akm-cli 0.10.261012-beta → 0.10.261014-beta

package/docs/migration/release-notes/0.10.0.md

@@ -4,8 +4,9 @@
 0.10.26101001 through 0.10.26101202 and the monthly releases that follow
 (`0.10.YYMMNN`). It
 removes surface that nothing used, merges CLI spellings, sets the improve
-defaults from measurements, and adds OpenCode 2 support. It adds no `state.db`
-migration and keeps `index.db` at layout 26.
+defaults from measurements, replaces `engines` with `connections` and
+`harnesses`, and runs OpenCode 2 inside akm. It adds no `state.db` migration
+and keeps `index.db` at layout 26.
 
 To upgrade from 0.9.15 or later:
 
@@ -24,8 +25,7 @@ every replacement and the verification steps are in the
 ## Version floor
 
 0.10 reads what 0.9.15 and later wrote. It converts nothing older. A config in
-the old `stashDir` / `sources[]` / `installed[]` layout, or with an `extraParams`
-key that shadows a first-class engine field, fails to load and names
+the old `stashDir` / `sources[]` / `installed[]` layout fails to load and names
 `akm migrate apply` under akm 0.9.x. If you are on 0.9.14 or earlier, install
 0.9.31, run `akm migrate apply`, then upgrade.
 
@@ -66,6 +66,49 @@ Each of these is an unknown flag or command (exit 2), with no alias:
 
 Other breaking changes:
 
+- `engines` and `defaults` in `config.json` are replaced by `connections` (the
+  OpenAI-compatible endpoints akm sends model requests to) and `harnesses` (the
+  agent programs you already have). The entry named `default`, or the only one,
+  is the default, and `defaults.improveStrategy` is `improve.strategy`. A config
+  in the old form still loads, read as the new form in memory with one warning
+  that names `akm migrate apply`. `akm migrate apply` converts it under a
+  backup: the default engine is renamed `default`, keys (`apiKeyFile`, a literal
+  or `${secrets/...}` `apiKey`) move to `credentials.json`, `models.json` is
+  folded into the connections' `models` and moved to the config backups,
+  `engine:` in assets, workflows and task sources becomes `connection:` or
+  `harness:`, and an entry akm cannot use stays in the file with a note.
+  `provider`, `supportsJsonSchema`, `workflow.judgeEngine`, a strategy's
+  `engine`, `model`, `llm` and `timeoutMs`, and an `extraParams` key that shadows
+  a first-class setting are dropped with a note.
+- A key is an `apiKey: "$VAR"` reference or an entry in `credentials.json`.
+  `apiKeyFile`, `${secrets/...}` and the `AKM_ENGINE_<NAME>_API_KEY` and
+  `AKM_LLM_API_KEY` lookups are gone. Until `akm migrate apply` has filed it, a
+  key held in `apiKeyFile`, a literal or a `${secrets/...}` reference is not sent
+  (akm warns); `akm upgrade` runs `apply` for you.
+- `models.json` and `akm models list` and `copy-defaults` are gone. `akm models`
+  lists a connection's aliases, then the models its endpoint lists, and `akm
+  models set <alias> <model>` changes one.
+- `--connection`, `--harness` and `--model` replace `--engine`. `--engine` and
+  `--require-engines` (which now does nothing: `akm improve` stops at planning,
+  exit 78, when no process has a connection or harness to run on, and no longer
+  checks before the run that every enabled process has a usable target; run `akm
+  health` for that) still run, hidden from `--help`, with one warning each; [how an
+  old engine name resolves](../../reference/configuration.md#the-engines-form) is
+  in the configuration reference. `akm setup` takes one flag per question (`--endpoint`, `--api-key-env`, `--name`, `--harness`,
+  `--embedding`, ...); `--probe` and `--config` are gone.
+- `akm health` (the `connections-and-harnesses` check) and `akm info` (its
+  `connectionsAndHarnesses` field) print one table in place of the engine
+  checks (`default-engine`, `default-llm-engine`, `configured-engines`,
+  `active-improve-strategy`, `thinking-control`, `engine-last-used`). An
+  unreachable connection is a warning.
+- akm no longer falls back to an `opencode` binary on `PATH`. With no connection
+  and no harness, model features and agent work are off, and each command that
+  needs one points at `akm setup`.
+- A workflow run frozen before plan version 8 whose plan holds a command target
+  cannot be resumed: `akm workflow run` abandons it and names the command that
+  starts it afresh.
+- `GET /api/config` lists `connections` and `harnesses` where it listed
+  `engines`.
 - The built-in improve strategies `quick`, `reflect-distill`, `thorough`,
   `catchup` and `proactive-maintenance` are removed. Only `default` and
   `consolidate` are built in. A config block with one of those names still
@@ -87,14 +130,32 @@ Other breaking changes:
 - `package.json` has an `exports` map: only `akm-cli/api`, `akm-cli/package.json`
   and `akm-cli/dist/*` resolve.
 - The runtime conversions for config older than 0.9.15 are removed, as above.
+- A harness and an `exec` unit's command run with your environment as it is; 0.9
+  gave them an allowlist. `pass_env:` still loads and selects nothing.
 
 ## New
 
-- **OpenCode 2.** akm detects the OpenCode major from the engine's binary and
-  drives OpenCode 1 or 2 through its own adapter, for SDK dispatch, CLI
-  dispatch, session history and config import. OpenCode 1 keeps working and
-  logs one warning recommending OpenCode 2. `akm upgrade` and `akm health` know
-  the new `akm-opencode-v2` plugin.
+- **Connections and harnesses.** `akm setup --endpoint URL --yes` sets up a
+  connection; `akm models` shows and changes which model answers each alias
+  (`fast`, `balanced`, `reasoning`); `--connection`, `--harness` and `--model`
+  say where one command runs. Model work runs on any harness, with its tools
+  restricted on Claude Code, Codex and OpenCode 2 and unrestricted, with a notice,
+  elsewhere.
+  Harnesses run as thin shells: akm hands a program the prompt and takes its
+  standard output as the reply.
+- **OpenCode 2, run by akm.** Agent work on a connection with no harness runs on
+  akm's own runtime, a pinned OpenCode 2 binary that akm fetches from the npm
+  registry on first use (about 114 MB, into its cache) and runs as a process,
+  with no entry in config. With no network for that step, enable the `opencode`
+  harness with an installed OpenCode 2 instead. A harness with `platform: "opencode"` is your
+  OpenCode, whichever major is installed, run through its CLI with your config,
+  providers, plugins, default model and logins; your OpenCode owns them and akm
+  reads, copies and embeds none of it. OpenCode 1 keeps
+  working; where akm reads its version it warns once that OpenCode 2 is
+  recommended.
+  `akm proposal extract --type opencode` reads OpenCode 2 history with SQLite,
+  read-only. `akm upgrade` and `akm health` know the new `akm-opencode-v2`
+  plugin.
 - **`akm-cli/api`.** `curate(query, options)` returns exactly what
   `akm --detail agent -q curate` prints, computed in-process. It is for the
   plugins; nothing else is a public API.
@@ -150,6 +211,9 @@ Other breaking changes:
   keys now.
 - The `targetVocab` marker on `task_history` rows and the `"mcp"` package
   keyword.
+- The `opencode serve` server management, the OpenCode HTTP adapters, the
+  per-harness result extractors and their JSON output modes, and the LLM feature
+  gate.
 
 ## Plugins
 
@@ -162,9 +226,11 @@ Other breaking changes:
   runs; the new build loads at the next restart. A spec pinned in your OpenCode
   config is left alone.
 - OpenCode 1 asks before reading or writing outside the project directory.
-  OpenCode 2 does not unless its config says `ask`, so akm's rejection of a
-  permission request only happens there once you add the rule. akm changes no
-  OpenCode default. See [Configuration](../../reference/configuration.md#engines).
+  OpenCode 2 does not unless its config says `ask`. OpenCode's headless `run`,
+  which akm's own runtime and the `opencode` harness both use, rejects every
+  permission request and cancels every question, and the model carries on; akm
+  changes no OpenCode default. See
+  [Configuration](../../reference/configuration.md#harnesses).
 - Plugins and scripts that pass `--shape agent` must move to `--detail agent` in
   step with the CLI. A call with `--shape agent` fails on 0.10, and one with
   `--detail agent` fails on 0.9.
@@ -192,12 +258,11 @@ Other breaking changes:
 - `akm proposal revert` of a retirement works after the 30-day archive purge.
 - `akm search` no longer warns "no embedding provider is configured" on a default
   install.
-- A signal to `akm agent` now ends the CLI harness it started. An OpenCode 2 SDK
-  dispatch ends at once when akm rejects a permission request, instead of waiting
-  out its deadline.
+- A signal to `akm agent` now ends the CLI harness it started.
 
 For the rules each improve process follows in 0.10, see
-[the 0.10 process rules](../../architecture/0.10-process-rules.md). For the
+[the improvement loop](../../architecture/improvement.md) and the
+[improve workflow reference](../../architecture/internals/improve-workflow.md). For the
 entry behind each item, run `akm help migrate <build number>` (for example
 `akm help migrate 0.10.26101201`) or read the
 [CHANGELOG](https://github.com/itlackey/akm/blob/main/CHANGELOG.md).

package/docs/migration/release-notes/0.6.0.md

@@ -93,5 +93,5 @@ Full migration guides:
 - https://github.com/itlackey/akm/blob/main/docs/archive/pre-1.0-migration.md (pre-1.0
   architecture refactor — read this first if you are coming from 0.5.x or
   an earlier 0.6 pre-release)
-- https://github.com/itlackey/akm/blob/main/docs/migration/v0.5-to-v0.6.md
+- https://github.com/itlackey/akm/blob/7a4f302febfc0fe8c0bf3028c6156e6edc5aae33/docs/migration/v0.5-to-v0.6.md
   (terminology cut, registry schema v3, publisher changes)

package/docs/migration/release-notes/0.7.0.md

@@ -260,7 +260,7 @@ akm proposal accept <id>
 
 - [Archived pre-1.0 migration plan](https://github.com/itlackey/akm/blob/be3a6a632b0cbe7a63ce71b7d093d8ac266e857c/docs/archive/pre-1.0-migration.md) — per-surface delta from any 0.6.x
   baseline. The canonical reference for upgrading.
-- [v0.5 → v0.6](https://github.com/itlackey/akm/blob/main/docs/migration/v0.5-to-v0.6.md) — the older terminology cut and
+- [v0.5 → v0.6](https://github.com/itlackey/akm/blob/7a4f302febfc0fe8c0bf3028c6156e6edc5aae33/docs/migration/v0.5-to-v0.6.md) — the older terminology cut and
   registry schema v3.
 - [v1 architecture spec](https://github.com/itlackey/akm/blob/be3a6a632b0cbe7a63ce71b7d093d8ac266e857c/docs/archive/v1-architecture-spec.md) —
   the architecture contract that 0.7.0 commits to maintain through

package/docs/migration/release-notes/0.9.0.md

@@ -43,7 +43,7 @@ Key operator-facing changes:
   `src/core/asset/asset-placement.ts`). That wiring is deferred to 0.10 as
   its own change (see
   [STABILITY.md](../../../STABILITY.md#on-the-horizon) and
-  [D12](https://github.com/itlackey/akm/blob/main/docs/architecture/specs/0.9.0-decisions.md#d12--bundleadapterplacenew-stays-unwired-until-010));
+  [D12](https://github.com/itlackey/akm/blob/7a4f302febfc0fe8c0bf3028c6156e6edc5aae33/docs/architecture/specs/0.9.0-decisions.md#d12--bundleadapterplacenew-stays-unwired-until-010));
   placement is already correct for every existing bundle today, this only
   changes which code computes it. `adapter.validate()`, by contrast, is a
   REQUIRED interface member and each adapter owns its own checks in 0.9.0:

package/docs/migration/release-notes/README.md

@@ -2,7 +2,7 @@
 
 This directory holds one `.md` file per release. Each file is the short,
 focused migration note that `akm help migrate <version>` prints to the
-terminal. The longform cross-release guides (e.g. `v0.5-to-v0.6.md`)
+terminal. The longform cross-release guides (e.g. `v0.8-to-v0.9.md`)
 live one level up in `docs/migration/`.
 
 ## Available notes