unmodified.
- Drop the corresponding `.gitignore` exclusions (no more vendor dir
to filter).
- `config_ui::parse_mode` default mode flipped from `Tui` to `Native`.
Bare `/config` → legacy navy modal. Explicit `/config tui` → the
contributor's schemaui editor (still available, gray-on-default
chrome, but opt-in). `/config web` and `/config <key>` /
`/config <key> <value>` unchanged.
- Help text updated to list `[native|tui|web]` in that order.
Verified: cargo build / clippy --workspace --all-features --locked
with -D warnings: clean.
The contributor's work (#365) ships and gets credit; users discover
the alternate editor via the help text.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(tui): paint chat area with explicit navy ink instead of Clear
The Clear-instead-of-fill in 0ae2cead reset cells to the terminal's
default background, which read as a brown-gray on most user setups
even though the rest of the TUI chrome is navy. Replace the Clear
with an explicit Block fill at palette::DEEPSEEK_INK, and pass the
same bg through to the Paragraph itself so streamed text cells
inherit ink rather than bouncing back to terminal default.
Net effect: the chat area visually unifies with the sidebar /
composer / footer instead of showing as a contrasting brown-gray
panel in the middle of an otherwise navy frame.
Stale-cell guarantee from #372-followup is preserved — the Block
fills every cell in the area on each frame, so wide tool output
(`gh pr list` ISO timestamps, etc.) still can't bleed past the
current frame's actual text.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(config): update tests for Native default + fix default_model override in session-only apply
- Update test_show_config_defaults_to_native and
execute_config_opens_config_view_action to expect
OpenConfigView (Native) instead of OpenConfigEditor(Tui),
matching the parse_mode default change from ce98f054.
- Fix apply_document bug where default_model was processed
in the main key-value loop after model, causing
set_config_value('default_model') to overwrite the
runtime model. default_model is now only applied when
persist=true, preventing session-only edits from being
silently reverted.
* style: cargo fmt
* chore: remove end-of-night report (session artifact)
---------
Co-authored-by: unic <yuniqueunic@gmail.com>
Co-authored-by: Jason <jason@aveoresearchlabs.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: YuniqueUnic <YuniqueUnic@users.noreply.github.com>
Applies the workspace formatter to the v0.8.5 commits — local builds
ran without `cargo fmt --check` so a few format inconsistencies
slipped through and CI's `parity` job (which runs fmt --check) failed.
Mechanical reflow only; no functional changes.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Workspace + npm wrapper + every internal crate path-dep pin moved from
0.8.4 → 0.8.5. scripts/release/check-versions.sh confirms parity across
the three sources. cargo build / clippy / test all clean.
Pushing this commit to main is the trigger for auto-tag.yml to create
the v0.8.5 tag, which fires release.yml to build the cross-platform
matrix and draft the GitHub Release. The npm publish remains a manual
follow-up (2FA on every publish, no automation token provisioned).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two test fixes uncovered by the full-suite run:
1. composer_history tests were using a module-local mutex to serialize
their HOME env mutation, but other tests in the workspace (config,
commands::restore, etc.) ALSO mutate HOME without that lock. Switch
to the crate-wide `test_support::lock_test_env()` so all HOME-
mutating tests share one mutex.
2. The `prompts::tests::rlm_first_class_guidance_present` test was
pinning the OLD "RLM Is First-Class" framing that #358 deliberately
reframed as "RLM Is a Specialty Tool". Renamed the test to
`rlm_specialty_tool_guidance_present` and updated the assertions to
guard the new framing — so a future encouraging-language regression
lights up CI.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When the user pressed ESC (or Deny / Abort) on an approval prompt, the
TUI correctly told the engine to deny the call. But the model would
often retry the same command — same name, same args, same approval
fingerprint — and the user would see the dialog again, frustrating in
the same way the equivalent yes-yes-yes loop would be.
Symmetric to the existing `approval_session_approved` "always approve"
cache: add `approval_session_denied: HashSet<String>` populated when
the user denies (not when the timeout fired — a timeout might mean
the user stepped away rather than refused). Subsequent ApprovalRequired
events whose approval_key or tool_name match the cache auto-deny via
`engine.deny_tool_call(...)` without re-showing the dialog. Logged via
`tool.approval.auto_deny_session` so the audit log captures the silent
denial.
Closes#360.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Pressing Up-arrow at the composer now recalls submissions from previous
sessions, not just the current one. Implementation:
- New `crates/tui/src/composer_history.rs` module with `load_history()`
+ `append_history()`. Persists to `~/.deepseek/composer_history.txt`
(one entry per line, oldest first). Capped at 1000 entries — entries
older than the cap are pruned at append time so the file never grows
unboundedly.
- `App::new` now seeds `input_history` from the persisted file at
startup, so Up-arrow at first launch shows yesterday's prompts.
- `App::submit_message` mirrors each non-slash submission to the
persisted history. Slash commands and empty/whitespace submissions
are skipped — those don't help recall and would pollute the stream.
- Consecutive-duplicate dedup so re-submitting the same prompt doesn't
bloat the file.
The persisted history is global (not per-workspace) — matches the
arrow-up recall pattern users expect from shells and Claude Code. Per-
workspace scoping is a follow-up if multi-project users find it noisy.
Tests: 6 unit tests cover round-trip, slash-skip, empty-skip,
consecutive-duplicate dedup, cap-pruning, and missing-file safety. The
test module uses an internal Mutex to serialize HOME env mutations so
tests can still run in parallel without stomping each other.
Closes#366.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Markdown tables don't render correctly in a terminal — monospace fonts
plus variable-width content (especially CJK characters) can't reliably
align column borders. Adds an "Output formatting" section to both
base.md and base.txt instructing the model to prefer plain prose,
bulleted/numbered lists, code blocks, or `- **Label**: value` pairs
over tables. If column-aligned data is genuinely necessary, the
guidance asks for narrow, ASCII-only, 2–3 column tables.
Closes#372.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Every persistence layer in crates/tui/src/ already gates `schema_version
> CURRENT_*` to reject newer-than-supported records (good — prevents
silent truncation when an older binary tries to load a v3 file with v4
fields). What was missing: the **forward upgrade path** for older
records. When we bump CURRENT_SESSION_SCHEMA_VERSION from 3 to 4 to
add a field, every v3 session on disk would silently load with the
new field's serde default — which is OK for additions but breaks
catastrophically for renames or shape changes.
This commit lays down the framework:
**`crates/tui/src/schema_migration.rs`** — new module:
- `SchemaMigration` trait. Each persistence domain implements it once
with `CURRENT_VERSION`, `DOMAIN`, and an ordered `MIGRATIONS` list
of `fn(&mut serde_json::Value) -> Result<(), MigrationError>` steps.
Index `i` migrates from version `i+1` to `i+2`.
- `SchemaMigration::migrate(value, from_version)` — runs every required
step, stamping `value["schema_version"]` after each step so a partial
failure leaves a known-state record rather than mixed.
- `MigrationError` — typed error with from/to versions + reason.
- `backup_before_migrate(path, domain)` — creates a `.bak` copy of the
source file before mutation. Errors are warn-logged and ignored
(continues because `write_atomic` is itself crash-safe). The `.bak`
is left on disk as a manual recovery artifact — no automatic GC.
**`schema_migration::registry`** — submodule that registers every
existing persistence domain (session, offline_queue, runtime, task,
automation, automation_run) at its current version with an empty
MIGRATIONS list. No domain has shipped a schema bump yet, so today's
behavior is a no-op. The next bump is now a 4-step recipe:
1. Write the `migrate_<domain>_v<N>_to_v<N+1>` step in this module.
2. Append it to `MIGRATIONS` and bump `CURRENT_VERSION`.
3. Wire `<Domain>Migration::migrate(...)` into the load function in
the owning module.
4. Add a fixture-based integration test.
Tests: 6 unit tests covering no-op, all-steps, partial migration,
newer-than-current rejection, backup creation, and backup-failure
robustness.
Wiring into individual load sites (session_manager, runtime_threads,
task_manager, automation_manager) is intentionally deferred until the
first actual schema bump needs it — wiring without migrations would
add code paths nothing exercises, and the framework is the part that
needs to land before the next bump can ship safely.
Closes#350.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
cargo-machete found 8 direct dependencies that are declared but never
used in the source tree. Removing them tightens the dependency graph
and shrinks Cargo.lock by 40 lines (transitive crate removals where
nothing else pulled them in).
Removed:
- deepseek-core: tokio (the core scaffold doesn't drive any tasks itself)
- deepseek-config: serde_json (TOML-only crate; no JSON serialization)
- deepseek-mcp: deepseek-protocol (proxy boundary doesn't consume protocol types)
- deepseek-app-server: tracing (no tracing! macros in the transport layer)
- deepseek-tui: bytes, csv, deepseek-tui-cli, tokio-stream
- bytes: no Bytes-typed I/O paths in the TUI
- csv: agent_swarm/spawn_agents_on_csv removed in #336/#357
- deepseek-tui-cli: TUI is the runtime, not the dispatcher; no facade calls
- tokio-stream: futures-util::StreamExt is sufficient for our SSE / mpsc paths
Verified by grep across each crate's `src/` — no `use` of the dep, no
fully-qualified path references. cargo build, cargo clippy -D warnings,
and cargo test continue to pass with the slimmed graph.
Closes#341.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The previous rlm prompt guidance ("Treat rlm as a normal reasoning
tool, not a last-resort escape hatch") encouraged the model to reach
for rlm in cases where a direct read_file or focused agent_spawn would
do better. The "RLM Is First-Class" framing was too encouraging given
that rlm is genuinely a specialty tool: it pays off ONLY when the input
can't fit in the model's context window.
Three audit items from #358 addressed:
1. **Reaching for rlm too often.** Reframed as "specialty tool" with
explicit do-not-use-when guidance front-loaded. The decomposition
workflow now says "ONLY when an input genuinely doesn't fit" with
a concrete size threshold (~50K tokens / a whole file / a long
transcript / a multi-document corpus).
2. **Tool description encourages overuse.** The rlm tool's description()
now leads with "DO NOT use this tool when..." (input fits, grep
suffices, short classification, interactive exploration), and only
then describes the legitimate use cases. Adds explicit cost/speed
caveat.
3. **Helpers documented as if they were tools.** Both the rlm tool
description and base.md/base.txt now state plainly: `llm_query`,
`llm_query_batched`, `rlm_query`, `rlm_query_batched` live INSIDE
the Python REPL. They are functions the sub-agent uses, NOT
separately-callable tools the model invokes.
Closes#358.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When the user has typed something into the composer and hits Enter, the
message goes to one of four fates depending on engine state:
- Immediate (idle + online) — most common, sends right away
- Steer (busy + tool execution) — forwards mid-turn
- QueueFollowUp (busy + streaming text) — parks for after TurnComplete
- Queue (offline) — parks on offline queue
Previously the user had no way to tell which would fire BEFORE pressing
Enter. The disposition flips with fast-changing internal state (whether
the model is currently streaming text vs. running a tool, whether
network connectivity has just dropped) and only the post-submit status
toast hinted at the result — which is too late if you wanted a different
behaviour.
Fix: extend the composer's bottom hint line so when the composer has
non-empty content, it shows what Enter will do RIGHT NOW. The hint flips
live with engine state, so the user sees the real behaviour before
pressing Enter:
↵ steer into current turn (sky blue, busy + tool execution)
↵ queue for next turn (muted, busy + streaming)
↵ offline queue (no engine) (warning yellow, offline)
The Immediate case stays unhinted — that's the default and surfacing it
would be noise.
Closes#345.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`SessionManager::list_sessions` previously called
`serde_json::from_reader` to extract just the `metadata` field, which
forced serde to scan every JSON token in the file just to validate
structure — including the entire `messages` and `tool_log` arrays we
were about to discard. For a user with hundreds of long sessions, a
single startup `list_sessions()` was reading and parsing tens of MB of
JSON.
Optimization: read at most 64 KB up front and string-extract the
top-level `metadata` object with a brace-balanced, string-aware scanner.
Real metadata blocks are < 1 KB and always appear before the large
`messages` payload, so the prefix read covers every realistic case.
Falls back to a full-file read only if the metadata block isn't
extractable from the prefix (legacy or oddly-formatted file).
Net: typical session metadata load goes from O(file size) to O(1 KB)
regardless of conversation length, and the disk read is bounded.
Tests:
- extract_top_level_metadata_skips_huge_messages_array — verifies the
scanner correctly extracts metadata from a session whose `messages`
array contains the literal string `"metadata"` in a user message.
- extract_top_level_metadata_handles_braces_inside_strings — verifies
brace-in-string handling so `{` / `}` inside JSON string values
don't throw off the depth counter.
Closes#337.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
After running /logout and entering a new API key, subsequent requests
could still be sent with the old key because the resolution path checked
the OS keyring before the in-memory override. The keyring still held
the old credential, so it shadowed the freshly-typed one.
Three changes:
1. **`Config::deepseek_api_key()` — explicit override is now path 0.**
When `self.api_key` is explicitly set (non-empty, non-sentinel), it
wins over keyring/env/provider-config. This is what the user just
typed, so it should be authoritative. Existing keyring-based flows
are unaffected: users who store their key via `auth set` have
`self.api_key = None`, so path 1 (keyring) still wins for them.
2. **`clear_api_key()` now wipes the keyring + provider-scoped keys.**
Previously only the legacy root `api_key = ...` line was stripped
from config.toml. Now every known provider slot in the OS keyring
(deepseek, nvidia-nim, openrouter, novita, fireworks, sglang) is
deleted, and every `api_key` line nested in a `[providers.<name>]`
table is also stripped.
3. **`/logout` clears the in-memory `Config` too.** The dispatcher
handler in ui.rs::execute_command_input wipes `config.api_key` and
every `config.providers.*.api_key` so a future clone of the
long-lived Config doesn't leak the stale value. The companion
onboarding flow in ui.rs also stamps the new key onto `config`
itself rather than only on a one-shot clone, so subsequent
/provider switches see the new credential.
Test coverage:
- `clear_api_key_strips_root_and_provider_scoped_keys` — verifies all
three credential locations get wiped from a fixture config.toml.
- `deepseek_api_key_prefers_explicit_in_memory_override` — guards the
precedence flip.
- `deepseek_api_key_ignores_sentinel_placeholder` — confirms the
legacy `KEYRING_SENTINEL` placeholder still falls through.
Closes#343.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Completes the panic-safety work #346 started in a8be33b3. Converts every
trivial production tokio::spawn site to spawn_supervised so a panicking
task writes a crash dump to ~/.deepseek/crashes/ and the parent process
stays alive.
Sites converted:
- tools/rlm.rs:190 — RLM progress drain
- tools/subagent/mod.rs:888 — run_subagent_task spawn
- tools/subagent/mod.rs:988 — run_subagent_task resume
- core/engine.rs:744 — sub-agent mailbox drainer
- core/engine.rs:1601 — engine event-loop spawn
- lsp/client.rs:127 — LSP writer
- lsp/client.rs:129 — LSP reader
- lsp/client.rs:135 — LSP dispatcher
- rlm/bridge.rs:188 — bridge progress drain
- task_manager.rs:790 — task worker loop
- automation_manager.rs:822 — automation scheduler
Sites left as-is (already panic-safe with their own catch_unwind):
- runtime_threads.rs:1242, 1462 — custom AssertUnwindSafe + catch_unwind
- mcp.rs:322 — MCP SSE loop with custom catch_unwind
Sites that don't need conversion:
- runtime_api.rs:287 — axum::serve runs in the parent task, not spawned
- runtime_api.rs:1583+ — test-helper spawn_test_server inside #[cfg(test)]
- All other spawn calls are in #[cfg(test)] modules where panics are
expected to propagate.
Also:
- main.rs panic hook now restores the terminal (LeaveAlternateScreen +
disable_raw_mode) before invoking the original hook, so a panicked TUI
doesn't leave the user's shell stuck in alt-screen mode.
- Adds spawn_supervised_tests::panicking_task_writes_crash_dump_and_does_not_kill_parent
that proves a panicking task produces a dated crash log under
~/.deepseek/crashes/<task>.log and the parent task completes Ok.
Closes#346.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Completes the v0.8.5 cleanup #336 started: with the model-callable swarm
surface gone, the supporting event/UI/state plumbing has no consumers.
- Delete crates/tui/src/tools/swarm.rs (2215 lines, parked under
#![allow(dead_code)] since #336)
- Drop pub mod swarm from tools/mod.rs
- Remove Event::SwarmProgress variant + handler in tui/ui.rs
- Remove app.rs swarm fields: pending_swarm_task_count, swarm_jobs,
last_swarm_id, swarm_card_index (and SwarmOutcome import + retain)
- Remove subagent_routing.rs swarm helpers: seed_fanout_card_from_tool_call,
sync_fanout_card_from_tool_result, sync_fanout_card_from_swarm_outcome,
worker_slot_from_swarm_task, status_to_lifecycle, swarm_task_status_to_lifecycle
- Simplify active_fanout_counts to read directly from the active FanoutCard
- Simplify handle_subagent_mailbox is_fanout to only "rlm" dispatches
- Strip dead "agent_swarm" / "spawn_agents_on_csv" string match arms in
ui.rs (tool dispatch, task panel refresh, ListSubAgents trigger,
active-cell skip), tool_card.rs (ToolFamily::Fanout), and tool_routing.rs
(extract_fanout_prompts function deleted entirely)
- Trim WorkerSlot to id/agent_id/status (label/model/nickname were only
populated by worker_slot_from_swarm_task); remove unused with_agent ctor
- Remove unused SubAgentManager::max_agents and ::available_slots methods
(only swarm.rs called them)
- Update widgets/agent_card.rs doc comments to point at rlm + future
multi-child dispatch instead of agent_swarm
FanoutCard decision: kept. It remains the visual primitive for rlm and
for any future multi-child dispatch the parent agent makes via repeated
agent_spawn calls.
Net: 2698 lines removed, 90 added.
Closes#357.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Add handle_paste(text) -> ViewAction method to the ModalView trait with a
default no-op. ProviderPickerView overrides it in KeyEntry stage to
sanitize and append pasted text to api_key_input (rejecting whitespace
in the same way as the Char handler).
Wire into the Event::Paste handler in ui.rs: before falling through to
app.insert_paste_text(), check view_stack.handle_paste(). If the top
modal consumes the paste, skip the composer entirely. If a modal is
open but does NOT consume the paste, also skip the composer — any
modal that receives paste while focused should handle it, not leak
into the chat input.
Add config_command(app, arg) that dispatches three paths:
/config (no args) -> opens interactive editor (existing behavior)
/config <key> -> shows current value of a single setting
/config <key> <value> -> sets value via existing set_config_value
Keys like model, approval_mode, locale, auto_compact, calm_mode,
show_thinking, mode, max_history, sidebar_width, sidebar_focus,
composer_density, composer_border, transcript_spacing are all read
live from App state for the /config <key> display path.
Unknown keys show a helpful error referencing /help config.
Add DeepseekCN as a first-class provider variant with:
- Enum variant + parse/as_str/display_name/all methods
- DEFAULT_DEEPSEEKCN_BASE_URL (https://api.deepseeki.com)
- Auto-detection when base_url contains api.deepseeki.com
- Locale-based auto-suggest: if no provider is configured and
system locale (LC_ALL/LC_MESSAGES/LANG) starts with 'zh-*',
the TUI defaults to DeepseekCN at startup
- ProvidersConfig.deepseek_cn for provider-scoped credentials
- All match arms updated across config.rs, client.rs,
provider_picker.rs, main.rs, and ui.rs
- provider_picker tests updated for the 7th provider entry
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).
Hunter Bown