samagotchi 0.45.0 → 0.46.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1dc1da4c0179829c1e78da27358f269fba9fcd1ee2a2412b73493bab37a1d81d
-  data.tar.gz: b04878e89e0d634c817e748cc9fe435728e4c6c62863d719a53b4080b1ea5ff0
+  metadata.gz: 9143ff1fecadcc026c2e0b079d61551359985d72d080f33fc7074af8f90402c1
+  data.tar.gz: 04d7e899417b9684ac61d337361ca91e8fa58dcdd091611109fcfff677a351ba
 SHA512:
-  metadata.gz: c0331854a38cff99772512941a1ce8227dc10448c00d4d4c758ba532cfdd19b311e7f4d9733bce7745645231794ec93212a658a542563a8f56008c97492f8c90
-  data.tar.gz: 984e5ce3436b750c872bf0a7dd10f1282ed7f4eaf9c084d9f1add023bdcee5088c8f48acbd9eb3e3d01e2efa8dad200c3a350a4a903725aa1de6597407c9ee36
+  metadata.gz: 272e94da604a43b0d3b6f405dc7b2bbe420e4c7adffc9fba6b8c5ecf52811b4411c4fce03e32e85e00ee60b1f30b395daf107a459e842e196803d08658bcfdf0
+  data.tar.gz: b3262e257e88b57a739e61c3774d5c2bbef910956fcd9fc6ef726275ddc4bbc10a59ee70a1a9236a50aada19e9663338e32077720bfc1d6b0db6fcbf7e059a43

data/CHANGELOG.md

@@ -8,6 +8,95 @@ and commands may change between minor versions. How releases are made:
 
 ## [Unreleased]
 
+## [0.46.1] - 2026-10-09
+
+### Changed
+
+- The terminal and the web word a retry line the same: `↻ retrying (503) in 4.0s, 2/5`, why in parens (the HTTP
+  status, the error's short name such as `ECONNREFUSED`, or `stream dropped`), the wait with one decimal, and the
+  retry of all there will be. The terminal said `retrying (2/5 in 4.0s)`, the web `↻ retrying (503) in 4 s, 2/5`.
+
+### Fixed
+
+- A question the model asks in a `chi -p --non-interactive` run no longer tells the model the user dismissed it:
+  it is told no one could answer (a non-interactive run). The question closes with reason `non_interactive`.
+- The web's card for a question closed that way reads "No one could answer (non-interactive run)", not
+  "Cancelled (non_interactive)".
+- A delegate's report read by a turn that ended canceled is no longer brought a second time when the Engine's
+  post-turn work then fails (a full disk, say).
+- github-pr 0.3.3: a `path:line` into a vendored copy (`vendor/lib/foo.rb:21`, or `/abs/repo/vendor/lib/foo.rb:21`)
+  is no longer linked to the PR's `lib/foo.rb` in the web: an absolute path's part before the PR path must be a
+  worktree's root (a directory with `.git`), or no directory on this machine. An absolute path into a worktree, or
+  one up from a subdir (`../lib/foo.rb`), still is.
+- A step whose stream kept dropping now fails saying how many requests it made ("after 3 attempts"), not
+  "after 1 attempts"; one attempt is said in the singular.
+- A step that ends on another error after its stream dropped (a 503) counts the dropped requests in that
+  error's attempts too, and a step asked again without thinking fields (a host refused them) keeps its count of
+  stream drops: it no longer gets two more ask-agains of its own.
+- A host that is down is named once in the models list's warning and in `/models` (`gw: connection refused`, not
+  `gw: gw: connection refused`).
+- A host whose model listing kept failing on network errors is named once too, in the models list's warning, the
+  web's and `/models` (`gw: request failed after 3 attempts: …`, not `gw: gw request failed after …`).
+- `/stats`' estimated cost names the host whose prices it used (`from hosts.gw.models prices`), not a literal
+  `hosts.<name>.models`.
+- The config warning for a model price's old `cached` key suggests `cache_read`, its new name.
+- The web's ⚠ for a model the server served instead of the one asked now shows on a session opened with no
+  worker running too (from its saved analytics), not only while its worker runs.
+- A host whose `/v1/models` fails no longer drops the ids declared under `hosts.<name>.models` from `chi models`,
+  `/models` and the web model picker: they stay, marked `host down` (greyed in the picker, still pickable;
+  `unavailable: true` in the JSON), next to the host's warning. Ids only the host itself lists still drop out.
+
+Update with `chi update`: it updates github-pr (0.3.3: no links from a vendored copy to the PR's file).
+
+## [0.46.0] - 2026-10-09
+
+### Added
+
+- `hosts.<name>.models:` declares the model ids a host serves whatever its `/v1/models` lists (a gateway's
+  round-robin ids), as a map of ids or a plain list. A declared `host:id` is never warned about or re-listed at
+  `chi send --new` and delegate spawns, and a bare id routes to its declaring host as if listed, before any
+  `/models` and in workers too. Two hosts declaring one id warn at start. See "Models a host serves but doesn't
+  list" in [docs/configuration.md](docs/configuration.md).
+- Declared `hosts.<name>.models` ids show first under their host in `/models` (as `rr/x (config)`, outside the 20
+  per host, also on a host that lists nothing), `chi models` (plain names; `--format json` adds `configured: true`)
+  and `GET /api/models` (`configured: true`). A host that doesn't answer shows none of them.
+- `hosts.<name>.models.<id>.price: {input, output, cache_read?, cache_write?}` (USD per 1M tokens) estimates the
+  cost of a generation whose provider reports none, or reports 0. A reported non-zero cost always wins. The estimate
+  is saved apart (`cost_estimate` per turn, `cost_estimate_sum` in the totals). See "Prices" in
+  [docs/configuration.md](docs/configuration.md).
+- `hosts.<name>.models.<id>.served: [ids]` (or `any`) names the models a gateway may answer a round-robin id with.
+  Those are no longer marked as served by another model (the web's `⚠`, the status line's `(served; asked …)`,
+  `/model`'s `served:`, `/stats`' "(asked for …)"); one it doesn't name still is.
+- An estimated cost shows with `~`: `/stats` (`$0.42 reported + ~$0.12 from hosts.<name>.models prices`) and the
+  ctx tooltip on the info bar and the session cards (`cost: ~$0.54 ($0.42 reported, ~$0.12 estimated)`).
+- The web model picker lists a host's declared ids first under it, noted `config` (the default model keeps
+  `default`), with `served by config (hosts.<name>.models)` in the row's tooltip.
+
+### Fixed
+
+- A chat generation whose stream dropped mid-answer (a read timeout or a reset after deltas had shown) failed the
+  whole turn: the chat loop now drops the partial reply and asks again for the same step, from the same
+  conversation, at most twice, reporting each ask-again as `generation_retrying`, as the transport's retries do.
+  A cancel, a provider error, a first-token timeout and a connection refused still fail as before, and a step whose
+  retries run out fails the turn with the same error. Each ask-again waits the transport's backoff (`retry.*`),
+  which a cancel cuts short, and `retry.max` caps the asks-again (`retry.max: 0` turns them off). Its
+  `generation_retrying` carries `restarted: true`: the web's live step, the TUI's activity line, a reload in the
+  middle of the turn and the stream hooks drop the partial reply, so the answer shows once.
+- `task_stop` could signal an unrelated process group whose leader reused a finished task's pid. A task now records
+  its process's start time, and a pid that started at another time is not signalled (the task ends as failed).
+- A delegate's report merged into a reminder or continue turn was lost when the turn failed past its loop (the
+  turn's own end, say): the turn kept only its start, yet the report counted as read. Its ring now stays, and the
+  next turn brings it.
+- A delegate wait that relayed a child's approval ran to its timeout when the child ended its turn with no reply
+  while the answer was being posted; it now ends there.
+- Chi Helper: a send that ended after the panel was reopened wrote its "sent"/"failed" line into the new panel, and
+  a success could close it; like a broadcast, it now leaves the new open alone.
+- `chi -p … --non-interactive` hung forever when the model asked a question (`ask_user_question`) while its stdin
+  was a pipe that stayed open (`sleep 30 | chi -p …`, a parent holding stdin): it waited for an answer line. Nobody
+  can answer there, as for an approval: the question is dismissed at once (one line on stderr), the model finishes
+  its reply, and stdin is never read. Piped answers without `--non-interactive` (`printf '2\n' | chi --no-shared -p
+  …`) work as before.
+
 ## [0.45.0] - 2026-10-08
 
 ### Added
@@ -2094,7 +2183,9 @@ 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/v0.45.0...HEAD
+[Unreleased]: https://github.com/dm1try/samagotchi/compare/v0.46.1...HEAD
+[0.46.1]: https://github.com/dm1try/samagotchi/compare/v0.46.0...v0.46.1
+[0.46.0]: https://github.com/dm1try/samagotchi/compare/v0.45.0...v0.46.0
 [0.45.0]: https://github.com/dm1try/samagotchi/compare/v0.44.0...v0.45.0
 [0.44.0]: https://github.com/dm1try/samagotchi/compare/v0.43.0...v0.44.0
 [0.43.0]: https://github.com/dm1try/samagotchi/compare/v0.42.0...v0.43.0

data/docs/architecture.md

@@ -287,7 +287,8 @@ The metrics in `/state`, `/snapshot`, `/stats` and the SSE `snapshot`/`reset` fr
 newest turn the worker finished and any it hasn't saved yet (at most 20 turns), with their tool
 calls and the running turn's finished ones. The full history is the session's `analytics.json`,
 which `SessionMetrics#persist` rewrites after each turn; the web server merges the two by id.
-The totals' `tokens` block adds the cached, cache-write and reasoning sums, the cost, the decode time and tokens
+The totals' `tokens` block adds the cached, cache-write and reasoning sums, the reported cost (`cost_sum`) and the
+estimated one (`cost_estimate_sum`, from `hosts.<name>.models` prices; 0 for none), the decode time and tokens
 behind the average speed (`avg_decode_tps`) and the last speeds (`last_decode_tps`,
 `last_prefill_tps`, `tps_source`: `server` or `estimate`). Each `generation_completed` event
 carries the generation's `speed` (`{decode_tps, source}`, null without one), its own prompt-cache

data/docs/cli.md

@@ -85,14 +85,20 @@ small -> box:gemma-small         # an alias and the ref it resolves to
 $ chi models qwen                # only the names containing "qwen" (any case)
 ```
 
+- A host's ids declared under `hosts.<name>.models` (see
+  [configuration](configuration.md#models-a-host-serves-but-doesnt-list)) come first under that host, listed or not,
+  as plain names like any other. They stay when the host fails, and its stderr warning says so
+  (`chi models: box: connection refused (its declared ids are still listed)`).
 - A default-host id is bare, except one with a `:` (`qwen3:8b`), which is written `<host>:qwen3:8b` so it can't
   read as a host name. An id that an alias of the same name hides is left out.
 - Each run lists anew (no cache); `--timeout S` caps the wait for the hosts (default 4 s). A host that fails or doesn't
   answer in time is noted on stderr (`chi models: box: no answer in 4 s`).
 - `--format json` prints one object: `default` (and `default_typed` when it was set as an alias), `default_host`,
-  `models` (`name`, `host`, `id`), `aliases` (`name`, `ref`, `host`) and `warnings`. The desktop helper's model
+  `models` (`name`, `host`, `id`, and `configured: true` on an id declared under `hosts.<name>.models`,
+  `unavailable: true` too when that host failed to list its models), `aliases` (`name`, `ref`, `host`) and `warnings`. The desktop helper's model
   chooser reads it.
-- Exit 0 when any host listed its models, 1 when none did (the default is still printed), 2 on a usage error.
+- Exit 0 when any host listed its models, 1 when none did (the default and declared names still print), 2 on a
+  usage error.
 
 ### Updating
 
@@ -245,6 +251,10 @@ Notes:
   then `chi: the session is kept with your prompt; continue it with: chi
   --resume ID` (exit 1). Ctrl-C saves the session with the prompt and a
   cancel note and exits 130.
+  Nobody can answer there: an approval is denied, and a question the model
+  asks (`ask_user_question`) is dismissed at once (one line on stderr), never
+  read from stdin. The model is told no one could answer (a non-interactive
+  run), not that you dismissed it, and finishes its reply.
 
 ### Scratch sessions
 
@@ -430,8 +440,10 @@ reports them),
 the decode speed, generation latency, cancellations, retries (the network's),
 thinking cuts (generations a plugin such as loop-guard cut) and output cap hits
 (generations that ended at the provider's cap), context used and window (the used figure is counted against the smaller of the window and the session's LLM context budget, and says so: `context used:     16000 tokens (25.0% of the 64000 budget)`), the memory indexes the session's prompt holds ([Memory](memory.md#the-indexs-size)), the model notes it carried (`model notes:      model_notes_deepseek (system, 612 chars)`, none without any; [Memory](memory.md#model-notes)), the prompt profile and the model the server says it ran, and the
-cost when the provider reports one (OpenRouter's `usage.cost`; no prices are
-guessed). The speed line is the last generation's and the session's average
+cost when the provider reports one (OpenRouter's `usage.cost`), and the cost
+estimated from a price under `hosts.<name>.models` when it reports none or 0,
+marked `~` and naming the current model's host (`cost:             $0.42 reported + ~$0.12 from hosts.gw.models prices (this session only)`;
+see "Prices" in [configuration](configuration.md#prices)). The speed line is the last generation's and the session's average
 (weighted by tokens): llama.cpp reports it exactly (`87 tok/s out, 1.9k tok/s
 prompt (last, server)`); for other servers it is estimated from the first
 streamed chunk to the end and marked `~` (`~64 tok/s out (last, estimate)`).
@@ -734,7 +746,7 @@ In interactive assist mode, you can switch the request model without restarting:
 - `/model`: show the effective model (and default when diverged: `runtime model: <effective> (default: <default>, profile=<name>, <source>)`, e.g. `profile=qwen36, server (chat_template)`). When the session's prompt carries model notes the line ends with `; notes: model_notes_deepseek (system, 612 chars)`; a switch's `runtime model set to …` names the new model's ([Memory](memory.md#model-notes)).
 - `/model clear` (or `default`/`none`/`off`): clear the session override, reverting to the configured default.
 - `/guardrails`: the guardrail rules (by source), what failed to load, and your stored approvals, numbered; `/guardrails revoke N` removes approval N (see [Guardrails](guardrails.md)).
-- `/models`: list model ids aggregated across all `hosts:` (an alias shows next to its id: a bare alias on every host listing the id, a `host:model` one only under its host; grouped `host (host:port):` with per-host `unreachable` warnings, e.g. an unset `api_key_env`; lists cached 60s, 10 minutes for a remote host; lazy — no startup prefill). At most 20 ids per host, then `… and N more`; `/models <text>` lists every id containing `<text>` (any case), e.g. `/models qwen` on OpenRouter.
+- `/models`: list model ids aggregated across all `hosts:` (an alias shows next to its id: a bare alias on every host listing the id, a `host:model` one only under its host; grouped `host (host:port):` with per-host `unreachable` warnings, e.g. an unset `api_key_env`; lists cached 60s, 10 minutes for a remote host; lazy — no startup prefill). Ids the host declares under `hosts.<name>.models` come first, as `rr/x (config)`, and don't count toward the cap; an unreachable host keeps them, under its warning, as `rr/x (config, host down)`. At most 20 ids per host, then `… and N more`; `/models <text>` lists every id containing `<text>` (any case), e.g. `/models qwen` on OpenRouter.
 
 Notes:
 
@@ -837,7 +849,8 @@ status> model=Qwen3.6-35B | ⑂ 2 running · 1 waiting | ctx=8.1% (under20) | me
 ```
 
 - `model=`: the model in use, `(default: …)` beside it when it isn't the config's default, and
-  `model=<served> (served; asked <name>)` when the server said it served another model.
+  `model=<served> (served; asked <name>)` when the server said it served another model (not for one its host's
+  `hosts.<name>.models.<id>.served` names; see [configuration](configuration.md#models-a-host-serves-but-doesnt-list)).
 - `↳ <id>`: the session that delegated this one.
 - `⑂ …`: this session's delegate children (forks aren't counted): how many run and how many wait
   for an answer; only the counts there are, nothing when none does (`/children` has the rest:
@@ -884,7 +897,9 @@ While a turn runs, one row above the prompt says what it is doing, the spinner f
   Qwen `TURN:` prefix and inline markdown are left out.
 - `| waiting for the first token… 5s` after 2 s with nothing streamed.
 - `| running execute…` while a tool runs (its `tool>` line prints when it ends).
-- `| retrying (1/3 in 0.5s): Errno::ECONNREFUSED` while a network error is retried.
+- `| ↻ retrying (ECONNREFUSED) in 0.5s, 1/3` while a failed request is asked again: why (the HTTP status such as
+  `503`, the error such as `ECONNREFUSED`, or `stream dropped`), the wait, and the retry of all there will be.
+  The web's timing line words it the same.
 - `| mcp: starting servers…` while a plugin's slow setup (an init task) runs, between turns too;
   `mcp> ✓ …` prints when it is done.
 

data/docs/configuration.md

@@ -413,6 +413,41 @@ models:
 `SAMAGOTCHI_HOSTS_JSON`, and reads `models:` from the config file each turn: after changing a host's `sampling:`,
 stop the session's worker (`chi sessions stop`) for it to take effect.
 
+## Prices
+
+A provider that reports no cost (`usage.cost`), or reports 0, can still be priced: give the model a price under
+the host that serves it, in USD per 1M tokens.
+
+```yaml
+hosts:
+  work:
+    url: https://gateway.example/v1
+    api: openai
+    models:
+      rr/deepseek-v4.1:
+        price: {input: 0.27, cache_read: 0.07, output: 1.10}
+  openrouter:
+    url: https://openrouter.ai/api/v1
+    api: openai
+    models:
+      qwen/qwen3.8-27b: {price: {input: 0.10, output: 0.40}}   # a listed id, here only for its price
+```
+
+- `input` and `output` are required; `cache_read` and `cache_write` are optional. Each is a number >= 0; a price
+  missing one of the required two, or with a value that isn't a number >= 0, warns at start and is ignored.
+- An unset rate is the input rate: that overstates cached reads, and understates Anthropic cache writes (billed
+  1.25x input for the 5 min cache, 2x for 1 h). Set them when it matters.
+- A price is per host, since one model can cost differently on two hosts. It is looked up by the model the session
+  asked for (its host and id), never by the model the host says it served.
+- Each generation with the server's token counts is estimated as uncached prompt × `input` + cached reads ×
+  `cache_read` + cache writes × `cache_write` + completion × `output`, over 1M. A generation with only estimated
+  counts (characters / 4, no usage from the server) isn't priced.
+- A reported cost wins: a generation with a non-zero `usage.cost` is never estimated. A reported 0 with a price is
+  estimated (a gateway that bills elsewhere reports 0); the 0 is kept as the reported cost.
+- The estimate is saved apart from the reported cost (`cost_estimate` per turn, `cost_estimate_sum` in the
+  session's totals in `analytics.json`) and shows with a `~`.
+- A server that sends no cached counts has its whole prompt priced at `input`: an overestimate.
+
 ## Thinking
 
 How much a model thinks before it answers. One level, `off`, `low`, `medium`, `high` or `default`, set per model,
@@ -555,11 +590,12 @@ When `default.model` is unset or blank, Samagotchi fails fast with a clear start
 With several `hosts:`, `host:model` (or an alias naming a host) pins the host.
 An unqualified model name goes to the default host when its `/models` list has
 that exact id, else to the first host in `hosts:` order whose list has it, else
-to the default host. Only exact ids count, never a substring: `/model gemma` on
+to the default host. A host's declared ids (`hosts.<name>.models`, below) count
+as listed. Only exact ids count, never a substring: `/model gemma` on
 a box that lists `gemma-4-26b` needs `box:gemma` or the exact id. The lists are
 known only after `/models` ran (nothing is fetched before the first turn), so
-until then an unqualified name goes to the default host; use `host:model` to pin
-one. A **remote** host (an `https` url or a public address; see "Remote or local") keeps its model
+until then an unqualified name goes to the default host, unless a host declares
+it; use `host:model` to pin one. A **remote** host (an `https` url or a public address; see "Remote or local") keeps its model
 list for 10 minutes (60s for local hosts).
 
 **The context window** (what the context status and `ctx=` count against) comes from,
@@ -608,6 +644,59 @@ alias, `/model`, `chi send --new --model`, the web's new-session model and a
 delegate's model. Any other unknown prefix (`nosuch:x`) is sent to the default
 host as the model id.
 
+### Models a host serves but doesn't list
+
+A gateway can serve ids its `/v1/models` never lists (round-robin aliases such
+as `rr/deepseek-v4.1`). Declare them under the host:
+
+```yaml
+hosts:
+  work:
+    url: https://gateway.example/v1
+    api: openai
+    api_key_env: WORK_API_KEY
+    models:
+      rr/deepseek-v4.1:
+      rr/qwen3.8-27b:
+```
+
+A plain list says the same: `models: [rr/deepseek-v4.1, rr/qwen3.8-27b]`. Ids are
+full ids (no globs), matched case-insensitively. A declared id is known on its
+host whatever the host lists:
+
+- `work:rr/deepseek-v4.1` never gets the "host 'work' doesn't list model" warning,
+  and the host isn't re-listed for it (`chi send --new --model`, delegates).
+- A bare `rr/deepseek-v4.1` goes to `work` as if `work` listed it, also before
+  any `/models` and in a session's worker. When several hosts list or declare an
+  id, the default host wins if it is one of them, else the first in `hosts:`
+  order; two hosts declaring one id get a warning at start saying which one a
+  bare id goes to. `host:id` still pins a host.
+
+**A gateway that answers with another model.** A round-robin id is served by one
+of its targets, and the reply names that one (`fireworks/deepseek-v4.1`), so chi
+marks every turn as served by another model than asked (the web's `⚠`, the status
+line's `(served; asked …)`, `/model`'s `served:`). `served:` lists the models the
+host may answer with, as exact ids (any case), or `any`:
+
+```yaml
+hosts:
+  work:
+    models:
+      rr/deepseek-v4.1:
+        served: [fireworks/deepseek-v4.1, baseten/deepseek-v4.1]
+      rr/qwen3.8-27b:
+        served: any
+```
+
+A served model it names is no mismatch: the web and the status line keep the name
+you asked for, and `/stats` names the served model without "(asked for …)". One it
+doesn't name is still marked. `any` gives that check up for the id.
+
+**Root `models:` vs `hosts.<name>.models:`.** The root `models:` holds settings
+by model name (sampling, thinking, window, profile…), on whatever host the model
+runs on; it says nothing about which host serves a model. `hosts.<name>.models:`
+says which models that host serves. Keep settings in the root one.
+
 ### Model aliases
 
 `model_aliases:` maps a name to a model id or `host:model`. An alias works
@@ -641,12 +730,17 @@ Transient network failures are retried automatically with exponential backoff.
   budget, so it fails at once (lower `default.max_tokens` or raise the key's limit).
 - A refused connection (nothing listening) is not retried: the turn fails at once with `can't reach host <name> at
   <address> (connection refused) — is the server running?`.
-- A stream that has already produced output is never retried (the retry would repeat it); it fails the turn.
+- A stream that has already produced output is never retried at the transport (the retry would repeat it). The
+  chat loop (an OpenAI-compatible host) drops the partial reply and asks again for the whole step, from the same
+  conversation, at most twice (at most `retry.max` times when that is smaller: `retry.max: 0` turns it off), after
+  the same backoff, reported as a retry (`↻ retrying (stream dropped) …`); once those run out the turn fails with
+  the error, as before. A refusal, a first-token timeout, a provider error and a cancel are never retried this way.
 - Cancellation (`Ctrl-C`) is never retried.
 
 Configuration:
 
-- `retry.max` (default `5`, env `SAMAGOTCHI_RETRY_MAX`): number of retries after the first failed attempt.
+- `retry.max` (default `5`, env `SAMAGOTCHI_RETRY_MAX`): number of retries after the first failed attempt; it also
+  caps a dropped stream's asks-again (at most 2), and `0` turns those off too.
 - `retry.base_delay` (default `0.5`, env `SAMAGOTCHI_RETRY_BASE_DELAY`): backoff base delay in seconds.
 - `retry.max_delay` (default `8.0`, env `SAMAGOTCHI_RETRY_MAX_DELAY`): cap for backoff delay in seconds.
 
@@ -680,7 +774,9 @@ and a plugin's steer (`ctx.steer`, `ctx.sessions.send`) never cuts.
 
 Assist-mode UX:
 
-- While waiting, retry notices are rendered in the existing thinking spinner area as a red `network error: retrying ...` status.
+- While waiting, a retry shows in the activity row (the web's timing line words it the same):
+  `↻ retrying (503) in 4.0s, 2/5`: why (the HTTP status, the error's short name such as `ECONNREFUSED`, or
+  `stream dropped`), the wait, and the retry of all there will be.
 - If retry attempts are exhausted, the submitted prompt is restored into the input editor so you can edit and resubmit.
 
 ## Server errors
@@ -1036,6 +1132,9 @@ described in their own sections.
 | `thinking.turn_preamble` | `true` | yes | Ask a `qwen36` model to open its thinking with a short `TURN:` line (the step label). |
 | `thinking.level` | `default` | `--thinking` | `off`, `low`, `medium`, `high` or `default` for every model; the flag and env outrank the `models:`/`hosts:` entries, the file's value doesn't. See "Thinking". |
 | `models.<key>.thinking`, `hosts.<name>.thinking` | none | | A model's or host's level. See "Thinking". |
+| `hosts.<name>.models` | none | | The model ids a host serves whatever its `/v1/models` lists: a map of ids, or a plain list. See "Models a host serves but doesn't list". |
+| `hosts.<name>.models.<id>.served` | none | | The models the host may answer that id with (exact ids, any case), or `any`: no served-model warning for those. See "Models a host serves but doesn't list". |
+| `hosts.<name>.models.<id>.price` | none | | The model's price on that host, USD per 1M tokens: `input`, `output`, optional `cache_read` and `cache_write`. Estimates the cost a provider doesn't report. See "Prices". |
 | `hosts.<name>.remote` | by address | | `true`/`false`: treat the host as a remote provider or a local server. See "Remote or local". |
 | `max_tool_output_chars` | `10000` | yes | Characters of each tool output kept in the conversation (both loops); a longer one is cut and ends with `[cut: N of M chars; read it in parts]`. A top-level key (see below). |
 | `cache.warmup` | `auto` | | `auto`: after a turn, send the next turn's prompt (up to the next message) to a local llama.cpp host on the native loop, so the next turn prefills only its message; never a remote or `api: openai` host. `off`: never. See [prompt caching](internals/prompt-caching.md#the-turn-end-warm-up). |

data/docs/desktop.md

@@ -62,7 +62,8 @@ for an alias), your recent picks and every host's
 models and aliases (from [`chi models`](cli.md#listing-the-models)), at most nine at a time.
 
 - Type to search: every word must match the host or the id; names starting with what you typed rank first. A name
-  no host lists is offered at the bottom as "not listed" and sent as typed (a host that is down, a model just added).
+  no host lists is offered at the bottom as "not listed" and sent as typed (a model just added, or one a down host
+  doesn't declare: a down host's `hosts.<name>.models` ids stay in the list).
 - ↑/↓ and ⏎, a click, or ⌘1…⌘9 pick; Esc (or ⌘M) closes the chooser only, a second Esc the panel. While an input
   method is composing, ⏎, the arrows and Esc are its own.
 - The row then shows the pick in the accent colour, and ⏎ sends `chi send --new --model <name>`, the name exactly as

data/docs/internals/background-tasks.md

@@ -19,6 +19,7 @@ Behavior:
 
 - `execute`, `task_create` and the `!cmd` shell bang run the command in a non-login shell: `/bin/sh -c` on Linux; on macOS, when `/bin/zsh` is there, `/bin/zsh --emulate sh +o ignore_braces +o sh_glob -o bash_rematch +o bsd_echo -c` (macOS's `/bin/sh` is bash 3.2, which can't parse an apostrophe in a heredoc inside `"$( )"`, the usual commit message shape). That mode reads no rc files and keeps POSIX word splitting, unmatched globs left as is, `{1..3}`, `[[ … =~ (…) ]]` with `BASH_REMATCH`, arrays, `$'…'`, `&>` and echo expanding `\t`. Bash-only builtins and variables (`shopt`, `BASH_VERSION`, `${!prefix*}`, `read -p`) are not there.
 - Task metadata and output are persisted under `tmp/tasks/`.
+- A task record keeps its process's pid and start time (`pid_started`). Before `task_stop` signals, the pid must still lead its own process group and must not have started at another time; otherwise the pid was reused by another process, nothing is signalled and the task ends as failed. A start time that can't be read at that moment (a failed `ps`) falls back to the group check, as does a record without `pid_started` (from an older chi). `task_get`, `task_list` and `task_wait`'s polls check the group only (no `ps` per poll).
 - Task listing is workspace-scoped (current project only).
 - `task_get` returns metadata and `output_path`; use `read` for output contents.
 - `task_wait` accepts `timeout`, `tail_lines` (maximum 100), and `done_pattern` (a regular expression string).

data/docs/internals/engine.md

@@ -293,7 +293,7 @@ Turn events (the main ones; `Events` in `events.rb` keeps the shared sets):
 | `:context_status` | the window's fill crossed a bucket | `{iteration, ...}` |
 | `:generation_started` | a request begins | `{iteration, context_window_tokens, context_window_source}` (native adds `profile`, `profile_source`) |
 | `:generation_chunk` | each streamed chunk | `{iteration, content, text, thinking, payload, tool_call?}` |
-| `:generation_retrying` | the transport retries the request | `{iteration, ...}` (the retry's fields) |
+| `:generation_retrying` | the transport retries the request, or the chat loop asks again for a step whose stream dropped mid-answer (`restarted: true`: what the step streamed is void, and the web's live step, the TUI's activity line, the Bridge's TurnAccumulator and the stream hooks' watch start it over) | `{iteration, attempt, max_retries, next_delay, error_class, error_message, status, restarted?}` |
 | `:generation_completed` | a generation ended, or was cut | `{iteration, content_length, thinking_chars, served_model, requested_model, finish_reason, ...}`; a cut adds `stopped_by`, `stop_reason`; the Engine adds `speed`, `tokens` |
 | `:generation_cancelled` | the turn was cancelled mid-loop | `{iteration, reason, stopped_by}` |
 | `:empty_answer_retry` | an empty, cut or malformed answer is asked again | `{iteration, attempt, of, finish_reason, thinking_chars, stopped_by?, malformed?}` |

data/docs/internals/llm-context-live.md

@@ -0,0 +1,111 @@
+# The llm_context live runs
+
+`script/llm_context_live.rb` runs chi itself on real coding tasks under each LLM context strategy and scores the
+sessions. The replay benchmark ([llm-context-bench.md](llm-context-bench.md)) scores stored sessions offline. These
+runs close the loop: the model lives with the strategy for a whole task, so they measure what the replay can't, such
+as whether a forgotten output comes back as a re-read and whether a note narrows the scope (context strategies P6).
+It is a development tool under `script/` and isn't shipped with the gem. It calls a paid model, so it is opt-in: the
+specs drive it with fakes on synthetic data.
+
+```sh
+ruby script/llm_context_live.rb validate TASKS ROOT                     # no model
+ruby script/llm_context_live.rb run TASKS ROOT --model openrouter:deepseek/deepseek-v4.1-flash \
+     [--tasks T1,T3] [--arms none,stale,stale_forget] [--samples 3] [--budget 64000|off] [--cap 8] [--jobs 3] [--limit 9]
+ruby script/llm_context_live.rb report ROOT [--json]
+ruby script/llm_context_live.rb grade|collect TASKS ROOT RUN...          # again, for runs already done
+```
+
+`TASKS` (a YAML file) and `ROOT` (where the runs and results go) live outside the repo. They hold task prompts and
+session files, and no session text goes into the repo, scrubbed or not.
+
+## Tasks
+
+A task is a real merged fix, replayed from its parent commit. The fix's spec changes are held back and graded
+afterwards.
+
+```yaml
+source_repo: /path/to/samagotchi
+tasks:
+  T1:
+    fix: 545a3562            # the run's repo is its parent
+    size: S
+    turns:                   # one chi turn each; {repo} is the run's repo path
+      - "In {repo} … find the cause and plan the fix. Don't edit yet."
+      - "Implement the plan and run the specs."
+    hidden: [spec/broadcast/triage_spec.rb]       # optional: the fix's *_spec.rb
+    regression: [spec/broadcast/triage_spec.rb]   # optional: the hidden ones' paths
+    fix_files: [lib/samagotchi/broadcast/triage.rb, spec/broadcast/triage_spec.rb]  # optional: what the fix changed
+```
+
+A file at `hidden/<task id>/<path>` beside the tasks file stands in for that hidden spec. Use it when the fix's spec
+pins a detail that another correct fix would get differently, such as an exact page size; the override keeps only the
+contract.
+
+`validate` checks each task's hidden specs: they must fail at the fix's parent and pass at the fix.
+
+## A run
+
+Each task × arm × sample is a run in `ROOT/runs/<task>-<arm>-s<n>/`:
+
+1. **prepare:** `git archive <fix>^` into `repo/`, then a fresh git repo with one base commit. It writes chi's config
+   in `config/` (the model's host copied from `--hosts-config`, default the user's config.yml; `turn.max_iterations:
+   150`; `recap: false`; `llm_context.apply: payoff`, no `stale_edits`). State goes in `state/`, and it runs `chi
+   bundle install loop-guard`. Every chi and rspec command gets `SAMAGOTCHI_ENV=test`, the run's `XDG_STATE_HOME`
+   and `XDG_CONFIG_HOME`, and no inherited `SAMAGOTCHI_HOSTS_JSON` (the smoke-run isolation).
+2. **run (Driver):** `chi send --new --wait --format json --dir repo --model M --llm-context <arm>
+   --llm-context-budget <N|off>` with the first turn, then each later turn into the same session. The arms are
+   `none`, `stale` and `stale_forget` (`stale,forget`). The tasks use two turns, because forget is offered at turn
+   ends. The driver answers questions as a parent agent would:
+   - the model's first question gets "use your judgement" (option 1 when it takes no text), and later ones are
+     dismissed;
+   - an approval is denied;
+   - the step-limit question gets Stop: there is no Continue, since the limit is part of the task.
+
+   A turn waits at most 45 minutes. Afterwards the session is stopped with `chi sessions stop`, then `pkill -f
+   <the run's state dir>`. Nothing is ever killed by a pid read from a file.
+3. **collect:** the numbers below, read before grading, and `diff.patch` (the work against the base commit).
+4. **grade (Grader):** the hidden specs are copied in as `<name>_p6hidden_spec.rb` and run in one `bundle exec rspec`
+   with the regression specs (the model's own copies), then removed. Pass means rspec exits 0 with at least one
+   example. The working tree is graded: nothing needs committing.
+
+The result goes to `ROOT/results/<run>.json`. A rerun skips runs that have a result, and starts over any run that
+has none.
+
+## Cost
+
+Each run's cost (OpenRouter's reported `cost`, summed over the turn records) goes to `ROOT/ledger.jsonl`. No run
+starts once the ledger reaches `--cap` (default $8). With `--jobs N` the runs in flight can pass the cap by what they
+spend. A payment error (chi send's `error_kind` `credits` or `credits_held`, or a 402 / over_budget in the detail)
+ends that run at once and writes `ROOT/STOP`, and no further run starts until someone removes it. The account's own
+key limit stays the hard stop.
+
+## What it scores
+
+Per run (`Collector`), from the session file, `analytics.json` and the repo:
+
+- **success:** the grade, plus a manual 0/1/2 in `ROOT/grades.yml` (`T1-none-s1: {grade: 2, note: …}`);
+- **steps, tool calls, edits, commits:** `ModelNotesReport::SessionReader`;
+- **reads, re-reads, re-reads after a stub** (by kind): `LLMContextBench::Replay#read_counts`. A re-read reads a
+  path the session read before. It counts as after a stub when an earlier read of that path had an applied stub
+  whose cause came before it: a forget's cause is its `forget_outputs` call, a stale stub's the read that superseded
+  it;
+- **stale stubs, forget calls, forgotten ids and their tokens:** `Replay#stubs` (chars/4);
+- **tokens:** prompt tokens sent (summed over requests), cached, re-prefilled and completion tokens, and the cost,
+  from the turn records;
+- **peak context:** the largest prompt of any turn (`prompt_tokens_max` on the turn record);
+- **scope:** distinct files read, files read and files changed outside the fix's set, and diff lines;
+- **wall time.**
+
+`report` gives each task × arm its pass count, manual grades, step-limit stops, and every metric's median with its
+min–max spread. It also gives the gate: `stale_forget` against `none`. Per task, a metric is better when
+`stale_forget`'s median is below `none`'s whole spread, worse when above it, and the same otherwise. The gate passes
+when, on both re-reads and scope (files read + files changed outside), the better tasks outnumber the worse, and
+`stale_forget` passed at least as many runs as `none`.
+
+## Limits
+
+- Three samples a cell is little. Read nothing into a difference inside one arm's spread.
+- Tokens from `Replay` are chars/4, and those from the turn records are the server's.
+- A Splash host may not report cached tokens or cost (they read 0).
+- The fix's spec file is copied in whole, so its old examples run twice: once hidden and once as the model left
+  them.

data/docs/sessions.md

@@ -65,7 +65,7 @@ chi sessions clean --dry-run --days 7            # test sessions older than 7 da
 **Ordering:**
 
 - `Session.list` / `SessionManager.list_sessions` / `GET /api/sessions?sort=&order=&limit=&offset=` default to `updated_at desc` (newest activity first). Also supports `created_at`, `asc`. `X-Total-Count` header when paginated.
-- Web UI (`chi web`): the page's scope is in its URL. Started in a git repo, `chi web` opens `/?dir=<that folder>`: that project's sessions, and new chats start in that folder; the header chip says `<project> · all`, and `all` opens the same place without `?dir` (every session; a new chat there starts in the server's own folder, shown on the start page, and cards name their folder; `← <project>` goes back to the project view it came from, or to the server's own project). One server serves every project: a second `chi web` (from another repo) finds it through `GET /api/info` and prints (with `--open`, opens) its page for its own folder instead of starting another. The 3 latest sessions sit above the chat (`hide ▴` puts them away behind a `▾ N sessions` pill, remembered; in a window under 900 px wide, where the strip scrolls sideways, `▴ hide` sits in the top bar where the pill comes back; a window under 700 px tall hides them by itself, so a question or approval card in the stage keeps room, and the pill shows them until the window is tall again). A parent and its delegates are one card there: its `▸ 2 delegates · 1 live · 1 waiting` chip (the waiting part in the attention colour, the card's border too) opens their rows in a popover under it (a row per delegate at any depth, indented; a click opens that one, Esc or a click outside closes it, and the strip's order holds while it is open). A fork is a card of its own, and so is a delegate whose parent isn't listed (archived, another project), with its `↳ <parent>` chip; the pill counts cards, and every live or waiting session. "All sessions" (or `/`) opens every session at `#/sessions`, with a search over preview, id and status (Esc or Back returns). There a parent's card holds its delegates the same way, the chip opening their rows inside the card (each with an archive button on hover), open by itself while one of them waits on you; the count says `14 (+7 delegates)`, a search that matches a delegate shows its parent's card with the list open and the matching rows marked, and select mode picks cards (archiving a parent takes its delegates). The open session is in the URL (`#/s/<id>`), so a reload or a copied link opens it again; the chi logo top left goes back to the empty start for a new chat. The message box grows with its text; drag its top edge to keep it taller (double-click resets). The info bar copies `chi --attach <id>` for a terminal. A session whose prompt carried model notes has a `notes: deepseek` chip there (the names without `model_notes_`; the tooltip lists each with its scope and size; `session.prompt_notes` in `GET /api/sessions/:id`, the live worker's, else the session file's; see [Memory](memory.md#model-notes)). Its `llm ctx` chip names the LLM context strategy the next turn runs under (`llm ctx stale,forget · session`, in the accent colour when the session set its own; the tooltip gives each value's source), and its popover sets the session's own strategy, apply rule and budget, or follows the model again, by running `/llm-context` in the worker (the reply shows as a command bubble); `GET /api/sessions/:id`'s `session.llm_context` carries the values (the live worker's, else resolved from the session file), and a `command_ran` that changed them carries the new ones. It shows the context used (`ctx 42%`) and the last generation's decode speed (`87 tok/s`, `~64 tok/s` when estimated; see `/stats` in [cli.md](cli.md#session-commands)); hovering `ctx` there or on a session card lists the session's tokens in (summed over every request, with the cached share), out (with reasoning) and the cost when the provider reports one, for this session only, and the memory indexes its prompt holds (`memory index: ~3.4k tokens in this session's prompt (system 2.0k, project 1.4k)`; see [Memory](memory.md#the-indexs-size)). The start page's model picker (bottom left of the composer, the chosen name `▾`) chooses the model a new chat starts on; it opens a search list over the conversation (↓ or a click; downward when the start page leaves no room above): an empty search shows the last 5 picks (Recent) and then each host's model ids A–Z under the host, the default host first; typed words must each match the host or the id (a substring, else for 3+ characters the letters in order, so `deepseek4.1 fla` finds `openrouter · deepseek/deepseek-v4.1-flash`), ⏎ picks, Esc/Tab close, a pick puts the focus in the message box: `GET /api/models` lists the hosts' models as chi spells them (`{default, models: [{name, host, id, sampling?, llm_context?}], warning?}`; `sampling` is the model's configured request parameters as `/model` words them, the row's tooltip in the list; bare for the default host, `host:model` for the others, from the same cached lists as `/models`, a bounded wait, a host that is down noted in `warning`), and `POST /api/sessions` takes `model` (blank means the default). Beside it, an `llm ctx` chip shows the LLM context the picked model starts under (each `GET /api/models` row's `llm_context`, as the info bar's); its form sets one for the new chat only, sent as `POST /api/sessions`'s `llm_context` and never remembered (see [configuration.md](configuration.md#llm-context-a-sessions-own-strategy)). The start page's first message goes as later ones do: `POST /api/sessions` with `idle: true` and `preview` (the message, which names the session until its turn is saved), then `POST /api/sessions/:id/turn`, so a failed first turn puts its prompt back in the composer too; a first line that is one of the new session's commands (`/model …`) goes to `POST /api/sessions/:id/command` instead, as later ones do. The browser remembers the last model picked; a running session's model is in the info bar and changes only with `/model`. In the composer a line is a command when it is `!…` or starts with one of the session's command names (its `commands` list; `/stats`, `/exit` and the other terminal words get the page's own reply); an unknown `/word` (`/usr/bin/env is missing`) goes to the model as a prompt, as in a terminal; a one-word `/word` no command answers (`/modle`) is not sent: the page shows `Unknown command /modle. Did you mean /model? /help lists the commands.` (the "Did you mean" part only when a name is close). A `POST /turn` (or a session's first `prompt`) that is one of the worker's commands runs as that command too (`202 {status, command_id, session_id}`), so `chi send`, `chi -p` and a page whose command list lags all get the command. ↑/↓ in the composer walk the prompt history the TUI's ↑ walks ([Persistent Prompt History](cli.md#persistent-prompt-history)): ↑ with the caret on the first line, ↓ from the last line while browsing, ↓ past the newest brings the draft back; `GET /api/history` returns `{entries: [...]}`, oldest first (the page fetches it on focus and after each send). The server records a sent line in the routes once the worker took it (`POST /turn` accepted, a `!command` through `POST /command` or as a session's first line); `"history": false` in the body keeps it out (an image-only send).
+- Web UI (`chi web`): the page's scope is in its URL. Started in a git repo, `chi web` opens `/?dir=<that folder>`: that project's sessions, and new chats start in that folder; the header chip says `<project> · all`, and `all` opens the same place without `?dir` (every session; a new chat there starts in the server's own folder, shown on the start page, and cards name their folder; `← <project>` goes back to the project view it came from, or to the server's own project). One server serves every project: a second `chi web` (from another repo) finds it through `GET /api/info` and prints (with `--open`, opens) its page for its own folder instead of starting another. The 3 latest sessions sit above the chat (`hide ▴` puts them away behind a `▾ N sessions` pill, remembered; in a window under 900 px wide, where the strip scrolls sideways, `▴ hide` sits in the top bar where the pill comes back; a window under 700 px tall hides them by itself, so a question or approval card in the stage keeps room, and the pill shows them until the window is tall again). A parent and its delegates are one card there: its `▸ 2 delegates · 1 live · 1 waiting` chip (the waiting part in the attention colour, the card's border too) opens their rows in a popover under it (a row per delegate at any depth, indented; a click opens that one, Esc or a click outside closes it, and the strip's order holds while it is open). A fork is a card of its own, and so is a delegate whose parent isn't listed (archived, another project), with its `↳ <parent>` chip; the pill counts cards, and every live or waiting session. "All sessions" (or `/`) opens every session at `#/sessions`, with a search over preview, id and status (Esc or Back returns). There a parent's card holds its delegates the same way, the chip opening their rows inside the card (each with an archive button on hover), open by itself while one of them waits on you; the count says `14 (+7 delegates)`, a search that matches a delegate shows its parent's card with the list open and the matching rows marked, and select mode picks cards (archiving a parent takes its delegates). The open session is in the URL (`#/s/<id>`), so a reload or a copied link opens it again; the chi logo top left goes back to the empty start for a new chat. The message box grows with its text; drag its top edge to keep it taller (double-click resets). The info bar copies `chi --attach <id>` for a terminal. A session whose prompt carried model notes has a `notes: deepseek` chip there (the names without `model_notes_`; the tooltip lists each with its scope and size; `session.prompt_notes` in `GET /api/sessions/:id`, the live worker's, else the session file's; see [Memory](memory.md#model-notes)). Its `llm ctx` chip names the LLM context strategy the next turn runs under (`llm ctx stale,forget · session`, in the accent colour when the session set its own; the tooltip gives each value's source), and its popover sets the session's own strategy, apply rule and budget, or follows the model again, by running `/llm-context` in the worker (the reply shows as a command bubble); `GET /api/sessions/:id`'s `session.llm_context` carries the values (the live worker's, else resolved from the session file), and a `command_ran` that changed them carries the new ones. It shows the context used (`ctx 42%`) and the last generation's decode speed (`87 tok/s`, `~64 tok/s` when estimated; see `/stats` in [cli.md](cli.md#session-commands)); hovering `ctx` there or on a session card lists the session's tokens in (summed over every request, with the cached share), out (with reasoning) and the cost when the provider reports one, for this session only (one estimated from a `hosts.<name>.models` price shows with `~`: `cost: ~$0.54 ($0.42 reported, ~$0.12 estimated)`), and the memory indexes its prompt holds (`memory index: ~3.4k tokens in this session's prompt (system 2.0k, project 1.4k)`; see [Memory](memory.md#the-indexs-size)). The start page's model picker (bottom left of the composer, the chosen name `▾`) chooses the model a new chat starts on; it opens a search list over the conversation (↓ or a click; downward when the start page leaves no room above): an empty search shows the last 5 picks (Recent) and then each host's model ids A–Z under the host, the default host first (an id the host declares under `hosts.<name>.models` first, noted `config`, its tooltip `served by config (hosts.<name>.models)`; a host that failed to list its models keeps those ids, greyed and noted `host down`, still pickable; a remembered or default model stays chosen even then, greyed on the button); typed words must each match the host or the id (a substring, else for 3+ characters the letters in order, so `deepseek4.1 fla` finds `openrouter · deepseek/deepseek-v4.1-flash`), ⏎ picks, Esc/Tab close, a pick puts the focus in the message box: `GET /api/models` lists the hosts' models as chi spells them (`{default, models: [{name, host, id, configured?, unavailable?, sampling?, llm_context?}], warning?}`; `configured: true` marks an id declared under `hosts.<name>.models`, listed first under its host, `unavailable: true` one whose host failed to list its models; `sampling` is the model's configured request parameters as `/model` words them, the row's tooltip in the list; bare for the default host, `host:model` for the others, from the same cached lists as `/models`, a bounded wait, a host that is down noted in `warning`), and `POST /api/sessions` takes `model` (blank means the default). Beside it, an `llm ctx` chip shows the LLM context the picked model starts under (each `GET /api/models` row's `llm_context`, as the info bar's); its form sets one for the new chat only, sent as `POST /api/sessions`'s `llm_context` and never remembered (see [configuration.md](configuration.md#llm-context-a-sessions-own-strategy)). The start page's first message goes as later ones do: `POST /api/sessions` with `idle: true` and `preview` (the message, which names the session until its turn is saved), then `POST /api/sessions/:id/turn`, so a failed first turn puts its prompt back in the composer too; a first line that is one of the new session's commands (`/model …`) goes to `POST /api/sessions/:id/command` instead, as later ones do. The browser remembers the last model picked; a running session's model is in the info bar and changes only with `/model`. In the composer a line is a command when it is `!…` or starts with one of the session's command names (its `commands` list; `/stats`, `/exit` and the other terminal words get the page's own reply); an unknown `/word` (`/usr/bin/env is missing`) goes to the model as a prompt, as in a terminal; a one-word `/word` no command answers (`/modle`) is not sent: the page shows `Unknown command /modle. Did you mean /model? /help lists the commands.` (the "Did you mean" part only when a name is close). A `POST /turn` (or a session's first `prompt`) that is one of the worker's commands runs as that command too (`202 {status, command_id, session_id}`), so `chi send`, `chi -p` and a page whose command list lags all get the command. ↑/↓ in the composer walk the prompt history the TUI's ↑ walks ([Persistent Prompt History](cli.md#persistent-prompt-history)): ↑ with the caret on the first line, ↓ from the last line while browsing, ↓ past the newest brings the draft back; `GET /api/history` returns `{entries: [...]}`, oldest first (the page fetches it on focus and after each send). The server records a sent line in the routes once the worker took it (`POST /turn` accepted, a `!command` through `POST /command` or as a session's first line); `"history": false` in the body keeps it out (an image-only send).
 - Web notifications: when a session needs you while the tab is hidden or behind another window (a question or a guardrail approval, a plugin card with buttons during a turn such as check-in's, a failed turn, a turn done after 10 s or more; a delegated session only for its questions, a canceled turn never), the page title counts it, `(N) Chi`, until you come back to the tab. The bell at the right of the top bar also turns on OS notifications ("needs an answer", "needs approval", "needs you", "turn failed", "done in 42 s", under the session's first message; a click opens the session): its first click asks the browser for the permission, and the choice is kept per browser. Any session of the page's scope counts, not only the open one. What was already so when the page loaded never counts, and several chi tabs show one notification per event. A chi tab in front tells the others (a `BroadcastChannel`), so while you look at one, the ones behind neither notify nor count what it shows; coming back to a tab clears those events in the other tabs' titles too. The hub's `session` frames carry what this needs: `pending_question` (`{id, kind}`, kind `question` or `approval`), `pending_card` (`{id, bundle}`: the running turn's card with actions, from `pending_card.json` that the worker keeps in the session's folder while one is open; a card without actions, such as loop-guard's, never counts) and `last_turn` (`{outcome, ended_at, seconds, origin}`, saved in the session's JSON as the engine ends each turn).
 - The web frontend is a zero-build ES-module stack in `lib/samagotchi/web/public/`: `data.js` (retrieval, typed SSE `openStream` for a session and `openEvents` for the session list), `sessions_list.js` (the list as a pure reducer over `GET /api/events`: a snapshot replaces it, an upsert keeps a known card in place, a removal drops it; `families()` groups delegates under their parent), `families_view.js` (a parent's family chip, its rows and the strip's popover), `notify.js` (which of those events needs the user, for the notifications), `app.js` (presentation/state; a session with no live stream gets one when its `session` event says `bridge_up`, after one re-read: `event_seq` starts over in each worker, so a dropped stream is never resumed with its old cursor), `format.js` (pure formatters such as `previewOf`), `prompt_history.js` (the composer's ↑/↓ over the shared prompt history). Unit-tested via `npm test` (`node --test spec/web/public/*.test.js`).
 - Selecting a session in the web UI is read-only: `GET /api/sessions/:id` never spawns a worker (it reads a live worker's snapshot when one runs, else the session file). A prompt (`POST /turn`) or a command (`POST /command`) wakes the worker, and `/stream` briefly waits for a freshly-spawned bridge before answering. A caught-up SSE reconnect holds the stream open; `reset` markers are only sent for reconnects behind the ring window, or with a cursor from another worker (event ids are `<event_seq>-<epoch>`, one epoch per worker).
@@ -175,7 +175,7 @@ chi send --wait -m "and the tests?" 3fa2               # a follow-up in the same
 chi send --wait 3fa2                                   # sends nothing: waits for its next reply
 ```
 
-- `--new` takes no ids (one new session per call). `--dir DIR` is its folder, and so its project (default the current one); `--model M` its model (default the configured one). A host config.yml doesn't have is refused before anything is spawned (exit 1). A `host:id` whose id that host's last saved list doesn't have (`~/.local/state/samagotchi/model_lists.json`, what `chi models` / `/models` / the web last listed for that host, at most a week old) gets one warning line on stderr, with up to three close ids as a hint (`did you mean: gemma-small?`), and the session starts anyway: some hosts serve ids they don't list (a one-model llama.cpp server takes any name). A saved list older than 10 minutes that misses the id is re-listed once (that one host, capped at 5 s) before the warning: the list can be stale by content, e.g. a one-model server reloaded with another model; a list re-listed that way names the typed id, nothing is said. A list younger than 10 minutes is taken at its word (a host that serves ids it never lists would otherwise pay the re-list on every launch). A re-list that fails, times out or lists nothing falls back to the saved list. A bare id (no `host:`) isn't checked that way — routing sends it to whichever host lists it — and with no saved list for the host nothing is said; a wrong id then fails the worker's first turn.
+- `--new` takes no ids (one new session per call). `--dir DIR` is its folder, and so its project (default the current one); `--model M` its model (default the configured one). A host config.yml doesn't have is refused before anything is spawned (exit 1). A `host:id` whose id that host's last saved list doesn't have (`~/.local/state/samagotchi/model_lists.json`, what `chi models` / `/models` / the web last listed for that host, at most a week old) gets one warning line on stderr, with up to three close ids as a hint (`did you mean: gemma-small?`), and the session starts anyway: some hosts serve ids they don't list (a one-model llama.cpp server takes any name). A saved list older than 10 minutes that misses the id is re-listed once (that one host, capped at 5 s) before the warning: the list can be stale by content, e.g. a one-model server reloaded with another model; a list re-listed that way names the typed id, nothing is said. A list younger than 10 minutes is taken at its word (a host that serves ids it never lists would otherwise pay the re-list on every launch). A re-list that fails, times out or lists nothing falls back to the saved list. An id its host declares under `hosts.<name>.models` (see [configuration](configuration.md#models-a-host-serves-but-doesnt-list)) is never warned about or re-listed. A bare id (no `host:`) isn't checked that way — routing sends it to whichever host lists or declares it — and with no saved list for the host nothing is said; a wrong id then fails the worker's first turn.
 - `--new` prints `<full id>  started` on stdout. With `--wait` that line (and the `sent` line for an existing session) goes to stderr, so stdout is exactly the answer: the reply of the turn the message started, in full. It is the worker's `output/` file, the same one `delegate` reads; a turn that ends with only tool calls and no text has none.
 - `--wait` takes one session: `--new` or one id. A session with a running turn is refused (`busy: a turn is running; wait or attach`, exit 1): the message would run after it, and its reply would come back as the answer.
 - Exit codes with `--wait`: 0 answered; 3 the turn waits for an answer from you (a question, a hook's question, a guardrail approval, or the step-limit question: see [chi as a sub-agent](sub-agent.md#the-step-limit)), and the session keeps waiting: stderr gets the whole question (`waiting for an answer (approval): …`, its text, the numbered options, whether free text is allowed) and how to answer it (`chi answer ID --question QID --option N`, or `chi --attach ID`, the web); 4 `--timeout S` passed with the turn still running (it goes on; wait again); 1 the turn ended without a reply (canceled, failed or empty), the worker failed or vanished, or the session was stopped; 130 on Ctrl-C, which leaves the turn running (`still running: chi --attach ID`). There is no default timeout.

data/lib/samagotchi/bridge/turn_accumulator.rb

@@ -264,6 +264,11 @@ module Samagotchi
           else
             append_text(event[:iteration], "text", event[:content])
           end
+        when :generation_retrying
+          # A dropped stream's step asked again: what it streamed is void.
+          if event[:restarted]
+            parts.reject! { |part| %w[thinking text].include?(part[:kind]) && part[:iteration] == event[:iteration] }
+          end
         when :tool_call_started
           part = { kind: "tool", iteration: event[:iteration], call_index: event[:call_index],
                    tool: event[:tool], params: event[:params], status: "running" }

data/lib/samagotchi/bundles/github-pr/manifest.yml

@@ -1,6 +1,6 @@
 ---
 name: github-pr
-version: 0.3.1
+version: 0.3.3
 scope: system
 description: Attaches the branch's open GitHub pull request to a session as context (and any PR URL with chi context add or the web's "+ URL"); the agent gets a note when reviews, comments, checks or its state change; in the web, a path:line in an answer links to that line of the PR; the auto_attach setting can offer the PR with a card first, or attach nothing
 trust_level: reviewed
@@ -11,7 +11,7 @@ needs:
   hint: brew install gh, then gh auth login
 plugin:
   file: plugin.rb
-  sha256: sha256:eb6207a0aec4267eb15d28e4db2edb10d458c3ff574c2be56f225b24b7afb733
+  sha256: sha256:f68b53bfb552e35c9b151ee42cc10c07923481fc3d5496f023422e388df6719a
 scripts:
   pr_context.rb: sha256:a883d2780e89c68c0d7b6d5e0fcb22c273f17bb167e79064e0e99db6bd2ee6f0
 context_providers: