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.mdindex 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 ofa conversation (keyed by `conversationId`) now maps to SessionStart, in thenative, 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 writeinto 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` (anddiff --git a/docs/desktop/capture-and-dedup.md b/docs/desktop/capture-and-dedup.mdindex 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.mdindex 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 inputevent to SessionStart (`should_process_hook_event` in`crates/ai-memory-cli/src/commands/hook.rs`), so it posts session-startand 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 recorderthat printed `{}` made the transcript record `tool call denied bypre-tool hook` and `PostToolUse` never fired. ai-memory's shell and nativediff --git a/docs/llm-providers.md b/docs/llm-providers.mdindex 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 theinstallation 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 Claude4.7 and later models and Claude Mythos Preview because those models rejectnon-default sampling parameters. `llm-test` sends the same representative 0.2