Prepare Imp 0.16.0 release

CHANGELOG.md

@@ -4,6 +4,8 @@ User-visible changes to Imp are recorded here.
 
 ## Unreleased
 
+## 0.16.0 — 2026-10-17
+
 ### Added
 
 - `Imp.Run.start/3` `request_retry: [waits: [...], reserve: ms]`: a model

README.md

@@ -145,7 +145,7 @@ text or JSON you can score, such as an agent's tool descriptions.
 ## Install
 
 ```elixir
-{:imp, "~> 0.15.0"}
+{:imp, "~> 0.16.0"}
 ```
 
 Imp needs Elixir 1.19 or later and a C and C++ compiler, for the native code
@@ -162,7 +162,7 @@ large-scale benchmarking. Bug reports and pull requests are welcome.
 - [Getting started](docs/getting-started/index.md) builds one program step by
   step, from the first call to a supervised server, with real scores.
 - [Coming from DSPy](docs/coming-from-dspy.md) maps DSPy's names to Imp's.
-- [Tutorials](https://github.com/deepfates/imp/tree/v0.15.0/livebooks) are Livebook notebooks
+- [Tutorials](https://github.com/deepfates/imp/tree/v0.16.0/livebooks) are Livebook notebooks
   you can run offline or with a key.
 - The [cheatsheet](docs/cheatsheet.cheatmd) has the common calls on one page.
 

RELEASE_NOTES.md

@@ -1,21 +1,22 @@
-# Imp v0.15.0
+# Imp v0.16.0
 
 Imp is a framework for typed, optimizable language-model programs on the BEAM.
-This release adds two ReActV2 options a caller opts into: `finish: :tools`,
-which ends a turn only through a `finish_on` tool, for a program that acts
-only through its tools, and `history_replay: :actions`, which shows earlier
-turns without the text and reasoning written beside their calls. Programs that
-use neither send byte-for-byte the requests 0.14.1 sent and save as before.
-New options make this a minor release under Imp's versioning rule.
+This release adds `request_retry:` to `Imp.Run.start/3`, which sends a model
+request the provider failed in a way that may pass again in the same run, after
+a wait. It also changes two things a caller may rely on: an LM client other
+than ReqLLM reports its charge as metadata `:cost`, because `Imp.Core` no longer
+reads it from the usage map; and a ReActV2 forced `submit` with invalid
+arguments goes to the extractor. A new option and changed behaviour make this
+a minor release under Imp's versioning rule.
 
 ## Install
 
 ```elixir
-{:imp, "~> 0.15.0"}
+{:imp, "~> 0.16.0"}
 ```
 
-`~> 0.15.0` takes later 0.15 patch releases and nothing newer. The two-part
-form, `~> 0.15`, means `>= 0.15.0 and < 1.0.0` in Mix, so `mix deps.update
+`~> 0.16.0` takes later 0.16 patch releases and nothing newer. The two-part
+form, `~> 0.16`, means `>= 0.16.0 and < 1.0.0` in Mix, so `mix deps.update
 imp` under it takes every later 0.x release, including minor releases that
 change what callers receive.
 
@@ -28,38 +29,43 @@ in its release definition; see [releases that use MCP or
 ACP](docs/production.md#releases-that-use-mcp-or-acp).
 Ordinary Imp startup starts no protocol endpoint.
 
-## Changes and upgrading from 0.14
+## Changes and upgrading from 0.15
 
-Change the Imp dependency to `{:imp, "~> 0.15.0"}`, run `mix deps.update imp`,
-and commit `mix.lock`. No code or data migration is needed: saved programs
-without the new options load with their defaults.
+Change the Imp dependency to `{:imp, "~> 0.16.0"}`, run `mix deps.update imp`,
+and commit `mix.lock`. No data migration is needed. Check the second item if
+you use an LM client of your own, or build response envelopes by hand.
 
-- **Added: `finish: :tools`.** Only a `finish_on` tool ends a ReActV2 turn.
-  There is no `submit`; the outputs come from the `finish_on` functions. A
-  step that writes text and calls no tool is a thought, followed by one
-  ordinary step and a line naming the ending tools (`unsent_note:` replaces
-  it). Nothing is forced and no last request is made: a failed request gets
-  one more ordinary step, once per turn and not on the last allowed step; a
-  second thought in a row, a step that says nothing, the step limit or a
-  second failure ends the turn `:incomplete`, with the request's error in
-  `termination_error`, or `:deadline_exceeded` when the deadline has passed.
-  A program with `finish: :tools` needs a `finish_on` tool and refuses
-  `last_request_note` and `last_request_tools`. A call may give its own
-  `finish:` (when the task has no input of that name), so a `:tools` program
-  can ask for one text answer, such as a summary, with `finish: :auto`.
-- **Added: `history_replay: :actions`.** Earlier turns are shown as their
-  inputs, the calls with their results, and their outputs; the text and
-  reasoning written beside the calls, and steps that only wrote text, are left
-  out. The current turn is shown whole: it starts with the call's new inputs
-  or its own `last_request_note`, or, on a resume with neither, at the last
-  step that carries inputs. The returned history keeps every step. This
-  diverges from DSPy's ReActV2, which replays every step whole; the default,
-  `:trajectory`, still does. Some thinking APIs reject an earlier tool-call
-  message without its reasoning content; check your provider.
-- **Added: `unsent_note:`.** The line shown after each thought-only step, in
-  place of Imp's. A blank line is refused.
+- **Added: `request_retry:` on `Imp.Run.start/3`.** `request_retry: [waits:
+  [ms, ...], reserve: ms]` sends a model request that failed with an error
+  `Imp.Errors.retryable?/1` accepts (408, 425, 429, 5xx, a failed connection)
+  again inside `Imp.LM.request/2`, after each wait in turn. Under a deadline
+  the last wait repeats while it leaves `reserve` (60 s by default) of the
+  deadline; without one, the list is the bound. A provider's `retry-after`
+  longer than the wait is waited instead. Each attempt is its own
+  `:model_request` and `:model_response`, and a failed response followed by
+  another attempt carries `retry_in_ms`. Only the outermost request in a
+  process retries, so an LM that wraps an LM does not multiply attempts.
+  Streamed requests are not sent again. `waits` must not be empty. Off unless
+  given. A timed-out attempt may have been finished and billed by the
+  provider without a response to record, so a retry can be billed twice;
+  under a deadline each attempt is capped to the time left.
+- **Changed: where a call's charge is read.** OpenRouter bring-your-own-key
+  billing moved into `Imp.Clients.ReqLLM`, which records the charge it
+  resolves as `:charge` in its `req_llm` response metadata. `Imp.Core` reads
+  `LMResponse.cost` from that `:charge` (final when present, `nil` included),
+  and otherwise from metadata `:cost`; it no longer reads usage `"cost"` or
+  `"is_byok"`. An LM client other than ReqLLM, or a hand-built response
+  envelope, must report its charge as `:cost` in its metadata (or
+  `req_llm.charge`), or its cost is `nil`.
+- **Fixed: a forced `submit` with invalid arguments is extracted.** A ReActV2
+  forced `submit` whose arguments fail validation now goes to the typed
+  extractor and ends `:extracted`, where it ended `:incomplete` with no
+  outputs. If that extraction request fails with an LM error, the call
+  returns `{:error, %Imp.Predict.ReActV2.StepError{}}`, where it returned
+  `{:ok, prediction}` ending `:incomplete`. A forced `submit` the tool policy
+  refuses still ends `:incomplete`.
 
-Rollback means restoring `0.14.1` in the lock and removing the new options.
+Rollback means restoring `0.15.0` in the lock and removing `request_retry:`.
 See the [changelog](CHANGELOG.md) for every change.
 
 ## Known limits

docs/coming-from-dspy.md

@@ -12,7 +12,7 @@ brought in.
 ## The five-minute version
 
 ```elixir
-# pip install dspy             ->  {:imp, "~> 0.15.0"}
+# pip install dspy             ->  {:imp, "~> 0.16.0"}
 # lm = dspy.LM("openai/...")    ->  lm = Imp.req_llm("openai:gpt-5.4-mini", api_key: ...)
 # dspy.Predict("q -> a")        ->  program = Imp.predict("q -> a", lm: lm)
 # program(q="...")              ->  {:ok, pred} = Imp.call(program, %{q: "..."})
@@ -87,7 +87,7 @@ error row too. Each model request has a receive timeout, and
 has no time limit of its own (an MCP tool call does, 30 seconds by default),
 so to bound an agent, start it with `Imp.start_run/3` and cancel it when you
 choose. The
-[deployment example](https://github.com/deepfates/imp/blob/v0.15.0/examples/deployment/README.md)
+[deployment example](https://github.com/deepfates/imp/blob/v0.16.0/examples/deployment/README.md)
 is a complete OTP application.
 
 **Optimizers see what you name.** DSPy finds predictors by walking a module's

docs/diving-deeper/modules-and-composition.md

@@ -149,7 +149,7 @@ A custom module is your code, so it is not saved as a whole. What an optimizer
 chose for it is data: `Imp.ProgramParameters.values/1` reads it,
 `Imp.ProgramParameters.apply_values/2` puts it on a freshly built program, and
 `Imp.Optimizer.Artifact` writes it to a checksummed file. The
-[deployment example](https://github.com/deepfates/imp/blob/v0.15.0/examples/deployment/README.md)
+[deployment example](https://github.com/deepfates/imp/blob/v0.16.0/examples/deployment/README.md)
 does this in a supervised application.
 
 ### Built-in variants

docs/diving-deeper/saving-and-artifacts.md

@@ -21,7 +21,7 @@ Save the whole program when it is made of Imp's modules: `Imp.predict/2`,
 when the program is your own struct implementing `Imp.Module`, or when you
 want the program's code to live in your release and only its tuned text to
 cross the persistence boundary. The
-[deployment example](https://github.com/deepfates/imp/tree/v0.15.0/examples/deployment)
+[deployment example](https://github.com/deepfates/imp/tree/v0.16.0/examples/deployment)
 does the second.
 
 ### 2. JSON with a checksum

docs/getting-started/running-in-your-application.md

@@ -121,7 +121,7 @@ Changing models is then a configuration change, and rotating a key is a
 restart.
 
 The
-[deployment example](https://github.com/deepfates/imp/blob/v0.15.0/examples/deployment/README.md)
+[deployment example](https://github.com/deepfates/imp/blob/v0.16.0/examples/deployment/README.md)
 is the complete version of this page: a two-stage program like `TicketTriage`,
 learned parameters loaded and reloaded as an `Imp.Optimizer.Artifact`, crashed
 and timed-out calls contained, and the whole thing restarted in a fresh OS

docs/getting-started/setting-up.md

@@ -5,15 +5,15 @@ Add Imp to a Mix project:
 ~~~elixir
 def deps do
   [
-    {:imp, "~> 0.15.0"}
+    {:imp, "~> 0.16.0"}
   ]
 end
 ~~~
 
 or, for a script or a Livebook notebook:
 
 ~~~elixir
-Mix.install([{:imp, "~> 0.15.0"}])
+Mix.install([{:imp, "~> 0.16.0"}])
 ~~~
 
 Imp needs Elixir 1.19 and a C and C++ compiler, for the native code in two

docs/getting-started/where-to-go-next.md

@@ -51,7 +51,7 @@ The module documentation is the reference for every function.
 [Running Imp in production](../production.md) covers what the last page began:
 supervision, provider failures, runs you can observe and cancel, and
 telemetry. The
-[deployment example](https://github.com/deepfates/imp/blob/v0.15.0/examples/deployment/README.md)
+[deployment example](https://github.com/deepfates/imp/blob/v0.16.0/examples/deployment/README.md)
 is a complete application to copy from.
 
 ## Try it in a notebook

docs/production.md

@@ -5,16 +5,16 @@ where its credentials come from, how long a call may take and what it may
 cost. This page covers those decisions in the order you meet them: starting
 Imp, credentials, concurrency, timeouts, cost and caching, persistence and
 telemetry. The
-[deployment example](https://github.com/deepfates/imp/tree/v0.15.0/examples/deployment)
+[deployment example](https://github.com/deepfates/imp/tree/v0.16.0/examples/deployment)
 is a complete OTP application that puts them together.
 
 ## Imp in your supervision tree
 
-Imp is an OTP application, and adding `{:imp, "~> 0.15.0"}` to your
+Imp is an OTP application, and adding `{:imp, "~> 0.16.0"}` to your
 dependencies starts it with yours. It supervises its settings, its response
 cache and the task pools that bound its work. It opens no listener and
 starts no subprocess, and the MCP and ACP runtimes start only when you use
-them. In a script, `Mix.install([{:imp, "~> 0.15.0"}])` starts it too.
+them. In a script, `Mix.install([{:imp, "~> 0.16.0"}])` starts it too.
 
 ## Credentials at runtime
 
@@ -263,7 +263,7 @@ standard error.
 
 ## The reference application
 
-[`examples/deployment`](https://github.com/deepfates/imp/tree/v0.15.0/examples/deployment)
+[`examples/deployment`](https://github.com/deepfates/imp/tree/v0.16.0/examples/deployment)
 is a small OTP application that loads a checksummed artifact at startup, reads
 its key from the environment, serves calls from bounded supervised tasks,
 answers overload and timeouts with errors instead of blocking, and reloads

examples/deployment/README.md

@@ -150,4 +150,4 @@ Use a whole-program artifact for a supported portable Imp shape. Use
 its selected predictor parameters should cross the persistence boundary.
 
 During source development set `IMP_PATH` to the Imp checkout. Other
-applications use the Hex dependency in `mix.exs`, `{:imp, "~> 0.15.0"}`.
+applications use the Hex dependency in `mix.exs`, `{:imp, "~> 0.16.0"}`.

examples/deployment/mix.exs

@@ -11,7 +11,7 @@ defmodule ImpDeployment.MixProject do
 
   defp deps do
     case System.get_env("IMP_PATH") do
-      nil -> [{:imp, "~> 0.15.0"}]
+      nil -> [{:imp, "~> 0.16.0"}]
       path -> [{:imp, path: path}]
     end
   end

livebooks/01_real_lm_front_door.livemd

@@ -7,7 +7,7 @@ imp_path = System.get_env("IMP_PATH")
 lockfile = imp_path && Path.join(imp_path, "mix.lock")
 
 cond do
-  is_nil(imp_path) -> Mix.install([{:imp, "~> 0.15.0"}])
+  is_nil(imp_path) -> Mix.install([{:imp, "~> 0.16.0"}])
   File.regular?(lockfile) -> Mix.install([{:imp, path: imp_path}], lockfile: lockfile)
   true -> Mix.install([{:imp, path: imp_path}])
 end

livebooks/02_without_a_provider.livemd

@@ -7,7 +7,7 @@ imp_path = System.get_env("IMP_PATH")
 lockfile = imp_path && Path.join(imp_path, "mix.lock")
 
 cond do
-  is_nil(imp_path) -> Mix.install([{:imp, "~> 0.15.0"}])
+  is_nil(imp_path) -> Mix.install([{:imp, "~> 0.16.0"}])
   File.regular?(lockfile) -> Mix.install([{:imp, path: imp_path}], lockfile: lockfile)
   true -> Mix.install([{:imp, path: imp_path}])
 end

livebooks/03_evaluate_and_optimize.livemd

@@ -7,7 +7,7 @@ imp_path = System.get_env("IMP_PATH")
 lockfile = imp_path && Path.join(imp_path, "mix.lock")
 
 cond do
-  is_nil(imp_path) -> Mix.install([{:imp, "~> 0.15.0"}])
+  is_nil(imp_path) -> Mix.install([{:imp, "~> 0.16.0"}])
   File.regular?(lockfile) -> Mix.install([{:imp, path: imp_path}], lockfile: lockfile)
   true -> Mix.install([{:imp, path: imp_path}])
 end

livebooks/04_tools_agents_mcp_rlm.livemd

@@ -7,7 +7,7 @@ imp_path = System.get_env("IMP_PATH")
 lockfile = imp_path && Path.join(imp_path, "mix.lock")
 
 cond do
-  is_nil(imp_path) -> Mix.install([{:imp, "~> 0.15.0"}])
+  is_nil(imp_path) -> Mix.install([{:imp, "~> 0.16.0"}])
   File.regular?(lockfile) -> Mix.install([{:imp, path: imp_path}], lockfile: lockfile)
   true -> Mix.install([{:imp, path: imp_path}])
 end

livebooks/05_operating_imp.livemd

@@ -7,7 +7,7 @@ imp_path = System.get_env("IMP_PATH")
 lockfile = imp_path && Path.join(imp_path, "mix.lock")
 
 cond do
-  is_nil(imp_path) -> Mix.install([{:imp, "~> 0.15.0"}])
+  is_nil(imp_path) -> Mix.install([{:imp, "~> 0.16.0"}])
   File.regular?(lockfile) -> Mix.install([{:imp, path: imp_path}], lockfile: lockfile)
   true -> Mix.install([{:imp, path: imp_path}])
 end
@@ -103,7 +103,7 @@ Enum.each(busy, &Task.await/1)
 refused
 ```
 
-The [deployment example](https://github.com/deepfates/imp/tree/v0.15.0/examples/deployment)
+The [deployment example](https://github.com/deepfates/imp/tree/v0.16.0/examples/deployment)
 wraps the same pattern in a `ProgramServer` that also reloads parameters while
 serving.
 

mix.exs

@@ -1,7 +1,7 @@
 defmodule Imp.MixProject do
   use Mix.Project
 
-  @version "0.15.0"
+  @version "0.16.0"
 
   def project do
     [

priv/public_api.json

@@ -10359,7 +10359,7 @@
       "types": []
     }
   ],
-  "package_version": "0.15.0",
+  "package_version": "0.16.0",
   "schema_version": 3,
   "scope": "Curated Imp API compiled from package-shipped sources. Exports come from non-hidden documentation entries; callbacks, types, and struct fields are category- and policy-gated."
 }

test/package_contract_test.exs

@@ -114,7 +114,7 @@ defmodule PackageContractTest do
     version = Mix.Project.config()[:version]
     dependency = hex_dependency(version)
 
-    assert version == "0.15.0"
+    assert version == "0.16.0"
     assert File.read!("RELEASE_NOTES.md") =~ "# Imp v#{version}"
     assert File.read!("CHANGELOG.md") =~ "## #{version}"
     assert File.read!("examples/deployment/mix.exs") =~ dependency