Commit Graph

326 Commits

Author SHA1 Message Date
alan 5090f1cf4e Pipelines skill: outcome-first output, aligned review and loop guidance, operator material moved to docs
Rewrite format.md around turn files, the output.md order (# outcome, edge word, # handoff, detail), checks, configs, human stages and the land stage delivery gate (sh -c in a fresh detached worktree, clean checkouts incl. untracked, 64 KB output cap, opencode only). Align review guidance across practices, verification, orchestration and the feedback-loop example. Fix loop-limit semantics in control.md against runner.go, budget_tokens sizing, read for large inputs, blocked-else-error and one stage naming set. Move dated verification logs to docs/verification-history.md and brokered chat, TUI keys and harness internals to docs/operator-reference.md; label operator-only references in SKILL.md.
2026-11-04 17:27:01 +00:00
alan 70391b17c2 Stage diffs: clean Git files take their baseline from the index blob
On a large Git workspace the 32 MiB retained-text budget was spent
alphabetically on files that never change, so small late edits were
recorded with no_patch. The stage-start snapshot now keeps text only for
files dirty or untracked at start; a clean tracked file keeps its hash and
stage-0 index blob id. When it changes or is deleted, the after capture
reads that blob in one `git cat-file --batch` and uses it only if its
SHA-256 matches the start read, so stage commits/resets do not move the
baseline and filters or assume-unchanged never yield a wrong patch. The
after capture shares unchanged files' representation instead of spending
budget on them again.

FileChange gains no_patch_reason (binary, file_size, budget, lines,
evidence_size, git_status, baseline). Non-Git workspaces keep their
behaviour.
2026-11-04 17:08:01 +00:00
alan 6870c81960 Skill install: also refresh Codex's copy under $CODEX_HOME/skills 2026-11-04 16:43:55 +00:00
alan a627b38ef3 Merge main; use the shared chatShutdownDetacher for OpenCode and Codex
OpenCode and Codex chats implement Detach (called by chatManager.Close)
instead of a parallel DetachSessions interface. Docs follow the Claude Code
host and the systemd KillMode=process unit. The opt-in live restart check
copies only the stage provider's login row into its scratch OpenCode
database, builds the CLI for skill install and removes its scratch tree.
2026-11-04 16:24:17 +00:00
alan aa8eddd686 Keep OpenCode/Codex chat and stage sessions running across server restarts
A stopping server no longer interrupts harness sessions. Runs are canceled
with a shutdown cause, so stage clients leave admitted sessions running and
owned; start-up recovery re-adopts live OpenCode V2 stage sessions (wait,
read back the result, continue the graph), restarts unadmitted visits,
continues runs between stages, and falls back to interrupted with a reason
when the harness is gone. Chats with live work are recorded on shutdown and
reattached on start; turns that ended during the downtime are folded in
from history. The server-spawned V2 chat serve is now a detached owned
service. PIPELINES_SHUTDOWN_SESSIONS=stop restores the old behaviour.
2026-11-04 16:17:08 +00:00
alan 6b22389cae Merge: Claude Code chats survive server restarts via a detachable host 2026-11-04 16:15:06 +00:00
alan 34c2ccec25 Install and document pipelines-claude-host alongside the server 2026-11-04 16:14:35 +00:00
alan c810437aa5 Claude Code chats survive server restarts in a detachable host
A pipelines-claude-host process owns each claude -p CLI and its pipes,
spools its stream-json output with offsets and serves a private Unix
socket. The server detaches on shutdown and reattaches on start,
replaying the spool to rebuild turns, approvals, questions, background
tasks and the live model. Explicit close, idle release and CLI exit stop
the host; a crashed host falls back to --resume with a notice.
2026-11-04 16:09:56 +00:00
alan 9351cd7d74 Merge: pipeline stages run on their own OpenCode service with stage-only limits 2026-11-04 14:12:38 +00:00
alan b655278674 Run OpenCode stages on a Pipelines-owned stage service with their own limits
Stages now run on a detached Pipelines-owned opencode serve started with
OPENCODE_CONFIG_CONTENT carrying stage tool_output (16384 bytes / 400 lines)
and compaction.auto defaults, configurable through PIPELINES_OPENCODE_STAGE_*.
Chats keep their existing service and configuration; a server-spawned chat
serve can take PIPELINES_OPENCODE_CHAT_CONFIG. The service shares the user's
OpenCode config, credentials and session database, keeps a stable private
registration so retained references (recovery, interrupt, export) stay valid,
revives on the same port after a crash, replaces itself when idle after a
settings change, and is stopped on shutdown only when idle.
PIPELINES_OPENCODE_STAGE_SERVICE=shared restores the previous behaviour.
2026-11-04 14:04:35 +00:00
alan c188b36d95 Skill practices: quiet test wrappers, targeted diffs and file ranges, grep logs, batch tool calls 2026-11-04 13:12:21 +00:00
alan dfa239d637 Lint: catch 'the server checks and lands it'; value fallbacks are not silent guards 2026-11-04 13:11:26 +00:00
alan 3c31bca87f Merge main; align lint and skill practices with essential memory/history and the four graded examples 2026-11-04 13:08:47 +00:00
alan 37e941bbba Authoring lint: required checks, undeclared outcomes, delivery claims, loop limits, silent guards, boilerplate 2026-11-04 13:04:11 +00:00
alan d7e54f4612 Merge: short essential memory per stage; full history on demand 2026-11-04 13:01:16 +00:00
alan 538143554c Split stage memory into capped essential memory.md and full history.md
Every stage used to be told to read memory.md, the full output of every
earlier turn (19 KB average, 92 KB max), and paid for it on each model call.
memory.md is now essential memory, hard-capped at 4 KB and inlined in the
prompt: the task, the previous stage's # handoff section (or its truncated
output head), a one-line-per-stage outcome ledger and the server-captured
changed files. history.md keeps the old full memory on disk; read-capable
stages are pointed at it and input.md for on-demand detail, and it is never
inlined. The prompt asks each stage for a short # handoff section.
2026-11-04 13:00:48 +00:00
alan e5c015f6ed Merge: no UI-review auto-skip without complete change capture; capture lists over-budget changes
# Conflicts:
#	internal/protocol/runs.go
2026-11-04 12:58:45 +00:00
alan f16d61cdfa Skip fallback needs complete, empty evidence; capture lists over-budget changes
The server skip fallback for stages with a skipped edge now applies only
when every earlier visit recorded a complete file-change capture with no
changed files and no image artifact. Any change (no repo-specific UI path
or extension list), any partial/unavailable/missing capture, a human
decision or a checkpoint-retry prefix runs the model. auto_skip=false opts
a stage out. The fallback verdict names the server fallback.

Capture compares over-budget text by hash and, in Git, lists paths it
could not compare when their git status changes, marked no_patch, so a
large workspace no longer records files: [] for a real edit. Run detail
gains a warnings list for partial/unavailable captures, also printed by
inspect on stderr.
2026-11-04 12:56:40 +00:00
alan e727c3fd07 Merge main into run token usage branch 2026-11-03 22:21:38 +00:00
alan 3227d61caf Token usage: keep cache/reasoning split, count only recorded steps, cost only when positive; captures fixture, docs and notes 2026-11-03 22:16:49 +00:00
alan aa948bdfe4 Runs list carries per-run token usage; app shows tokens beside size, Most tokens sort, Summary and stage tokens 2026-11-03 22:04:55 +00:00
alan 8c7093d1e6 Merge: chat list shows running turns and background tasks for every chat 2026-11-03 19:54:35 +00:00
alan 45c933c176 Chat list: spinner and background-task badge from server activity on every row
The list applies chat_activity pushes and each row's activity by seq, so
every listed chat shows a running turn, not only the chat open here. An
idle chat with running background tasks wears a quiet badge with tooltip and
semantics "Background tasks running (N)". Older servers keep the old
behaviour. List rows that never changed carry the server's current seq so
they order after snapshots kept from an earlier server process.
2026-11-03 19:53:52 +00:00
alan 1b98877d88 Chat list activity: turn running and background tasks on every row, pushed to every connection
chat_sessions rows carry activity (turn_running, background_tasks, seq) from
the hub's own state, and chat_activity is pushed to every connection when a
session's turn starts or ends or its running background-task count changes.
A room whose last viewer left stays observed while background tasks run,
bounded by the unattended limits; a Claude Code process exit ends its tasks.
2026-11-03 19:45:43 +00:00
alan a48e4a5b6a Replace starters with four graded examples seeded into new databases
The template catalog is now Example 1-4: one stage, two stages (handoff),
feedback loop (runner-owned limits, retries, timeout) and human decision
(type=human approve/revise/abort with notify hooks). All read-only or leave
changes uncommitted; none commits, pushes or deploys.

A brand-new database (schema created by this Open) gets the examples once at
server start, bound to the configured default model and harness. A
server_settings marker records the decision, so removed examples never come
back and existing installs are marked without any pipeline being added or
rewritten.
2026-11-03 19:35:47 +00:00
alan 7ecc12b747 LAN discovery: server advertises _pipelines._tcp over mDNS; app finds servers on the connect screen
Server: internal/discovery publishes a DNS-SD record (hashicorp/mdns) with
the port LAN clients dial (the web proxy via -mdns-port, which the
supervisor passes, or a non-loopback -addr) and TXT v, name, path, tls, auth.
On by default; -mdns=false or PIPELINES_MDNS=off disables it. Failures are
logged and never block startup; the advert is withdrawn on shutdown.

App: the Connect to Pipelines screen gets 'Find servers on this network'
behind a ServerDiscovery interface (Bonsoir: Android NSD with multicast lock,
iOS Bonjour with NSLocalNetworkUsageDescription and NSBonjourServices).
Tapping a server fills the address and connects; manual entry stays. Web has
no scan.
2026-11-03 14:54:54 +00:00
alan ad4233f7b8 Chat: /new continues the same chat on a fresh session
The composer's /new used to create a separate chat. It now sends
chat_new_session. The server starts a fresh native session on the chat's
own harness (OpenCode, Codex or Claude Code) and re-keys the
operator_sessions row in one transaction. The chat keeps its title,
directory, backend, colour, star, model and mode. The old row is kept
unlisted with replaced_by, and its native session stays resumable.

The reply and the chat_session_changed push carry previous_id, so every
client swaps the row in place and an open conversation follows it to the
fresh, empty transcript with a notice.
2026-11-03 14:06:44 +00:00
alan 6ca415c134 Search: order results newest first in every group
Chat hits sort by the chat's last use whatever field matched, and run,
step, field, artifact and pipeline hits sort by their own date, before
the result cap applies so the cap drops the oldest. Each kind's row scan
also walks newest first. Score still reports the match tier. The app
sorts both groups newest first as well.
2026-11-03 13:35:27 +00:00
alan 63a67e0621 Merge: search finds chats and opens them 2026-11-03 13:02:16 +00:00
alan bff7115e4e Search: find operator chats by title, directory and message text
A search with kind chat matches the operator-session registry's titles and
directories and the newest messages of recent transcripts through the chat
broker (bounded count, concurrency and one-second budget), answered off the
connection's read loop. The all-kind search is unchanged for older clients.

The app sends the chat search after its run search and shows a Chats group
with title, harness, directory and snippet; a chat hit opens that chat in the
Chat tab. The probe fixture answers chat searches over ?chats=N.
2026-11-03 13:01:53 +00:00
alan edc1543874 Merge: background-task notices grouped in the chat 2026-11-03 12:45:18 +00:00
alan 1a9db0206c Chat: group consecutive background-task notices into one collapsed chip
Two or more consecutive Claude Code task notices fold into one
task_notices row: a chip 'N background tasks' (tinted when one failed)
that opens a sheet with one compact row per task (outcome icon, summary,
outcome word), like the tools and permissions chips. A lone notice stays
one line. The server also treats Claude Code's [SYSTEM NOTIFICATION]
banner as harness text, so a bannered notification without an origin is
still a notice, never the operator's turn. The chat fixture gains
?tasks=N.
2026-11-03 12:44:57 +00:00
alan a12a7b3d66 Claude chats: pass the chat title as --name so terminal resume lists them by name
Spawns pass the session title with --name (Claude Code records it as the
transcript's custom-title). A rename tells the harness the new title for its
next spawn, and the first routing of a session after a restart hands it the
registry title.
2026-11-03 12:31:31 +00:00
alan d34185b56c Merge: chat colours, Ctrl+1-9, starred chats alphabetical
# Conflicts:
#	app/lib/features/chat/conversation/chat_thread_view.dart
#	app/tool/perf/perf_fixture.dart
#	internal/protocol/chat.go
#	internal/server/chat_close.go
#	internal/server/chat_sessions.go
2026-11-03 11:22:50 +00:00
alan 1de74f76bb Chat info: Session section with native id, resume command and export
The chat information sheet gains a Session section: the harness's native
session id (copy), harness, directory, a verified resume command (copy)
and Export conversation (Markdown), Export JSON and, for Claude Code,
Export native session (the JSONL transcript).

Server: chat_sessions rows carry resume_command and native_export; new
chat_export command builds Markdown/JSON from the same paged history
chat_messages serves (bounded at 8 MiB), refuses non-operator sessions.
App: exports go through the artifact file bridge (web download, share
sheet on phones).
2026-11-03 10:59:41 +00:00
alan a4c191a416 Chats: a shared highlight colour per chat, pushed live with star and rename
chat_color {session_id, color|null} stores a palette name (red, orange,
amber, green, teal, blue, purple, pink) on the operator-session row; rows
and replies carry it as color. Colour, star and rename changes are pushed
to every other connection as chat_session_changed.
2026-11-03 10:53:38 +00:00
alan 10049b8062 Chat info: account quota per harness (Claude rate_limit_event, Codex account/rateLimits, OpenCode unsupported)
Usage frames carry optional usage.account {harness, source, plan, as_of,
windows[{id,label,used_percent,resets_at}], unsupported}. Claude Code quota
comes from its rate_limit_event stream lines and the initialize account
(plan), shared across chats on the same account. Codex reads
account/rateLimits/read once per connection (re-read when a chat opens after
5 min) and merges account/rateLimits/updated. OpenCode exposes no quota API
and says so. The app's chat info sheet shows an Account usage section with a
progress bar and reset countdown per window, Material and Cupertino.
2026-11-02 18:57:13 +00:00
alan 895b23d2da Chat reply notifications: up to 1000 characters, paragraphs kept
The finished-reply notification now carries up to 1000 characters of the reply
(was 200), keeping its paragraph breaks for the app's expanded notification;
ntfy still gets it on one line within its 2048-byte limit.
2026-11-02 17:08:19 +00:00
alan 9393345acb Merge: worktree-agent-adedec543a1830ea7 2026-11-02 16:47:33 +00:00
alan a7b32d4473 Merge: worktree-agent-af03a51b8bf6c96ab 2026-11-02 16:47:32 +00:00
alan 07d4740d0c Show injected Claude input as agent reports and notices, not operator bubbles
Claude Code records subagent/peer reports, task notifications, reminders and
skill bodies as user-role entries. Classify them server-side (history and live
stream) by origin/isMeta/queued_command mode: reports become kind agent_report,
task notifications kind notice, harness meta is hidden, and the mid-turn
wrapper is unwrapped to the operator's text. The app draws a collapsed Agent
report card and a one-line system notice on the agent's side.
2026-11-02 16:44:07 +00:00
alan 1a9fc74999 Show the chat mode control as soon as the session names its mode
A created chat's reply carried no mode, and the chat destination kept the
first row it opened for the whole visit, ignoring later list re-reads, so the
mode control only appeared after closing and reopening the chat. The server
now names the mode on a created row, and the destination adopts each listed
row that a re-read changed (excluding the live running flag), so the open
conversation follows new, refreshed and other-device mode changes in place.
2026-11-02 16:37:35 +00:00
alan b4382b08ad Apply the chat directory's environment and account to Claude Code chats
Claude Code chats now start with the chat directory's own environment:
direnv (allowed .envrc only, via direnv export json) and mise (mise env
--json), cached per directory and invalidated when config, watched files or
allow records change. A blocked .envrc is logged and shown in the chat as a
notice and never applied. When the directory chooses the Claude account
(CLAUDE_CONFIG_DIR, API key or token variables), the server's service token
and login-file fallbacks are skipped and inherited credentials dropped.
Transcripts in a directory's CLAUDE_CONFIG_DIR are found for history,
resume and after a restart. PWD is set to the chat directory.
2026-11-02 16:37:20 +00:00
alan d78cbe3f66 Merge: one way to set up harnesses (pipelines harness setup) 2026-11-02 16:14:50 +00:00
alan 108c29f9eb One harness setup path: pipelines harness setup <claude|codex|opencode|pi>
Checks the CLI on the server's PATH (install command when missing), signs in
with the harness's own login only when needed (--login forces it), keeps the
OpenCode/Pi model pickers, and verifies with the server's check. Works on
native and Docker installs (Docker delegates to the container setup); --host
is a hidden compatibility alias. harness list shows all four harnesses'
installed/signed-in/configured/default status. ./install --opencode|--pi now
point to the command; ./install ends with the next-step hint.
2026-11-02 16:11:04 +00:00
alan 80022ea41a Keep observing chats with an in-flight turn after the last client leaves
Chat attention notifications (questions, approvals, finished replies) come
from a session's event stream, which the hub only read while a room existed;
detach destroyed the room when the last client left, so a turn that finished
or asked with the app closed notified nobody.

A room whose last client leaves now stays observing, unattended, while its
turn is in flight or it holds an unanswered question/approval, and is torn
down when the turn ends (or after 6h for a stuck turn); at most 16 such rooms.
At server start, recently used open sessions whose harness reports a running
turn (OpenCode /api/session/active, Codex thread/turns/list) are observed
again so their reply still notifies. Settings, dedupe and app_notifications
recording are unchanged.
2026-11-02 16:07:42 +00:00
alan 815f7c2a5a Stage notifications: no empty "()" and say what a waiting stage needs
A waiting human stage has no outcome yet, so its notification read
"… · waiting ()". The outcome is now shown only when recorded, and a
waiting stage reads "waiting for your decision".
2026-11-02 15:47:06 +00:00
alan eed3806efb Add a home-restricted folder picker to the new-chat dialog
Server: list_directory returns a directory_listing (path, home, parent,
entries with is_dir/is_git_repo/hidden, truncated) confined to the server
user's home subtree after cleaning and resolving symlinks, refusing pseudo
filesystems and capping entries at 2000. Documented in docs/cli.md.

App: "Choose folder…" in the create dialog opens a picker (full-screen page
on phones, large dialog on wide windows, Material and Cupertino) with
breadcrumbs, filter, Show hidden, git badges, dimmed files, recent folders,
inline errors and "Start chat here". The probe app gains a folder fixture
for captures.
2026-11-01 21:51:48 +00:00
alan 3bfb3d6b44 Fix decide-after-finish refusal and run size loop data race
A run stays in r.active after finishRunState persists its terminal status
until its goroutine finishes notifying, so a decision in that window was
refused as "already active". decide now refuses only runs whose terminal
state is not yet durable; a finished run gets ResolveDecision's
already-decided / not-waiting answer, and an executing run is still refused.

Tests overwrote runner.artifactsRoot after Handler/newRunner had started
background goroutines (sizeLoop, session export jobs) that read it. The
root is now fixed at construction through newRunnerAt, which
HandlerWithOptions uses for Options.ArtifactsRoot, and tests configure it
there instead of mutating the field afterwards.
2026-11-01 18:58:14 +00:00
alan 70cdf985c5 Show server-queued chat prompts from the server, with Remove
The thread reads the session's queued prompts from the chat_subscribe reply
and chat_queue frames: a reload draws them as Queued after the transcript,
a delivered one enters the transcript as Sent, a refused one becomes Not
sent, and Remove sends chat_unqueue. A prompt the server reports queued is
dropped from the device unsent store; the any-frame queued heuristic is
used only with a server that does not report its queue.
2026-11-01 18:42:10 +00:00