Users reported running `deepseek-tui` inside project directories
with hundreds of GB of content — ML datasets, model weights
(`.safetensors`, `.gguf`, `.pt`, `.onnx`), Docker image dumps,
parquet / arrow caches, anything that falls outside the snapshot
built-in excludes. The pre/post-turn snapshot path called
`SnapshotRepo::open_or_init` which initialized the side git repo
and then ran `git add -A` — which walked the entire workspace
indexing every file. On a 100-300 GB directory this hung the TUI
for minutes-to-hours while git churned through the index.
The pre-existing v0.8.27 fixes (#1112: retention cap, mid-session
prune, expanded built-in excludes) addressed the orthogonal
"snapshots grow unbounded over many turns" angle but did nothing
to prevent the first snapshot from being impossible to take.
This change adds `estimate_workspace_size_bounded()` — a bounded
`ignore::WalkBuilder` walk that respects `.gitignore` and the
snapshot module's existing skip list (`node_modules/`, `target/`,
`.next/`, `.venv/`, `__pycache__/`, etc.). The walk early-exits
at either the byte cap or 200,000 file entries, returning `None`
to signal "too big to snapshot."
`SnapshotRepo::open_or_init_with_cap(workspace, cap_bytes)` calls
the estimator *before* the side `git init`, and returns
`Err(InvalidInput)` with a "workspace too large" reason — which
`turn::snapshot_with_label` already logs at WARN and continues
past, so a too-large workspace silently disables snapshots
without blocking any turn. The check is paid only on first init;
subsequent snapshots through the existing side repo skip it.
Plumbing:
- `SnapshotsConfig.max_workspace_gb` (default 2, `0` disables)
- `EngineConfig.snapshots_max_workspace_bytes` resolved at engine
construction from `config.snapshots_config().max_workspace_gb`
- `pre_turn_snapshot` / `post_turn_snapshot` / `pre_tool_snapshot`
take a `cap_bytes: u64` argument threaded from the engine
- `SnapshotRepo::open_or_init` retains its v0.8.31 signature as a
thin wrapper over `open_or_init_with_cap` using the default cap
- `config.example.toml` documents the new `max_workspace_gb` knob
with the "set to 0 to disable" escape hatch for users with
legitimate large monorepos
Six new tests pin both the estimator (under-cap returns Some,
over-cap returns None, builtin-excluded dirs skipped, cap=0
disables the bound) and the `open_or_init_with_cap` integration
(oversized workspace fails with the right error and references
the config knob; cap=0 succeeds even on oversized content).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`image_analyze` sends an image file to an OpenAI-compatible vision
endpoint and returns the model's natural-language description.
Complements `image_ocr` (which uses local tesseract for "what text
is on this image"); `image_analyze` is for "what is this image
about" — visual reasoning the local OCR engine can't do.
Trust-boundary scope: **two-step opt-in only**.
1. The feature is gated by `[features] vision_model = true` —
default `false`.
2. The tool needs a `[vision_model]` config block specifying
`model` (with optional `api_key` / `base_url` — falls back to
the main config api_key + the OpenAI base URL).
Without both, the tool isn't registered, so no install fires a
vision API call without explicit user setup. Workspace boundary:
the tool rejects absolute paths and any `..` parent-dir
traversal before any base64 encoding or HTTP call. Stateless —
each call sends only the requested image + optional prompt; no
session, no conversation history attached. Supports PNG, JPEG,
GIF, WebP, and BMP inputs.
**Billing**: each call hits the configured vision endpoint
(OpenAI by default — `gpt-4o-mini` / `gpt-4o` family commonly
configured). Users with their own deployments (Gemini, Claude
Vision via OpenAI shim, local llama.cpp) can point `base_url` /
`api_key` at the alternative.
Tests cover the tool metadata (read-only capability, correct
name), MIME-type detection across the supported formats and the
unsupported-format rejection path, and the workspace-boundary
checks (absolute paths and `..` traversal both reject before
any API call). Skipped from the upstream PR: the
`.github/workflows/sync-cnb.yml` rewrite, which v0.8.31 already
addressed with the concurrency/scoped-push refactor; landing the
older form would regress that commit.
Resolved a clippy::collapsible_if in tool_setup.rs (the
`if feature && let Some(cfg) = ...` form) to satisfy the
workspace -D warnings gate.
Harvested from PR #1467 by @MMMarcinho
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
AtlasCloud (https://atlascloud.ai) hosts the V4 family on its own
DeepSeek-compatible endpoint at `https://api.atlascloud.ai/v1`, and
several contributors had been running it through the
OpenAI-compatible passthrough with manual `base_url` / model
overrides. Selecting `provider = "atlascloud"` in
`~/.deepseek/config.toml` (or via `DEEPSEEK_PROVIDER=atlascloud`)
now wires up:
- documented `DEFAULT_ATLASCLOUD_BASE_URL` /
`DEFAULT_ATLASCLOUD_MODEL` defaults so a fresh install needs
only the api_key
- a `[providers.atlascloud]` config block with the same fields
every other named provider exposes (api_key / base_url / model
/ http_headers)
- `ATLASCLOUD_API_KEY` env var path, including the secrets test
cleanup loop so per-test env hygiene continues to work
- the provider-picker / `/provider` slash command entries so the
provider is reachable from the runtime UI, not just config
- the env-driven `*_BASE_URL` override branch so users who pin a
proxy can still flip it without editing config.toml
Trust-boundary pins held: AtlasCloud is opt-in (default remains
DeepSeek), no API keys are hardcoded, the api_key resolution flows
through the same `secrets` crate path every other provider uses,
and the provider-config base_url stays settable per environment.
Resolved 3-way merge conflicts in `crates/secrets/src/lib.rs` (env
cleanup loop) and `crates/tui/src/config.rs` (per-provider
base_url match arm + `provider_passes_model_through` predicate)
so the contributor's AtlasCloud branch coexists with the v0.8.x
provider expansion already on `main`. Added the missing match arm
in `validate_provider_base_url` so the non-exhaustive-pattern
check passes after the new variant lands.
Harvested from PR #1436 by @lucaszhu-hue
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
DuckDuckGo HTML scraping with Bing fallback remains the default
`web_search` backend — no API key required, no behaviour change for
installs that don't opt in. Users in regions where those scrapers
are rate-limited or unreliable can now set `[search]
provider = "tavily" | "bocha"` plus `api_key = "..."` in
`~/.deepseek/config.toml` (or via the `DEEPSEEK_SEARCH_PROVIDER` /
`DEEPSEEK_SEARCH_API_KEY` env vars) to route every `web_search`
call through the chosen API.
Tavily targets general AI-agent search; Bocha (博查) is the
mainland-China-friendly equivalent. Both providers are gated by
the existing `[network]` policy on their respective hosts
(`api.tavily.com`, `api.bochaai.com`) and surface a clear
`ToolError` (rather than a silent fallback to DuckDuckGo) when
the user has opted in but forgotten to set `api_key`. Test pins
the missing-key behaviour for both providers.
Resolved 3-way merge conflicts in `web_search.rs` (description
text and test module) so the contributor's helpers
(`truncate_error_body`, `sanitize_error_body`) coexist with the
v0.8.30 spam-detection and query-parsing tests already on `main`.
Folded the `SearchProvider::default()` impl into a `#[default]`
derive to satisfy the workspace `-D warnings` clippy gate, and
threaded `search: Option<SearchConfig>` through `merge_config` so
the multi-config layering doesn't break the field initialiser.
Harvested from PR #1294 by @sandofree
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Sets the `deepseek-cn` provider preset's default `base_url` to the official host (`https://api.deepseek.com`) per [api-docs.deepseek.com](https://api-docs.deepseek.com/). Keeps recognizing `api.deepseeki.com` in URL heuristics and chat-client normalization so existing configs continue to work, and updates the `doctor` strict-tool-mode endpoint hint, docs, and examples accordingly.
Closes#1079. Thanks to @Jefsky for the fix.
Summary:
- Keep default auto alternate-screen mode inside the TUI so transcript scrolling stays app-owned unless users explicitly opt out.
- Queue terminal resume events when the engine channel is full, avoiding stranded paused terminal state after interactive tool cancellation or bursts.
- Scope crash-checkpoint recovery to the resolved launch workspace instead of the shell cwd.
- Add runtime deepseek_version to the prompt environment block so agents can distinguish installed runtime identity from a stale checkout.
Test plan:
- cargo test -p deepseek-tui --locked on a simulated merge with current main
- cargo fmt --all -- --check
- git diff --check
- Existing PR CI was green for lint, version drift, Linux/macOS/Windows tests, npm wrapper smoke, and GitGuardian.
* feat(tui): add `notification_condition` override + assistant text in body (#820)
`[notifications]` already controls method (auto/osc9/bel/off), the
`threshold_secs` gate, and the `include_summary` body. Some users
want a simpler high-level switch — "always notify on every turn" or
"never notify" — without having to know the lower-level fields.
This adds a single optional `[tui].notification_condition` field:
- `"always"` — notify on every successful turn (no duration
threshold). The configured `[notifications].method` and
`include_summary` flag are still respected.
- `"never"` — suppress all turn-completion notifications.
- omitted — fall back to the existing `[notifications]` defaults
(the v0.8.15 behavior is unchanged).
The OSC 9 / BEL body now also carries the assistant's reply text,
sanitized and truncated to 360 characters, with a fallback to the
latest assistant message in `api_messages` when the streaming buffer
was empty (e.g. a tool-only turn). When `include_summary = true`,
the elapsed/cost line is appended on a new line.
Drive-by: drop the unused `Method::from_str` helper (the new code
match-arms over the typed `NotificationMethod` enum, so the parser
helper had no remaining callers).
Differences from upstream #820:
- Keeps the `[notifications]` section in `config.example.toml`
(with `notification_condition` documented as an opt-in override)
rather than deleting the existing block. This avoids breaking
configs that already set `[notifications].method` etc.
- Drops the unrelated `#[allow(dead_code)]` on
`schema_migration::registry`.
- Threads `Option<CostEstimate>` through the helper (the cost
surface changed from `Option<f64>` since #820 was authored).
Tests:
- `notification_settings_*` (3) — `always` keeps the configured
method, `never` returns `None`, missing override falls back.
- `completed_turn_notification_*` (4) — streaming text wins, falls
back to latest assistant message, default placeholder, and 360-char
truncation with `...`.
Integrates #820.
Co-authored-by: zero <1603852@qq.com>
Co-authored-by: zerx-lab <161401688+zerx-lab@users.noreply.github.com>
* style: fmt — collapse short test message helper calls
---------
Co-authored-by: zero <1603852@qq.com>
Co-authored-by: zerx-lab <161401688+zerx-lab@users.noreply.github.com>
Integrates the useful custom HTTP header support from #881 onto current main.
- support root, provider-specific, and DEEPSEEK_HTTP_HEADERS overrides
- apply validated extra headers to model API requests while preserving protected Authorization and Content-Type defaults
- document the config shape in README, config.example.toml, and docs/CONFIGURATION.md
Co-authored-by: Desheng <8596814+dst1213@users.noreply.github.com>
Neither field had any code path that read it. Shipping config knobs
that do nothing trains users to mistrust config. Remove until the
implementation exists.
Tool outputs (read_file, grep_files, exec_shell, fetch_url, web_search) that
exceed a configurable token threshold are now intercepted before they reach
the parent context. A structured synthesis header replaces the raw blob; the
full content is stored in the workshop variable `last_tool_result` for later
`promote_to_context` retrieval.
Key changes:
- New `crates/tui/src/tools/large_output_router.rs`: `LargeOutputRouter`,
`WorkshopConfig`, `WorkshopVariables`, `RouteDecision`, token estimator,
synthesis-prompt builder, and wrap_synthesis helper. Full unit-test suite.
- `ToolContext` gains `large_output_router` and `workshop_vars` fields plus
the `with_large_output_router` builder; constructor defaults are `None` so
sub-agents and test contexts are unaffected.
- `ToolRegistry::execute_full_with_context` applies routing after every tool
call; `raw=true` in the tool input bypasses routing for that invocation.
- `EngineConfig` gains a `workshop` field; `Engine::new` creates the shared
`WorkshopVariables` Arc when the field is present and wires it into every
`build_tool_context` call.
- `Config` gains `[workshop]` table deserialization; `merge_config` propagates
it like other optional tables.
- `config.example.toml` documents `[workshop]`, `large_output_threshold_tokens`
(default 4096), and per-tool threshold overrides.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add locale option to config.example.toml [tui] section with all
supported values (auto/en/ja/zh-Hans/pt-BR) and clear notes that
this controls TUI chrome only, not model output language.
- Fix README.zh-CN.md: settings.toml → config.toml (wrong filename).
- Expand README.zh-CN.md locale section with concrete config snippet
and LANG= env-var example; add link to docs/LOCALIZATION.md.
The zh-Hans locale has been fully implemented in localization.rs since
v0.7.6 — this commit makes it discoverable without reading source code.
Closes#566
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Post-merge review feedback on #583 surfaced four small accuracy gaps:
1. The narrative docs in `docs/CONFIGURATION.md` and the inline comment
in `config.example.toml` said the notification fires "when a turn
takes longer than a threshold" — but the call site in
`tui/ui.rs:928` is gated on `TurnOutcomeStatus::Completed`. Failed
and cancelled turns are silent on purpose. Spell that out so users
don't expect alerts on long failures.
2. The `notify_done` rustdoc still summarised `Auto` as "Osc9 for known
terminals, Bel otherwise" — internally inconsistent with the new
Windows-aware fallback documented one screen earlier on the
`Method::Auto` enum and on `resolve_method`. Update the public
rustdoc to point at the canonical resolution table on
`resolve_method` and call out the `Off`-on-Windows branch.
3. The `## Key Reference` list in `docs/CONFIGURATION.md` had no entries
for `[notifications].method`, `[notifications].threshold_secs`, or
`[notifications].include_summary`. Other features with a dedicated
subsection (e.g. `[memory].enabled`) are listed there too, so readers
scanning the canonical key list could not discover the notification
knobs. Added the three keys with cross-references to the
Notifications subsection.
4. The Windows-only test only covered the unknown-`TERM_PROGRAM` →
`Off` fallback. The positive path (known OSC-9 terminal still
resolves to `Osc9`) was only tested via `iTerm.app`, which is a
macOS-only program — Windows CI would still pass if the `WezTerm`
arm of the match disappeared. Added
`auto_detect_picks_osc9_for_wezterm_on_windows` so the
WezTerm-on-Windows compatibility guarantee is exercised on the
Windows runner.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
On Windows, the audio stack maps BEL (`\x07`) to the
`SystemAsterisk` / `MB_OK` chime — the same sound applications use
for error popups. So with the previous `Method::Auto` fallback to
`Bel`, every successful turn-completion notification ended up
sounding identical to a software error.
Reported by a community user who described it as "the popup-error
sound from a CAD program I used to use" (#583).
resolve_method() now returns `Off` instead of `Bel` on Windows for
unknown TERM_PROGRAM values. Known OSC-9-capable terminals
(`iTerm.app`, `Ghostty`, `WezTerm`) still resolve to `Osc9` on
every platform, so users running WezTerm on Windows keep getting
real notifications. macOS and Linux behaviour is unchanged.
Windows users who actively want an audible cue can opt back in by
setting `[notifications].method = "bel"` in `~/.deepseek/config.toml`.
Also:
- Documents `[notifications]` in `docs/CONFIGURATION.md` with an
explicit Windows note (the schema was previously undocumented).
- Updates the inline comment in `config.example.toml` so users
reading the seed config see the platform-specific behaviour.
- Splits the existing `auto_detect_picks_bel_for_unknown` test
into a Unix variant (`#[cfg(not(target_os = "windows"))]`) and
adds a new Windows-gated test that asserts the `Off` fallback,
so CI's Windows runner exercises the platform-specific path.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
New `HookEvent::ShellEnv` fires immediately before each `exec_shell`
invocation. The hook's stdout is parsed as `KEY=VALUE\n` lines and the
resolved env vars are merged on top of the spawned process environment.
Useful for ephemeral credentials (`aws-vault export …`), per-skill
PATH adjustments, short-lived tokens.
* `HookExecutor::collect_shell_env(&context)` runs every matching
`shell_env` hook synchronously, captures stdout, parses it, returns
the merged map. Later hooks override earlier ones.
* `parse_env_lines` tolerates `export KEY=VAL`, quoted values
(`"…"` / `'…'`), comments (`#`), blank lines. Lines without `=` are
silently dropped — easier than failing the whole hook for one stray
human-friendly line. Values are taken verbatim; we don't run the
string through a shell to avoid expansion surprises.
* Resolved KEY names (NEVER values) are written to
`~/.deepseek/audit.log` so a session can be reconciled later
without leaking the secret material.
* Hook failure / timeout contributes no vars — `exec_shell` is never
aborted because of a misbehaving env hook.
Plumbing:
* `RuntimeToolServices` gains an optional
`Arc<HookExecutor>`. Wired in `tui/ui.rs` from the App's existing
`app.hooks` clone. Test contexts default to `None`.
* `ShellManager::execute_with_options_env` and
`execute_interactive_with_policy_env` are new variants that accept
an `extra_env: HashMap<String, String>` and forward it via
`CommandSpec::with_env` so `prepare()` carries it into `ExecEnv.env`.
* The original `execute_with_options` / `execute_interactive_with_policy`
call the new variants with an empty map so existing callers
(including all 5 internal call sites) keep working unchanged.
* `commands/hooks.rs` `event_label` covers the new variant.
Tests cover `parse_env_lines` against realistic hook output (bare
assignments, `export` prefix, quoted values, comments, blanks, malformed
lines). `cargo clippy --workspace --all-targets --all-features --locked --
-D warnings` clean.
`config.example.toml` documents the new event with an `aws-vault`
example and the audit-logging contract.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Bridge work to unblock whalescale-desktop's Settings/Composer/Archived-chats
flows without requiring a daemon recompile per dev-port or client-side
aggregation.
#561 / whalescale#255 — CORS allow-list configurable
* Add `[runtime_api] cors_origins` config field, `--cors-origin URL`
(repeatable) flag on `deepseek serve --http`, and `DEEPSEEK_CORS_ORIGINS`
env var. User entries stack on top of the built-in defaults
(localhost:3000, localhost:1420, tauri://localhost). Resolution preserves
first-seen order and drops empty/duplicate values; invalid HeaderValues
log a warning and are skipped.
* Refactor `cors_layer()` to read merged origins from `RuntimeApiState`.
#562 / whalescale#256 — `PATCH /v1/threads/{id}` accepts the full editable
field set
* Extend `UpdateThreadRequest` with `allow_shell`, `trust_mode`,
`auto_approve`, `model`, `mode`, `title`, `system_prompt`. Each is
optional; missing means no change. Empty-string clears `title`/
`system_prompt`. Empty `model`/`mode` rejected with 400.
* Add `title: Option<String>` to `ThreadRecord` (additive, no schema bump
per documented criteria — old readers ignore the field without
misinterpretation). `list_threads_summary` now returns the user-set title
when present, falling back to the derived input-summary title.
* `thread.updated` event payload now carries a `changes` map with only the
fields that actually changed.
#563 / whalescale#260 — list-archived-only filter
* New `archived_only=true` query param on `GET /v1/threads` and
`GET /v1/threads/summary`. Backed by a new `ThreadListFilter` enum
(`ActiveOnly` | `IncludeArchived` | `ArchivedOnly`). `archived_only`
takes precedence over `include_archived`. Default behavior unchanged.
#564 / whalescale#261 — `GET /v1/usage` aggregation
* New `RuntimeThreadManager::aggregate_usage` walks all threads/turns,
filters by inclusive `since`/`until` RFC 3339 bounds, accumulates token
totals + cost (via `pricing::calculate_turn_cost_from_usage`), and
groups by `day` (default), `model`, `provider`, or `thread`.
* New `GET /v1/usage` route. `since`/`until`/`group_by` query params,
`since > until` and unknown `group_by` rejected with 400. Empty time
ranges yield empty `buckets` (never 404).
5 new tests cover preflight Allow-Origin echoing for both default and
extra origins, the extended PATCH field set + clear-by-empty + 400 paths,
the archived_only filter on list + summary endpoints, and the
/v1/usage envelope + validation errors. Existing 13 runtime_api tests
continue to pass; the parity gates and full workspace test suite are clean.
`docs/RUNTIME_API.md` and `config.example.toml` updated to document the
new params, body shape, endpoint, and CORS knob.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Resolves the post-#514/#517/#518 conflicts:
- CHANGELOG.md: kept both polish-stack and Linux ARM64 entries under
[Unreleased]; reordered so the ARM64/install-message Changed/Docs
sections precede the Releases footer.
- config.example.toml: kept both the `instructions = [...]` example
and the `[memory]` opt-in stanza in sequence.
- crates/tui/src/config.rs: kept both `instructions_paths()` (#454)
and `memory_enabled()` (#489) on the Config impl.
- crates/tui/src/prompts.rs: extended
`system_prompt_for_mode_with_context_and_skills` to take BOTH
`instructions: Option<&[PathBuf]>` and `user_memory_block:
Option<&str>`. Section 2.5a renders instructions; 2.5b renders the
memory block — both above the skills block so KV prefix caching
still wins.
- crates/tui/src/core/engine.rs: thread both args through the two
call sites.
- crates/tui/src/prompts.rs: update the `system_prompt_for_mode_with_context`
forwarder and the test caller to pass `None` for the new arg.
- .gitignore: ignore `.claude/*.local.md` and `*.local.json` so
local ralph / Claude-Code notes can't leak into commits.
Folds in two valid suggestions from the gemini-code-assist review on #519:
- `client.rs`: collapse the duplicated `LlmError → label` match and the
`human_retry_reason` body into a single
`retry_reason_label_and_human(err) -> (&'static str, String)` helper.
- `widgets/footer.rs::retry_banner_spans`: merge the two separate
`match &props.retry` blocks into one that returns both `(label, color)`.
Behavior is unchanged; refactor is a pure DRY win.
Adds a new optional `instructions = ["./AGENTS.md", "~/.deepseek/global.md"]`
config field that's loaded at startup and concatenated into the
system prompt, in declared order, above the skills block.
* `Config::instructions: Option<Vec<String>>` — raw paths from
`~/.deepseek/config.toml` or the per-project overlay.
* `Config::instructions_paths()` — `expand_path` each entry,
drop empties, return the resolved `Vec<PathBuf>`.
* `merge_project_config` — project's array replaces the
user-level array wholesale (including `instructions = []` to
clear the user list for the current repo). The typical "merge"
pattern is for users who want both — they list `~/global.md`
inside the project array.
* `EngineConfig::instructions: Vec<PathBuf>` — threaded from
config through both engine entry points (`Engine::new` for
Default and `refresh_system_prompt` for runtime swaps).
* `prompts::render_instructions_block(paths)` — loads each file
in order, caps each at 100 KiB with a `[…elided]` marker on
overflow, skips missing files with a tracing warning. Returns
`None` when nothing renders so the caller appends nothing.
* `system_prompt_for_mode_with_context_and_skills` gains an
`instructions: Option<&[PathBuf]>` parameter. Block lives
between the project-context block and the skills block so it
benefits from KV prefix caching and per-project overrides
apply consistently turn-over-turn.
Documentation:
* `config.example.toml` documents the field, the wholesale-
override semantics, and the size cap.
Tests:
* 5 new tests in `prompts.rs`: no-op for empty input, skip
missing files, declared-order concatenation, skip empty files,
truncate oversize files, plus an end-to-end test that the
block appears in the assembled system prompt when configured.
Adds a small, opt-in user-memory layer so the model has access to durable
preferences and conventions across sessions, and the user can dump quick
notes without leaving the TUI.
### What ships
- **Hierarchy loader** (#490): on every prompt assembly the engine reads
`Config::memory_path()` (defaults to `~/.deepseek/memory.md`, override via
`memory_path` in config or `DEEPSEEK_MEMORY_PATH`) and injects the file
as a `<user_memory>` block alongside the existing `<project_instructions>`
block. Goes above the volatile-content boundary so prefix-cache stays warm.
Oversize files (>100 KiB) are truncated with a marker.
- **`# foo` composer quick-add** (#492): typing a single line that starts
with `#` (but not `##` / `#!`) appends a timestamped bullet to the memory
file and consumes the input — no turn fires. The composer status line
surfaces the path that was written. Multi-`#` prefixes deliberately fall
through so users can paste Markdown headings.
- **`/memory` slash command** (#491): `/memory` (or `/memory show`) prints
the resolved path and contents inline; `/memory path`, `/memory clear`,
and `/memory edit` (prints `${VISUAL:-${EDITOR:-vi}} <path>`) cover the
rest of the manual-curation surface.
- **`remember` tool** (auto-update): model-callable tool that takes a
`note` string and appends it as a bullet — the same persistence path as
`# foo`. Auto-approved (writes only the user's own memory file). Only
registered when memory is enabled, so it doesn't pollute the catalog when
the feature is off.
- **Opt-in toggle** (#493): default behaviour is off. Enable with
`[memory] enabled = true` in `config.toml` or `DEEPSEEK_MEMORY=on` in
the environment.
### What's wired
- New `crates/tui/src/memory.rs` module (`load`, `as_system_block`,
`compose_block`, `append_entry`).
- New `crates/tui/src/tools/remember.rs` (`RememberTool` + 3 tests).
- New `crates/tui/src/commands/memory.rs` (`memory(app, arg)` handler).
- `EngineConfig` gains `memory_enabled: bool` + `memory_path: PathBuf`.
- `ToolContext` gains `memory_path: Option<PathBuf>`.
- `App` exposes `memory_path` + `use_memory` from `AppOptions` (previously
destructured-and-dropped); `main.rs` populates `use_memory` from
`config.memory_enabled()`.
- `system_prompt_for_mode_with_context_and_skills` accepts an optional
`user_memory_block` parameter; the engine computes it via
`memory::compose_block(...)` and threads it through.
- Composer Enter handler intercepts `# foo` only when
`config.memory_enabled()` is true; otherwise falls through to existing
turn-submission path.
- `MemoryConfig` table (`[memory] enabled`) added to `Config`, surfaced
in `config.example.toml`, plumbed through `merge_config`.
### Tests
- 8 unit tests in `memory::tests` covering `load` (missing / whitespace /
real), `as_system_block` (xml shape, empty input, oversize truncation),
and `append_entry` (creation, repeated append, empty-after-strip rejection).
- 3 unit tests in `tools::remember::tests` covering disabled-state error,
successful append, and missing-`note`-field validation.
### Verification
cargo fmt --all -- --check ✓
cargo clippy --workspace --all-targets --all-features --locked -- -D warnings ✓
cargo test --workspace --all-features --locked ✓ (1821 + supporting; was 1809 on main)
Closes#490#491#492#493
Refines #489 (EPIC parent — phase-1 MVP delivered; phase-2 items
494–497 stay on the v0.9.0 board)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Modern terminals (iTerm2, Terminal.app 13+, Ghostty, Kitty, WezTerm,
Alacritty, recent gnome-terminal/konsole) make a URL clickable when it's
wrapped in:
\x1b]8;;TARGET\x1b\\LABEL\x1b]8;;\x1b\\
Terminals that don't understand the sequence simply render the visible
LABEL and ignore the escape, so emitting OSC 8 is a strict UX upgrade
for supporting terminals and a no-op for the rest.
### What's wired
- New `crates/tui/src/tui/osc8.rs` module with `wrap_link(target, label)`,
`strip_into(s, &mut out)`, and a process-wide `ENABLED` AtomicBool that
defaults to `true`.
- `markdown_render::render_line_with_links` now wraps recognized URLs
(`http(s)://…`) in OSC 8 when the runtime flag is on. Display width is
computed from the bare URL — the escapes are zero-width on supporting
terminals.
- `ui_text::line_to_string` and `line_to_plain` strip OSC 8 wrappers when
the span content contains an escape, so selection / clipboard output
carries clean URLs and not the raw escape codes.
- `[tui] osc8_links: bool` config (default `true`) added to `TuiConfig`,
documented in `docs/CONFIGURATION.md`, and surfaced in
`config.example.toml`. `run_tui` applies it at startup.
### Tests
- 7 unit tests in `osc8::tests` covering wrap, strip-with-ESC-terminator,
strip-with-BEL-terminator, plain passthrough, mixed escapes, default
state, and round-trip set/unset.
- 2 markdown_render tests proving URLs in paragraph blocks emit the OSC 8
wrapper when enabled and emit plain text when disabled.
- 2 ui_text tests proving `line_to_plain` strips OSC 8 wrappers from spans
and passes plain spans through unchanged.
Tests that touch the global ENABLED flag serialize through a static
Mutex inside the test module 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 ✓ (1820 + supporting; was 1809)
Closes#498
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>
Issues #202, #203, #204, #205:
- Cycle/seam triggers use active request input size + response
headroom reserve, not lifetime cumulative API usage.
- V4 hard-cycle headroom calibrated around fixed TURN_MAX_OUTPUT_TOKENS
plus CONTEXT_HEADROOM_TOKENS safety buffer.
- /tokens, /cost, footer/header labels, and docs now separate
active context, turn telemetry, cumulative usage, cache hit/miss,
context percent, and cost.
- Foreground exec_shell timeout output tells the model the process
was killed and suggests task_shell_start or background exec_shell
plus poll/wait.
- Added regression tests for active-token basis, V4 headroom,
seam trigger basis, footer label behavior, and shell timeout
recovery metadata.
- Preserved #200/#201 policy: V4 default is append-only,
prefix-cache preserving; replacement compaction, Flash seams,
and capacity intervention remain opt-in.
`run_interactive` now calls `session_manager::prune_workspace_snapshots_at_boot`
right after the system-skills installer, dropping any snapshot in the
side-git repo older than 7 days (default; configurable via the new
`[snapshots]` section in `config.example.toml`). The helper is
non-fatal: a missing `git` binary, read-only home, or absent snapshot
dir all log a single WARN (or DEBUG for the count of pruned commits)
and return, so the TUI keeps starting even when retention can't run.
Also document the snapshot subsystem in `config.example.toml` —
disk-footprint expectations, where the side repo lives, and how
`/restore` / `revert_turn` consume it.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- README: add a "Publishing your own skill" section explaining the
`github:owner/repo` install path, the multi-skill `skills/<name>/`
layout, and how to submit to the curated registry.
- config.example.toml: document `[skills] registry_url` /
`max_install_size_bytes` next to the existing `[network]` section so
users see the network-gate dependency in context.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Inject LSP diagnostics as a synthetic user message after every successful
file edit (`edit_file`, `apply_patch`, `write_file`) so the agent sees
compile breaks before its next reasoning step. Largest agent-quality
lever in v0.7.0.
Pieces:
- `crates/tui/src/lsp/`: thin JSON-RPC stdio client (no `tower-lsp`),
per-language registry, diagnostics renderer producing the
`<diagnostics file="…">` block format. `LspManager` owns lazily
spawned per-language transports keyed by `Language`.
- `core/engine.rs`: hook on the success branch of the tool-result loop
derives the edited file path(s) per tool, queries the LspManager
with a 5 s timeout, and collects rendered blocks into
`pending_lsp_blocks`. The queue is flushed as a `text` content
block on the next request iteration so the model sees the
diagnostics before it streams its next turn.
- `[lsp]` config schema (`enabled`, `poll_after_edit_ms`,
`max_diagnostics_per_file`, `include_warnings`, optional
`servers` override) with built-in defaults for rust-analyzer,
gopls, pyright, typescript-language-server, and clangd.
- Failure modes are non-blocking by design: a missing LSP binary
logs a one-time warning and skips the hook; a crashed server or
poll timeout simply drops that turn's diagnostics. The agent's
work is never blocked.
Tests: 24 unit tests cover language detection, registry overrides,
filter/sort/truncate behavior, and the rendered block format. Three
engine-level tokio tests exercise the full path through a fake
transport (no real LSP server is ever spawned in CI).
Acceptance criteria (per #136):
- Edit introducing a type error -> next request body contains
`<diagnostics file="…">` block at the right line/col.
- `[lsp] enabled = false` -> no diagnostics injected.
- Snapshot test exercises full path with mock transport.
- LSP binary not on PATH -> one-time warning, agent proceeds.
- 5 s timeout, errors-only by default.
- Transports spawn lazily on first edit per language.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds the `[network]` table to both the workspace config crate (`ConfigToml`)
and the live tui config (`Config`), plus a documented example block in
`config.example.toml`. Schema:
```toml
[network]
default = "prompt" # allow | deny | prompt
allow = ["api.deepseek.com", "github.com"]
deny = []
audit = true
```
`NetworkPolicyToml::into_runtime()` builds a runtime `NetworkPolicy` so the
engine can construct a `NetworkPolicyDecider` without reaching across crate
boundaries. Defaults preserve pre-v0.7.0 behavior: when the section is
absent, no policy is enforced.
Hunter Bown