Add @deepseek-ai/dsh-tmux-context: an opt-in per-turn context plugin that
reads which tmux session/window/pane this agent process runs in (plus the
window layout tree) via the ctx.bash seam, and injects it as one durable,
source-attributed user/message when the location changes.
- Pull on the first step of each turn; no tmux hook or background process.
- Detect a real pane by tty, not $TMUX_PANE alone: a terminal launched from
a tmux shell inherits $TMUX/$TMUX_PANE from that ancestor, so the command
also matches the pane's #{pane_tty} against this process's controlling
terminal and emits fields only on a match.
- No-op outside a real pane, without a bash executor, or on a malformed
reading.
- Own location and layout only: no pane sizes, no sibling-pane scraping.
- Unit tests at 100% per-file coverage, plus a keyless Loader e2e with a
mock bash provider so it replays without tmux.
- Agent Note: 2026-07-27-tmux-location-context.
The parent implementation introduced sandboxMode and approvalPolicy as generic SessionHeader fields, then propagated those fields through both persistence backends, session-query indexes, collision checks, policy-specific seed-boundary folds, catalogs, and a broad test matrix. That storage plane is unnecessary: Session already accepts a validated constructor seed, and persistence captures that seed when the session is announced before committing its first batch.
Capture each parent override synchronously at delegation, append source-tagged sandbox/mode and approval/policy records after the optional fork prefix, and create the child with that combined seed. Keeping header.seedLength at the original fork-prefix length preserves lineage while ordinary last-event-wins folds make the inherited records outrank stale parent history and remain subordinate to later child switches. Unswitched parents still stamp nothing, so children continue to follow deployment defaults.
Remove the generic header fields and every persistence/query/schema branch built around them. Collapse the inheritance suite from ten leaking scenarios to four owned-context cases covering real filesystem confinement, stale fork precedence, delegation-time capture, and the no-override path. The assembled headless snapshot now asserts the persisted inheritance event directly.
This keeps the security behavior while restoring policy ownership to the existing event log and deleting the speculative durability machinery that the original tests did not exercise.
39 conflicts resolved per the reattachment plan (missions worktree-projbiz
0728-1859): baseline wins for deleted packages (host/runtime, old ui/acp,
ui-sidebar Rows/tree) and retired specs; unions for wire-layer exports and
client summary fields; the approval takeover, waitingApprovals tracking, and
PendingApproval domain face carry over onto the master structure. The two
new host specs follow the runtime->apiproxy rename. Dead PR-side wiring
(ConversationInjected permissions/setPermission spread, InputBar controls
prop, boot.ts sandbox composition) resolves to master and its replacement
lands in follow-up commits.
Retarget the feature branch to the current master tip without rewriting its existing review history. Keeping this as a dedicated merge checkpoint makes the later simplification diff attributable to the stacked child rather than mixing base movement with design changes.
Resolve the identified-message API drift in the feature tests by constructing complete user messages, reading the nested tool-result message shape, and adapting the prompt-submit listener signature. Preserve both sides of the user-approval conflict: master’s createUserMessage wrapper and the feature’s inherited-policy attribution.
Regenerate the Cordis and persistence catalogs, re-record the session README pair, and refresh the affected ACP/headless fixtures so derived artifacts describe the merged source rather than either parent in isolation.
Validated with the focused policy/session/persistence/query suites (430 tests), focused ACP/headless snapshots (3 tests), build, doc-sync (25 gates), lint, hygiene, and git diff checks.
The browse interaction also presents a dialog (the in-app modal), so 'dialog'
failed to discriminate the two capability kinds; 'native' names where the
chooser runs. Package directory-picker-dialog -> directory-picker-native, kind
'dialog' -> 'native', with every seam/gateway/client/doc reference updated and
the seam Agent Note's naming rationale rewritten to match.
ds-review-bot round 3. The seam package broke the service-package export
contract (named export only), so the config catalog filed it under Other
libraries and default imports failed; it now default-exports DirectoryPicker
like every abstract seam, and the regenerated catalog lists it as one.
The picker-kind effect also let a settlement from a superseded flow open
leak into the current one (close/reopen mid-describe, or a reconnect that
swaps the backend): the read now resets the affordance on every open and a
cleanup-toggled flag discards obsolete settlements, both directions pinned
by jsdom races.
Fetch-Metadata and Origin are only attached to trustworthy destinations, so
over plain HTTP a rebound page's same-origin GET (EventSource, images,
navigations) arrives with no browser markers and a readable response. Remove
the marker shortcut; non-browser clients pass the same fence via loopback,
the CLI-derived LAN IP literals, or a declared authority.
A dangling colon (harness.internal:) or zero-padded port parses cleanly while
WHATWG silently rewrites it, turning an intended exact-port grant into an
any-port grant. Replace the character blacklist with a round-trip check: an
entry must read back from parsing exactly as written (case aside), refusing
the whole rewrite class at load.
WHATWG parsing would quietly read a hostname out of harness.internal/path or
user@harness.internal, authorizing the typo's hostname; other typos would sit
silently ignored until requests 403. Refuse every URL part beyond host[:port]
at plugin load.
The web GUI's folder picking was hardwired to one interaction: a native
OS chooser compiled into the gateway, unusable for remote deployments
and swappable only by editing apiproxy source.
Directory picking becomes a three-package capability seam in
packages/host: ctx.directoryPicker returns a discriminated capability —
dialog (the extracted native chooser; host-display only) or browse
(new: one-level listing + child creation over Node stdlib, hidden flags
host-stamped, symlinks followed, ancestry crumbs; remote-capable). The
gateway injects the seam, advertises the kind via
host.describe.directoryPicker, serves host.listDirectory /
host.createDirectory under browse, and answers
directory-picker-unavailable across kinds. cordis.yml is the swap
point; apps/cli keeps dialog mounted, so behavior is unchanged until
the in-app browser PR flips the default. The connection fixture serves
a deterministic browse tree; WorkspacesService gains the browse calls
the browser UI will drive. Decision record:
.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.md
Markerless requests pass on any Host (a non-browser sender is the principal
and forges headers anyway); browser Host matching gains port-less entries and
WHATWG normalization; dsh derives LAN IP-literal authorities for an
all-interfaces bind and web grows --trusted-host for named ones.
The only browser-trust guard covered host.pickDirectory, while the
consequential methods (session.prompt drives bash) accepted any Host —
open to DNS rebinding, where a rebound page reads and writes the API as
if same-origin and only the Host header betrays the attacker's domain.
The pickDirectory-specific loopback guard becomes a prefix-wide fence:
Host must be loopback or an exact host[:port] from the new trustedHosts
config, an attached Origin must equal that authority, and explicit
cross-site markers are refused; requests without browser markers (curl,
tests, native clients) pass, because without a browser there is no
confused deputy. The loopback-socket check is dropped — binding policy
expresses reachability, and the fence is not an auth layer. The Agent
Note records the full threat model and the alternatives.
gen-cordis-catalog type-link rows for the ProjectionDefinition surface and
CommandExecution; a sessionProjections service-role row for gen-doc-graphs;
regenerated module graph, persistence/config/cordis catalogs and api-catalog;
packages/README rows condensed back under the word ceiling; the RFC's sketch
fences marked ignore-check on both language sides (pairing re-recorded).