Skip to content

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

Rust

fix: finish #1306 and #1301 for merge

AkitaOnRailsd5e8c4a82d59
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 07525ccc..3203bde5 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -25,11 +25,13 @@ version in [`docs/changelog/`](docs/changelog/):
user turn: `invocationNum` restarts at 0 each turn, so only the first turn of
a conversation (keyed by `conversationId`) now maps to SessionStart, in the
native, shell and PowerShell hooks. Payloads without a `conversationId` keep
- the previous per-turn behavior.
+ the previous per-turn behavior. A conversation resumed in a new process does
+ not start a new session, so a handoff left meanwhile is read with
+ `memory_handoff_list` rather than injected. (#1306)
- Fixed `llm-test --provider anthropic-oauth` reporting Anthropic's refusal of a
`claude setup-token` token as a plain rate limit: that 429 now carries a hint
- that it is not a real rate limit and names the alternatives, and
- `docs/llm-providers.md` documents the behavior. (#1170)
+ that it is not a real rate limit and names the alternatives, which
+ `docs/llm-providers.md` already describes. (#1170)
- Fixed the thin-client commands ignoring a custom `bind`, which could write
into the wrong store. `server_url` defaulted to `http://127.0.0.1:49374`
and was never derived from `bind`, so `ai-memory --data-dir X status` (and
diff --git a/docs/desktop/capture-and-dedup.md b/docs/desktop/capture-and-dedup.md
index 8bb64678..43cb440d 100644
--- a/docs/desktop/capture-and-dedup.md
+++ b/docs/desktop/capture-and-dedup.md
@@ -138,6 +138,5 @@ never invent capture from it; treat it as metadata only.
product gains traction with users; no docs.
5. Scope for scratch-workspace sessions: single `desktop/claude-scratch`
pool vs per-scratch projects (product decision; affects auto-scope).
-6. Antigravity `invocationNum` restarts at 0 on every user turn, so
- ai-memory's SessionStart mapping runs per turn: acceptable, or gate it
- per conversation? (product decision after measuring the server effect)
+6. Resolved (#1306): Antigravity `invocationNum` restarts at 0 on every user
+ turn, so SessionStart is now gated per conversation (`conversationId`).
diff --git a/docs/desktop/verification-2026-10.md b/docs/desktop/verification-2026-10.md
index 25de30e0..35e42310 100644
--- a/docs/desktop/verification-2026-10.md
+++ b/docs/desktop/verification-2026-10.md
@@ -74,8 +74,8 @@ recorder, `agy -p` and the documented stream-json input
event to SessionStart (`should_process_hook_event` in
`crates/ai-memory-cli/src/commands/hook.rs`), so it posts session-start
and fetches the handoff on every turn. The brief and the profile digest
- have their own once-per-session markers; whether the per-turn
- session-start post and handoff fetch are acceptable is open.
+ have their own once-per-session markers. Resolved in #1306: only the
+ first turn of a conversation (by `conversationId`) maps to SessionStart.
- **A `PreToolUse` reply without a `decision` denies the tool.** A recorder
that printed `{}` made the transcript record `tool call denied by
pre-tool hook` and `PostToolUse` never fired. ai-memory's shell and native
diff --git a/docs/llm-providers.md b/docs/llm-providers.md
index 3f6e8cd0..fb014d78 100644
--- a/docs/llm-providers.md
+++ b/docs/llm-providers.md
@@ -335,13 +335,6 @@ wrappers forward either token by name to short-lived helper commands such as
`llm-test`; configure the long-lived server container separately as shown in the
installation guide.
-Anthropic may also refuse a subscription token outright: with a `claude
-setup-token` token, every request whose system prompt does not identify itself
-as Claude Code can come back as `429 rate_limit_error` with the body `"Error"`,
-even though the same token works from `claude -p` (#1170). That 429 is not a
-real rate limit, and ai-memory does not impersonate Claude Code to get around
-it. Use `anthropic` with an API key, or an OpenAI-compatible gateway, instead.
-
For both Anthropic providers, ai-memory omits `temperature` for Claude
4.7 and later models and Claude Mythos Preview because those models reject
non-default sampling parameters. `llm-test` sends the same representative 0.2