Skip to content

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

Rust

Merge remote-tracking branch 'upstream/main' into feature/kimi-window-order

Lucas Oliveirac9eb264496fd
diff --cc CHANGELOG.md
index b697f54d,ba7b17fc..a4af606d
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@@ -7,51 -7,40 +7,84 @@@ and this project adheres to [Semantic V
## [Unreleased]
+### Added
+- `AI_MEMORY_LLM_HEADERS` (`llm_headers` in `config.toml`) attaches extra
+ HTTP headers to every LLM chat request, for gateways that require a
+ caller-identifying header. Entries are `Name=Value` or `Name: Value`,
+ comma separated in the env var. Parsed and validated once at the
+ configuration boundary, so a malformed entry fails at startup rather than
+ on the first consolidation pass, and providers consume typed header
+ material instead of operator strings. Headers ai-memory sets itself
+ (`authorization`, `content-type`, `x-api-key`, `x-goog-api-key`,
+ `anthropic-version`, `anthropic-beta`, `openai-beta`, `host`,
+ `content-length`) are refused: `reqwest` appends rather than replaces, so a
+ duplicate would break the request instead of overriding it. Values are
+ marked sensitive on the wire and never logged — the `Debug` output carries
+ header names only.
+
+### Changed
+- Every LLM chat request now sends `User-Agent: ai-memory/<version>`.
+ `reqwest` sends no user agent unless one is configured, so provider
+ requests previously arrived anonymous, and gateways that require callers to
+ identify themselves reported ai-memory as an unknown client. An
+ `AI_MEMORY_LLM_HEADERS` entry for `user-agent` overrides it. The Copilot
+ provider is unchanged: it keeps `GitHubCopilotChat/<version>`, the
+ editor-plugin agent GitHub's Copilot API expects.
+- The `opencode` provider now sends `x-opencode-session` on every request,
+ defaulting to one id per process when `AI_MEMORY_LLM_HEADERS` does not
+ supply one. OpenCode's Go documentation covers third-party access to its
+ endpoints and asks callers to identify themselves; both Go and Zen
+ correlate requests by that header, and traffic without it is reported as
+ unattributable.
+ Set the header explicitly to keep the value stable across restarts or to
+ tell several ai-memory instances apart.
+
### Fixed
+ - `install-hooks --agent zcode --apply` now removes stale ai-memory
+ hooks left under event keys this version no longer manages (e.g. a
+ legacy `SessionEnd`), instead of reporting "already up to date" while
+ a broken/orphaned entry lingered (#600). The dry-run printed snippet
+ also now states plainly that `--apply` persists the auth token to
+ `<data-dir>/auth-token` (0600) and writes token-less args, so the
+ applied config differs from the embedded-token snippet by design.
+ - Local-embedding model download (`fetch_model`) now bounds a stalled
+ connection instead of hanging startup forever (#602): a 30s connect
+ timeout and a generous 600s overall ceiling (large model files, so
+ not the inference clients' flat 120s that would fail a slow download).
+ - The OKF v0.2 migration no longer crash-loops on startup with a
+ libgit2 `invalid object specified … class=Tree` error that left the
+ server unable to boot (#594). The wiki commit re-hashed files through
+ libgit2's index, whose stat cache could trust a cached blob OID absent
+ from the object database (a store carried across libgit2/git versions,
+ or an interrupted earlier operation) — `write_tree` then aborted and,
+ because the migration commits through that path, every restart failed.
+ The commit now clears the index before staging so every file is
+ re-hashed from the working tree. (The Docker runtime ships no `git`,
+ so the fix is in-library, not a CLI fallback.)
+ - HTTP headers that carry a credential in an opaque value are now redacted
+ before reaching durable storage. Previously such a header matched no
+ built-in pattern unless it used the `Bearer` keyword or an
+ `UPPER_SNAKE_TOKEN=` shape. The bearer rule requires the literal keyword,
+ and the generic env-var rule requires `[A-Z][A-Z0-9_]*_TOKEN`, which never
+ matches a kebab-case header name. `X-Amz-Security-Token` (AWS SigV4),
+ `X-Api-Key`, `Private-Token` (GitLab), and `Ocp-Apim-Subscription-Key`
+ (Azure) all fall in that gap, and tool output echoing a `curl` invocation
+ is a common way they reach capture. A `key` or `token` suffix on its own
+ does not imply a secret, so it must be qualified by an auth word:
+ `Idempotency-Key`, `Continuation-Token` and storage partition keys are
+ left intact and stay readable in captured output.
+- `AI_MEMORY_LLM_BASE_URL` now works with `AI_MEMORY_LLM_PROVIDER=opencode`.
+ The provider hardcoded OpenCode's **Go** endpoint and the factory dropped
+ the configured base URL without a word, so Zen's general catalogue at
+ `https://opencode.ai/zen/v1` was unreachable through it — Zen and Go are
+ separate products, not two spellings of one. Go remains the default, so
+ existing setups are unaffected; an override keeps the `x-opencode-session`
+ default and the user agent, since both endpoints correlate requests the
+ same way. Model ids are per catalogue, so set `AI_MEMORY_LLM_MODEL`
+ explicitly when overriding. `OPENCODE_ZEN_BASE_URL` is deprecated in
+ favour of `OPENCODE_GO_BASE_URL`: the constant named Zen but has always
+ held Go's URL. It keeps its value, so code compiled against it is
+ unaffected.
- `as_of` time-travel queries and the entity retrieval stream now work
on real stores. Both read the entity index, which was populated only
from an LLM consolidator's `entities:` frontmatter — absent on the