samagotchi 0.2.0 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: da62382ff837576724b356e7ac03ccb484c382628b4a3a7fcfaacf799de4cc92
-  data.tar.gz: 2822682cf66025598dbb6effc4598f97b3658fec0153cfcfaf5088a7385764dd
+  metadata.gz: 63f5d3415cd7f3cfe7f2811ab19bcabca4eafe62e349fd9d0d28fcd157c38340
+  data.tar.gz: a2fea7402c8a1cba19e795320c134e12a5cf58b026934cc954c4ecd80e6d765c
 SHA512:
-  metadata.gz: 860855c62b763f58c44d06e137f8f45abceb81e4e8169c5c46182b69ae00442cc44c285c056e79120ce2b5a6ef2516c3e7fb75739188b650fc6c918644f25796
-  data.tar.gz: 429c0f7b9fc76def59cd87a9493bddaca7813d38f73f8ce974616f9f55af89767aca8b7f9b2cd629b8e0a7fe606e98eee05ee52199a74ec6d3d13c00f23c2e82
+  metadata.gz: b8c4eb982683f47f10b9f77af3bc0b32518b8707860fcb796377870bb838ba13d326ece7b2e28f675097507478ec3723206ecd654fe8720e8653bf9a234f6930
+  data.tar.gz: fd059521495cca9d033924c818c8b35da945e6354b7806acdf65af7f275e51f9b20f5b228ff00dd81c2f16d73abd8de881d505b7eb3620e0a70792e28f4d7965

data/CHANGELOG.md

@@ -8,6 +8,201 @@ and commands may change between minor versions. How releases are made:
 
 ## [Unreleased]
 
+## [0.4.0] - 2026-09-30
+
+### Added
+
+- `chi update`: brings an installed chi up to date in one command: the gem
+  from rubygems, then the system bundle, the shipped bundles you installed and
+  the desktop helper (rebuilt only when its sources changed), shown in one
+  table. Your edits to bundle files are kept and reported, running workers and
+  an old `chi web` are only reported, `--dry-run` shows the plan, and
+  `--no-gem` / `--no-bundles` / `--no-desktop` (or `update.*` in config.yml)
+  skip parts. The first start of a new chi version says in one line when
+  something can be updated.
+- A thinking level per model, host or run: `thinking: off | low | medium |
+  high | default` (`models.<key>.thinking`, `hosts.<name>.thinking`,
+  `thinking.level`, `--thinking LEVEL`). Chat hosts get the matching request
+  fields; native Qwen and Gemma turn thinking off. chi says once when a level
+  can't work on a host, and a host that refuses the thinking fields (gpt-oss
+  on OpenRouter) is asked again without them. `/model` and `chi self` show
+  the level.
+- Edit previews: an edit/write approval shows the diff it would make, in the
+  web card and in the terminal, and every edit/write row gets a
+  "diff +3 −1" that opens to the change (live, after a reload and on a join).
+- `chi send --image PATH` (repeatable, up to 20): images go with the message
+  as attachments, the same as the web composer's chips; converted and
+  downscaled once, then copied into each session. Works with `--new` (the
+  session starts idle, then gets the message with its images) and `--wait`.
+  A missing file or a non-image stops the send before anything goes out.
+- The desktop helper takes images: a clipboard screenshot, image files from
+  Finder's Send to chi, other apps' image data, or a drop on the panel; they
+  show as thumbnails and go with the message.
+- source-links 0.3.0: `#12` links to the current project's repo (from its git
+  remote) and `owner/repo#12` to that repo; `url:` templates take `{1}`,
+  `{name}`, `{repo}` and `{host}`, with `remote:` and `remote_host:` per
+  source, and the note lists each link once.
+- The web shows when the provider is asked again after an error ("↻ retrying
+  (503) in 3 s, 1/2") or a turn waits for a plugin's setup.
+
+### Changed
+
+- A model named with a host that isn't configured (`nosuch:org/model`, or a
+  provider's name like `openrouter:x`) is an error that names the host and
+  lists the configured ones, in the CLI, `chi send --new`, the web and
+  `/model`, instead of going to the default host.
+- The terminal no longer rewrites `#word` into a memory reference: "PR #1"
+  and "#ff0000" reach the model as typed (Tab still completes `#name`).
+- A question you dismiss reaches the model as dismissed, not as a tool
+  error, so it keeps asking when it should.
+- `/quit` works in the REPL like `/exit`, and the web answers it too;
+  `/stats` and `/recap` take trailing words in both terminals.
+- A delegated session gets reworded rules: the answer first, then evidence,
+  then what's unverified; follow-up messages arrive as new turns.
+
+### Fixed
+
+- A llama.cpp server started with `--api-key` works: the key in
+  `api_key_env` is sent on every request (it got 401). A 401/403 from any host
+  now says which variable to check or to set `api_key_env`.
+- A bundle upgrade that keeps your edited file no longer disables the
+  bundle's plugin, and the system bundle stops warning about the same edit on
+  every start.
+- One bundle with a broken manifest.json no longer stops the hooks of the
+  bundles after it from loading.
+- A long-running worker picks up edited guardrail rules.
+- `write` without content fails instead of emptying the file.
+- Per-model `vision:` follows a model alias, like `profile:` and `sampling:`.
+- A timeout of 0 in config means the default on llama.cpp hosts too (it was a
+  0-second timeout).
+- A reminder turn drops a pending continue offer, so a later "no" can't roll
+  the reminder back.
+- More than 8 options in `ask_user_question` is always an error (one path
+  silently used the first 8).
+- A memory read with a comma list counts each name in the REPL and the web.
+- `/archive` or `/quit` typed during a REPL turn no longer goes to the model
+  as text; `EXIT --DELETE` works in any case in an attached terminal.
+- `chi bundle status` finds index lines again (it said "no-index" for every
+  file).
+
+Update with `chi update` (new in this version: from 0.3.0, run
+`gem install samagotchi` once, then `chi update`). Bundle moved:
+source-links 0.3.0.
+
+## [0.3.0] - 2026-09-29
+
+### Added
+
+- `chi bootstrap [HOST[:PORT]|URL]`: the first setup in one command. It finds
+  out whether the server is llama.cpp or OpenAI-compatible (with no target, it
+  looks on localhost's usual ports), picks the model, sends a test request and
+  writes config.yml; an existing config gets a `hosts:` entry added after a
+  backup, its other lines untouched. `--key-env VAR` for a server that wants a
+  key, `--model`, `--name`, `--no-test`, `--dry-run`. The first-run "no model
+  configured" line points at it.
+- Web notifications: a session that needs you (a question or approval, a
+  failed turn, a turn done after 10 s or more) while the tab is in the
+  background counts in the page title, `(N) Chi`, and with the new bell in the
+  top bar on, shows an OS notification that opens the session.
+- `chi scratch`: a one-time session in the terminal that leaves nothing behind.
+  It is deleted however it ends, saves no memories and starts no other
+  sessions; one left by a killed process goes at the next sweep or
+  `chi sessions clean`.
+- Archiving a session: `chi sessions archive ID`, `/archive` in a terminal or
+  `archive` in the web's info bar hides it (and its delegates) from every list
+  and keeps it for good; `chi sessions list --archived` and "include archived"
+  in the web's all sessions find it, and a message you send to it brings it
+  back.
+- `chi send --new` starts a session with the message, the way the web does, so
+  it shows in the web at once (`--dir`, `--model`); `chi send --wait` (new or
+  one existing session) blocks and prints the answer, exit 3 when the turn
+  waits for your answer.
+- The `check-in` bundle (`chi bundle install check-in`): after 50 tool calls
+  in one turn with no answer (then every 50 more) a card asks you to nudge
+  the model, let it keep going or stop the turn; `mode: nudge` nudges it by
+  itself. `/checkin` shows and changes it for the session.
+- Plugins can steer the running turn: `ctx.steer(text)` and a hook's
+  `event[:steer]` put text into the turn as its own message at the loop's
+  next step, shown as `<bundle>> nudged: …`; `ctx.stop_turn(reason)` stops it.
+- The `source-links` bundle (`chi bundle install source-links`): refs like
+  `JIRA-123` or `GH-45` in an answer become links in the web, and a one-line
+  `sources:` note follows the turn in the terminal. Sources are patterns in
+  `bundles: source-links:`.
+- Plugins can change how an answer is shown without changing what the model
+  sees: an after_turn hook's `event[:present]` sets a display version of the
+  answer, which the web renders (and keeps after a reload).
+- Annotate presets: selecting text in an answer offers quick replies next to
+  Annotate (default "Agreed" and "Could you please elaborate?"); a pill puts
+  the quote and the text in the composer without sending.
+  `web.annotate_presets` (`|`-separated or a YAML list; `""` turns them off).
+- `sampling:` on a `hosts:` or `models:` entry (temperature, top_p, top_k,
+  min_p, penalties, …) is sent with every request to that host or model;
+  `temperature: null` sends none, so the provider's default applies.
+- `retry.empty_answer` (default 1): when the model returns an empty answer
+  (or runs out of tokens while thinking), chi asks again once in the same
+  turn; the terminal and the web show "↻ empty answer, asking again".
+- The context fill is saved with the session: `chi sessions list` and the web
+  list show it (`ctx 12%`), and `/stats`, the status line and the web meter
+  show it right after a restart or a reload. Token totals now cover the whole
+  session across worker restarts.
+- `chi send --wait ID` with no message waits for the session's next reply
+  without sending anything (also on a running session), e.g. after `--wait`
+  exited 3 for a question.
+- The desktop panel has a "New session in <folder>" row (⏎ starts a session
+  with the selection there).
+- Web notifications also cover a check-in card waiting for you, and a chi tab
+  in front keeps the tabs behind it from notifying twice.
+
+### Changed
+
+- Stop ends a turn that is waiting in `task_wait` or running `execute` within
+  about a second, and a Stop right after a turn starts ends it at once. A
+  background task keeps running: the model is told it's still running and how
+  to continue or stop it, and the cancel note lists the session's tasks still
+  running. A stopped wait shows as "stopped".
+- config.yml: a nested key now wins over its legacy flat `SAMAGOTCHI_*` key
+  (one warning names both); an unknown key warns with a did-you-mean;
+  top-level keys like `max_tool_output_chars` no longer warn; `no_interrupt`
+  and `no_default_input` work from config and env.
+- A refused connection to a host fails at once with "can't reach host … — is
+  the server running?" instead of retrying for half a minute.
+- A host whose `/props` doesn't answer costs one probe per 30 s, not a wait
+  at every turn.
+- `chi -p … --non-interactive` with an empty answer says so on stderr and
+  exits 1.
+- docs/configuration.md uses nested keys throughout and lists every setting;
+  the README starts with `chi bootstrap`.
+
+### Removed
+
+- The unused config keys `bridge.enable` and `thinking.preview_lines` (they
+  now warn as unknown).
+
+### Fixed
+
+- The web keeps a failed turn's prompt and reason after a reload, and a failed
+  turn's prompt comes back to the composer, also for a first message from the
+  start page.
+- Web answer links appear with the answer instead of being swapped in after it.
+- The title badge clears when you switch to the tab in Safari, and drops a
+  question answered from another tab or client.
+- `/archive` and `/exit` typed in the web composer get a short reply instead
+  of an error.
+- An approval card for a tool without a command or path shows its arguments.
+- A hook notice from before the turn stays in its step after a reload.
+- Card actions (check-in's Nudge, …) no longer leave a command bubble or line.
+- A 404 from a native (llama.cpp) host hints at `api: openai`.
+- A config `memories:` entry that can't be loaded is no longer called `--memory`.
+- `chi --resume`/`--attach` refuse a leftover scratch session.
+- `chi sessions list --live/--cwd/--format` show `[scratch]` too.
+- The legacy-key warning names the right nested key.
+
+### Bundles
+
+- New: `check-in` 0.1.1 (`chi bundle install check-in`, needs chi 0.3.0) and
+  `source-links` 0.2.0 (`chi bundle install source-links`). No other bundle
+  changed since 0.2.0.
+
 ## [0.2.0] - 2026-09-27
 
 The first public release. chi is an agent harness for local models
@@ -39,5 +234,7 @@ and long-lived sessions.
 - A macOS desktop helper (`chi desktop install`): a "Send to chi" Service and a
   hotkey panel that send selected text or the clipboard to your sessions.
 
-[Unreleased]: https://github.com/dm1try/samagotchi/compare/v0.2.0...HEAD
+[Unreleased]: https://github.com/dm1try/samagotchi/compare/v0.4.0...HEAD
+[0.4.0]: https://github.com/dm1try/samagotchi/compare/v0.3.0...v0.4.0
+[0.3.0]: https://github.com/dm1try/samagotchi/compare/v0.2.0...v0.3.0
 [0.2.0]: https://github.com/dm1try/samagotchi/releases/tag/v0.2.0

data/README.md

@@ -32,9 +32,44 @@ bin/chi self
 `bin/chi` runs the checkout; `bundle exec rake gem:install` installs it as a
 local gem, which puts `chi` on your PATH.
 
+### Updating
+
+```sh
+chi update --dry-run    # what would change
+chi update              # the gem, then the bundles and the desktop helper
+```
+
+`chi update` installs the newest samagotchi from rubygems.org (old versions
+stay installed: running sessions still use them), then brings the rest up to
+the new version: the system bundle, the bundles chi ships that you installed,
+and the macOS helper (rebuilt only when its sources changed). Memory files you
+edited are kept, and the table says which. Running sessions move to the new
+chi when their worker idles out (30 min) or on `chi sessions stop ID`; a
+running `chi web` needs a restart. From a checkout, `git pull` instead. See
+[CLI: Updating](docs/cli.md#updating).
+
+## Set up
+
+Point chi at your model server; it works out the rest and writes
+`~/.config/samagotchi/config.yml`:
+
+```sh
+chi bootstrap 192.168.1.29:8081          # llama.cpp on another machine
+chi bootstrap localhost:11434            # Ollama (any OpenAI-compatible server)
+chi bootstrap https://openrouter.ai/api/v1 --key-env OPENROUTER_API_KEY
+chi bootstrap                            # look on this machine's usual ports
+```
+
+It finds out whether the server is llama.cpp or OpenAI-compatible, picks the
+model (or asks, when there are several), sends one test request and writes
+the config. With a config already there, it adds a `hosts:` entry and keeps
+the rest of the file. Edit the file later as in [Configure](#configure);
+`chi bootstrap --help` has the options.
+
 ## Configure
 
-Create `~/.config/samagotchi/config.yml` (or `$XDG_CONFIG_HOME/samagotchi/config.yml`):
+To write the config by hand instead, or to change it later: create
+`~/.config/samagotchi/config.yml` (or `$XDG_CONFIG_HOME/samagotchi/config.yml`):
 
 ```yaml
 default:
@@ -44,7 +79,20 @@ server:
   port: 8080
 ```
 
-Other settings (multiple hosts, transports, timeouts, the idle recap) are in
+`server:` is a llama.cpp `llama-server`. For any other OpenAI-compatible
+server (vLLM, LM Studio, Ollama, a gateway), name it under `hosts:` with
+`api: openai` instead:
+
+```yaml
+default:
+  model: local:qwen3:8b    # host:model; the ids are in GET <url>/models
+hosts:
+  local:
+    url: http://localhost:11434/v1   # the API base, /v1 included
+    api: openai
+```
+
+`chi self` shows the model and host chi will use. Other settings (multiple hosts, transports, timeouts, the idle recap) are in
 [Configuration](docs/configuration.md).
 
 ## Use
@@ -58,11 +106,12 @@ chi web --open                            # web UI: this project's sessions (--s
 chi sessions list                         # this project's saved sessions (--scope=all: every one)
 pbpaste | chi note --source slack <id>    # background context for a session (no turn)
 pbpaste | chi send -m "same bug?" <id>    # a message to a session, the clipboard quoted above it
+chi send --new --wait -m "review feat/x"  # a new session you can watch in the web; prints the answer
 ```
 
 `@shot.png` in a prompt (or a pasted/dropped image in the web UI) shows the model an image, when it can see them; see [Images](docs/cli.md#images).
 
-`/model` switches models, Ctrl-C cancels a turn, and Ctrl-D or `/detach` detaches (the session keeps running; `chi --attach ID` comes back). `/exit` detaches and stops the session's worker too, unless something still needs it (a running turn, another UI); `chi --resume ID` picks the conversation up again. `/exit --delete` also deletes the session once the worker has gone; `chi sessions delete ID` deletes one from the shell.
+`/model` switches models, Ctrl-C cancels a turn, and Ctrl-D or `/detach` detaches (the session keeps running; `chi --attach ID` comes back). `/exit` detaches and stops the session's worker too, unless something still needs it (a running turn, another UI); `chi --resume ID` picks the conversation up again. `/exit --delete` also deletes the session once the worker has gone; `chi sessions delete ID` deletes one from the shell. `/archive` (or `chi sessions archive ID`) hides a session from every list and keeps it for good; `chi sessions list --archived` finds it again.
 
 ### Context notes
 
@@ -78,7 +127,9 @@ reply (a normal session: `chi --attach <id>` steers it).
 
 `chi send` is the other half: the text goes in as your message, the same as
 typing it in the attached terminal or the web composer, and a turn runs. Piped
-stdin plus `-m` puts the stdin above the message as a `>` quote.
+stdin plus `-m` puts the stdin above the message as a `>` quote. `chi send --new`
+starts a session with the message instead (it shows in the web at once), and
+`--wait` blocks and prints the answer.
 
 ### Send to chi (macOS)
 
@@ -119,6 +170,7 @@ once, for the session, for the repo, or for the whole rule in the repo.
 ```sh
 bundle exec rspec    # Ruby specs
 npm test             # web frontend specs
+npm run e2e          # web UI happy paths in Chromium, fake model (once: npx playwright install chromium)
 ```
 
 ## License