Fixture pendek sebelumnya (~8 token nyata per pesan lewat tiktoken)
tidak pernah melebihi target 700 token, jadi shape_messages tidak
pernah men-drop satu pesan pun -- satu test gagal, satu test lain
lulus secara vakum. Pakai fixture lebih panjang (~49 token/pesan)
yang diverifikasi melebihi target dengan nyaman.
9 task: tokens.rs (tiktoken-rs), window.rs, dedup.rs, squash.rs,
shaping.rs (port shortsend), gabungan cutover+fix /compact manual,
wiring squash, status bar, dan mode ringkas opsional. Setiap task
diverifikasi dengan cargo build/test nyata, bukan -D warnings (yang
sudah merah di main karena warning pre-existing di file lain).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Facade cuma dipakai generically oleh satu caller (Action::Compact);
auto-loop tetap butuh kontrol per-stage sendiri. Selaras dengan prinsip
"No DI" di CLAUDE.md. dedup::collapse juga diubah mengembalikan
(Vec<ChatMessage>, bool) supaya caller tahu ada perubahan tanpa perlu
ChatMessage: PartialEq.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Ditemukan saat menulis plan: kompresi JSON pada hasil read akan merusak
byte-exactness yang dibutuhkan untuk edit selanjutnya jika file yang
dibaca kebetulan berformat JSON (package.json, tsconfig.json, dst).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Rencana pengganti shortsend.rs dengan modul context/ (dedup, squash,
shaping, tokens, window) plus mode ringkas opsional, disusun dari studi
teknik rtk-ai/rtk, headroomlabs-ai/headroom, dan JuliusBrussee/caveman
(ide saja, tanpa menyalin kode).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
AppStateRest::new() men-spawn thread ignore::Walk untuk mention_index
tanpa syarat, padahal mode --attach cuma dipakai untuk render lokal —
handle_key dan logika mention berjalan di sisi daemon lewat IPC, jadi
index di client attach tidak pernah dipakai. Ini bikin setiap
--attach melakukan full workspace walk (sampai 50.000 entry) sia-sia.
Pindahkan thread-spawn itu ke method terpisah
spawn_mention_index_build(), dipanggil eksplisit dari
run_single_process() dan run_daemon() setelah AppStateRest::new(),
tapi sengaja tidak dipanggil dari run_attach().
Cursor bisa berpindah (Left/Right) tanpa menutup dropdown mention,
sehingga mention_start jadi stale relatif ke cursor saat Enter
ditekan. select_autocomplete() lalu memanggil replace_range dengan
start > end dan panic (crash seluruh TUI, termasuk daemon). Tambah
guard: jika cursor < mention_start atau mention_start > buffer.len(),
tutup dropdown dan kembalikan false alih-alih menyambung range yang
tidak valid. Tambah regression test yang mereproduksi skenario ini.
Tambah DaemonFrame::ClipboardCopy(String) supaya daemon bisa
mengirim teks pending_clipboard_copy ke attach client, yang
kemudian menulis sekuens OSC52 ke stdout-nya sendiri (bukan
stdout daemon yang tidak dimiliki terminal user).
Ketika write tool membuat file baru (bukan overwrite), path file
sekarang di-push ke mention_index untuk autocomplete @file mention.
- Capture file existence status sebelum write
- Push ke mention_index hanya untuk genuinely new files
- Add 2 tests: one untuk new file push, one untuk overwrite non-duplication
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Menambahkan field mention_index: MentionIndex ke ToolCtx/ToolCtxBuilder dan
AppStateRest, mengikuti pola dir_cache yang sudah ada. AppStateRest::new()
sekarang men-spawn thread background yang men-walk setiap workspace root
via ignore::Walk, membangun daftar path file (dengan prefix [N] untuk root
selain yang pertama) dan mengisi mention_index — data ini yang akan dipakai
fitur autocomplete @file-mention.
Menambahkan MentionIndex (indeks path file thread-safe untuk fitur
autocomplete @file-mention), enum AutocompleteKind untuk membedakan
dropdown slash-command dan file-mention, serta method baru pada
InputState: mention_query_at_cursor untuk deteksi token @mention di
posisi cursor, dan open_mention_autocomplete untuk fuzzy-match file
via nucleo-matcher. select_autocomplete kini kind-aware: menyisipkan
path file ke posisi mention alih-alih mengganti seluruh buffer.
The span_text function in src/view/markdown.rs's test module was no longer
called after the dim_false_plain_text_has_no_color test was fixed. With the
crate's dead_code = "deny" lint enabled, this unused function caused a compile
error. Removed it.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
The first assertion was checking span_text() which concatenates all spans
including trailing paragraph-end newlines, making the test guaranteed to fail.
Changed to check spans[0].content directly to verify the text span itself
contains 'hello world' with no color applied when dim=false.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Tambahkan helper apply_dim dan diff_line_style, ubah signature
render_markdown untuk menerima flag dim, serta deteksi fence bahasa
diff sehingga baris +/-/@@ tetap berwarna meskipun pesan sedang
dirender dim (tampilan tool-output).
- Added functionality to generate lessons based on code reviews, including prompts and instructions for the reviewer.
- Updated the `.gitignore` to exclude lesson documentation files.
- Removed the `/lesson` command from the help menu and command parsing.
- Enhanced the status bar to display a message when a lesson is being generated.
- Introduced a new `lesson_running` state to track lesson generation progress.
- Updated various components to handle the new lesson generation workflow, including subagent events and token usage tracking.
Colons are now at column 9 for all five lines (labels right-aligned
in 6-char field). Values start at column 10. Leading zeros retained
for minutes/seconds via {:02}.
total: 0 tok
main: 0 tok
learn: 0 tok
calls: 0
time: 0h 06m 46s
All five lines now use consistent label-first ' {:<7} {}' pattern
with aligned colons (column 9) and values (column 10). Elapsed time
uses {:02} leading zeros for minutes/seconds.
Fixes malformed output where some lines used number-first order
('{} tok total') while others used label-first ('main: {} tok'),
causing visual misalignment in the ~28-char-wide sidebar column.
feat(engine): summarize agent completion progress in UI notifications
feat(main): enable and disable bracketed paste support in terminal
fix(app_config): store API key from file as fallback for Claude provider
refactor(workflow): remove unnecessary card separator in workflow panel
src-misc/system-prompt.txt masih memakai framing lama "Zesdex Corp
CEO / 5 divisi" dan mereferensikan tool run_company_pipeline yang
sudah tidak ada, tertinggal saat commit 25f084f merombak arsitektur
ke hive-mind (CLAUDE.md, README.md, dan implementasi workflow_run
sudah diupdate saat itu, tapi file prompt utama ini terlewat).
Akibatnya AI membalas dengan persona CEO/company, bukan Core
Intelligence/hive-mind seperti didokumentasikan di README.md.
- system-prompt.txt: tulis ulang total ke model Core Intelligence /
cognitive cycle plan / processing node / access tier, konsisten
dengan CLAUDE.md dan tool hive_mind yang sebenarnya.
- system-tools.txt: tambah entri hive_mind dan read_findings yang
sebelumnya tidak ada sama sekali di daftar tool.
- workflow.rs: perbaiki sisa teks "divisions/subagents" di deskripsi
tool read_findings jadi "nodes/subagents".
Diverifikasi live: AI sekarang memperkenalkan diri sebagai "Core
Intelligence of Zesdex ... modeled as a hive-mind" alih-alih CEO.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Overlay Todo sebelumnya menampilkan jumlah pesan yang tidak relevan,
bukan isi task list. Overlay Usage sekarang pakai compute_usage_summary
yang sama dengan widget sidebar (DRY, angka konsisten).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Baris pertama widget Usage sebelumnya bisa melebihi lebar kolom sidebar
(30 kolom) pada sesi dengan jumlah token besar, menyebabkan teks
terpotong diam-diam tanpa wrap. Sekarang dipecah jadi beberapa baris
pendek yang aman di lebar berapa pun yang realistis.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Sidebar kanan permanen (Workflow/Tasks/Usage) menggantikan panel todo
ad-hoc yang lama. Widget baca state yang sudah ada, tidak ada perubahan
skema AppStateRest.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Overlay Todo dan Usage sebelumnya tidak punya trigger sama sekali di
jalur interaksi normal (cuma bisa lewat restore snapshot sesi) --
sekarang mengikuti pola /workflow yang sudah ada.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Konten Tool sebelumnya didorong sebagai satu Span tanpa split newline,
sehingga output tool multi-baris (stdout bash, hasil grep, diff)
tampil sebagai karakter \n literal alih-alih baris terpisah. Sekarang
mengikuti pola render_markdown + split_spans_into_lines yang sama
dengan role lain.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
markdown.rs juga disesuaikan: indentasi paragraf/heading bawaannya
dilepas supaya tidak bentrok dengan indent PREFIX_WIDTH di chat.rs
(baris pertama vs baris wrap lanjutan jadi sejajar).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
unnested_or_patterns, collapsible_if, items_after_statements, dan
case_sensitive_file_extension_comparisons di auto.rs, engine.rs, dan
actions/mod.rs.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Spec brainstorming untuk rombak total src/view + src/controller: layout
Multi-Pane Dashboard dengan sidebar Workflow/Tasks/Usage, palet Tokyo
Night, dan format chat inline rapat.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Pesan sistem bertanda [Hive-Mind Consensus] hanya di-push ke variabel lokal
run_agent_turn dan diarsipkan ke SQLite, tidak pernah masuk ke
rt.messages lewat TurnEvent — sehingga hive_mind_already_ran selalu
memindai daftar pesan yang kosong dan gerbang "converge sekali per sesi"
tidak pernah aktif. Tambahkan SessionRuntime.hive_mind_converged yang
diset dari event TurnEvent::SystemNote { kind: "hive_mind_converged" }
setelah konvergensi selesai, disalurkan lewat TurnCtx, dan dijadikan
sinyal utama di run_agent_turn (pemindaian pesan lama tetap sebagai
fallback defensif).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
RunningGuard resets TEST_GEN_RUNNING/ARCH_REVIEW_RUNNING/SECURITY_REVIEW_RUNNING
via Drop so a subagent panic can no longer wedge that review kind disabled
for the rest of the process. Doc comments on run_subagent_with_retry and the
three spawn_background_* / spawn_all_background functions now describe the
abort_flag and overlap-guard behavior added in Task 7.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
- Introduced a new hive-mind architecture that allows the Core Intelligence to issue directives to anonymous processing nodes.
- Each node executes its directive and merges output into a collective state, visible to all nodes in real-time.
- Added support for dynamic cognitive cycles, enabling flexible task management.
- Implemented documentation generation for hive-mind runs, ensuring a durable record of decisions and actions.
- Refactored existing company pipeline tools to align with the new hive-mind structure, replacing division-specific prompts with a more generalized approach.
- Updated workflow rendering to accommodate hive-mind nodes and their system-assigned designations.
- Enhanced error handling and validation for cognitive cycle plans.
- Updated README.md to reflect the addition of 3 new built-in tools, bringing the total to 37.
- Revised architecture documentation to indicate the increase in tool count.
- Enhanced backend documentation with updated line counts for various modules.
- Modified data documentation to change edit log format from JSON to JSONL.
- Updated dependencies documentation to reflect version upgrades for several crates.
- Improved prompts for auto-reviewer, division implementer, planner, tester, and quality reviewer to enforce stricter coding standards regarding linter bypasses.
- Refactored code in various modules to improve clarity and performance, including updates to error handling and tool execution logic.
- Added comprehensive tests for IPC frame serialization and deserialization.
- Updated `crossterm` from version 0.28 to 0.29.
- Upgraded `reqwest` from version 0.12 to 0.13 and added "form" feature.
- Bumped `serde_yaml_ng` from version 0.9 to 0.10.
- Increased `dirs` version from 5 to 6.
- Updated `rusqlite` from version 0.32 to 0.40.
- Upgraded `infer` from version 0.16 to 0.19.
- Bumped `sha2` from version 0.10 to 0.11.
- Updated `rmcp` from version 1.8 to 2.2.
- Refactored SHA256 hash encoding in `rewind.rs`, `mod.rs`, and `rest.rs` to use `hex::encode` instead of formatting with `{:x}` for better clarity and consistency.
- Updated status bar rendering in `status.rs` to feature a segmented design with clear visual segments for app name, status, and metadata.
- Refined color theme in `theme.rs` to adopt a modern dark palette with neon accents, improving visual hierarchy and readability.
- Revamped workflow panel in `workflow.rs` to display agent statuses as compact cards with state badges, enhancing clarity and user experience.
- Improved overall styling consistency across components, ensuring a cohesive look and feel throughout the TUI.
- Introduced prompts for various subagent roles: architecture reviewer, code quality reviewer, documentation maintainer, implementation team, testing team, and security reviewer.
- Implemented the auto-subagent orchestration in `auto.rs` to manage inline and background reviews.
- Created a division structure in `division.rs` to define roles and responsibilities for each subagent.
- Developed a company workflow orchestrator in `company.rs` to run the complete division pipeline, consolidating findings and generating executive summaries.
- Added logic to determine whether to run a full or quick pipeline based on request complexity.
asepharyana