The with_macro_dirs fixture derived its temp-dir name from a wall-clock
nanosecond timestamp, so parallel tests starting in the same clock tick
shared a directory and saw each other's macro files (flaky on CI
runners with coarse tick granularity). A process id + atomic counter
makes the name unique by construction.
An invalid installed macro invoked as a top-level command fell through
to the generic unknown-command error, while .macro <name> reported the
parse/validation failure. Both paths now surface the reason.
Long agent/skill descriptions wrapped badly in the bullet-list format.
Extract a shared asset_table helper (UTF8_FULL + dynamic arrangement,
same style as the markdown renderer and .list macros) and use it for
the agents, skills, and macros listings. The skills loaded marker
keeps its color; comfy-table's custom_styling feature accounts for
ANSI sequences in column widths.
Hand-rolled {:<24} padding broke alignment as soon as a macro name
exceeded the column width. Reuse the comfy-table UTF8_FULL preset with
dynamic content arrangement, matching the markdown renderer's tables.
Covers top-level .name invocation, the new description/isolated macro
fields (with the non-isolation persistence, fail-fast, nested-macro, and
.exit caveats), workspace .coyote/macros/ + --no-workspace-macros,
enabled_macros scoping at global/role/agent/session levels, and
.macro enable|disable across the README and every example config.
graph.example.yaml gains a note that enabled_macros is ignored in graph
configs.
CHANGELOG intentionally untouched: it is generated by commitizen at
release time from the conventional commit subjects.
Implements plans/custom-commands-design.md §8.
no_workspace_mcp (and therefore no_workspace_macros, per the exact-mirror
ruling) is CLI-flag-only: AppConfig field exists but there is no
Config-struct key and no env arm, so a config.yaml entry is non-functional.
Pre-existing issue: config.example.yaml:140 documents the dead
no_workspace_mcp key — recorded as follow-up, out of scope.
Mirrors --no-workspace-mcp exactly: a CLI-only flag backed by an
AppConfig field (default false) that disables .coyote/macros in both
the resolved macro policy and Macro::load's workspace-then-global
preference, so the two always agree (custom-commands design §5).
Make the macro isolated field live (design §3, §9 step 5):
isolated: false now runs the interpolated steps via run_repl_command
on the live RequestContext — session-recorded, conversation-visible,
with mutating steps persisting by design — while isolated: true keeps
the forked execution byte-for-byte unchanged.
- Add macro_non_isolated companion field beside macro_flag; both
fork-propagation sites mirror it verbatim.
- RAII MacroModeGuard wraps the whole &mut RequestContext (DerefMut
passthrough) and restores flag+mode on every exit path, including a
failing step; steps remain fail-fast.
- Reject nested macro invocation when the current mode is non-isolated
("nested macros not allowed in non-isolated mode"); an isolated
macro's step may still run a non-isolated macro inline on its fork.
- use_agent now suppresses the agent's default session only for
isolated macros; a non-isolated .agent step engages it as if typed.
Implements the invocation and management surfaces from
plans/custom-commands-design.md §4 and §6:
- Top-level dispatch: an enabled macro <name> now runs as ".<name> [args]"
from the command catch-all; runtime-disabled macros point at
".macro enable <name>", locked macros name the owning config, and
unknown commands keep the existing error verbatim
- .macro enable|disable <name>: runtime toggles over the in-memory
global-level enabled_macros list (disable with no list materializes
all-active-minus-name); toggles error when a role/agent/session
allowlist owns the field
- .set enabled_macros <csv|null> with workspace-then-global existence
validation; .set key completion gains enabled_macros and the
previously missing enabled_skills
- Dynamic completion: enabled macros (with descriptions) join built-ins
on ".<TAB>" without touching the static command registry;
".macro <TAB>" lists invocable macros (incl. built-in-shadowed ones)
plus the enable/disable subcommands; second-arg completion offers
toggle-eligible names
- .list macros: enriched table (name, source, isolated, state,
description) covering every resolver state incl. missing and
shadowed rows; .help gains a custom-commands section
- Session info/render and sysinfo display enabled_macros; Macro::load
resolves workspace-then-global; enable/disable rejected as macro
names in the creator
Adds src/config/macro_policy.rs: MacroPolicy::effective computes the
visible macro set on demand from the discovered definition files, the
four-level enabled_macros allowlists, and the built-in command names.
- Discovery scans workspace (.coyote/macros/) then global macros dirs on
every resolution; workspace shadows global by name, and the shadowed
global entry is retained and flagged so both stay listable (plan
custom-commands-design.md §5). Workspace scanning is gated on a bool
parameter so the future --no-workspace-macros flag wires in one line.
- Allowlist precedence is session > agent > role > global, first Some
wins, no merging; None falls through, an empty list is an explicit
zero, all-None enables everything (mirrors SkillPolicy).
- Per-macro states per plan §6: enabled, disabled (runtime, global-level
exclusions only), locked (role/agent/session exclusions, recording the
owning level), missing (unknown allowlist names warn instead of
bailing — deliberate divergence from skills), shadowed (built-in name
collisions), and invalid (parse failures and the reserved names
enable/disable). Invalid beats allowlist exclusion beats shadowing.
- Adds enabled_macros() accessors on Role, Session, and Agent alongside
their enabled_skills() counterparts, plus paths::workspace_macros_dir.
- 37 tests: state matrix, pairwise precedence, explicit-zero pinned at
every level, workspace shadowing, reserved names, builtin collisions,
missing rows, invalid YAML, and env-gated discovery (#[serial]).
Mirrors the enabled_skills plumbing per plans/custom-commands-design.md §5:
- global: Config + AppConfig structs, from_config copy, and the
COYOTE_ENABLED_MACROS env-override arm (csv_to_vec parsing)
- role: frontmatter via parse_string_or_array (list or csv string),
plus the export() mirror so Role::save round-trips the field
- agent (non-graph): plain serde on AgentConfig; graph.yaml silently
ignores the key (pinned by test, no field on Graph by design)
- session: plain serde with csv-or-vec deserializer
Empty list/string deserializes to Some([]) (explicit zero), distinct
from absent/null (None) — pinned by tests at every level, including
the env arm (serial-fenced against the from_config tests, which read
the process env via load_envs).
description (optional, default None) will surface in listings and
completion; isolated (default true) preserves today's forked-context
execution behavior exactly. Both fields use plain serde defaults so
every existing macro YAML deserializes unchanged, and unknown fields
in newer files remain tolerated by older binaries.
Adds Serialize to Macro/MacroVariable (None description skipped) and
back-compat, round-trip, and embedded-asset deserialization tests.
Per plans/custom-commands-design.md §3 / §9 step 1.
The Client trait's default chat_completions, chat_completions_streaming,
and embeddings methods now classify failures via ApiStatusError: on a
401 with a cached OAuth token, the token is distrusted (identity-aware
marker) and the call retried exactly once — the retry's prepare step
sees the marker and force-refreshes. Streaming retries only while the
SSE handler has received no content, preventing duplicate rendering.
A second 401 propagates the original error; other retry errors
propagate as-is. API-key clients never retry. No backoff by design:
cost is bounded to one refresh + one retry per failing request.
distrust_access_token compare-and-invalidates the in-memory entry only
when the cached token equals the rejected one, so a concurrent refresh
is never clobbered. is_valid_access_token and both expiry checks in
prepare_oauth_access_token treat marked tokens as expired, forcing a
refresh of provider-rejected tokens that are still locally unexpired.
The marker is cleared after every completed refresh, including ones
that return the same token.
catch_error and sse_stream now bail with ApiStatusError{status, message}
instead of bare anyhow strings, preserving every existing Display output
byte-for-byte. Enables structural status classification (e.g. 401
detection) via downcast through anyhow context chains.
Replace the spawn-time static Authorization header for OAuth-managed HTTP
MCP servers with McpOAuthClient, a custom implementation of rmcp's
StreamableHttpClient trait that resolves the bearer token on every
request via load_or_refresh_mcp_token. Tokens that expire mid-session
now refresh transparently instead of failing tool calls until restart.
On a 401 for an injected token, the wrapper force-refreshes (identity-
aware: a still-unexpired copy of the rejected token is not trusted) and
retries exactly once, matching Claude Code / official SDK semantics.
Both *_with_max_sse_event_size trait methods are overridden to preserve
the inner client's SSE size enforcement, and the inner reqwest client
mirrors rmcp's default (pool_max_idle_per_host(0), no redirects).
SSE, stdio, and static-header HTTP paths are unchanged; startup
warning semantics (McpAuthRequired reasons) are preserved. Verified
live: mid-session backdated token refreshed transparently during an
active atlassian session.
Compile-clean upgrade verified: zero source changes needed, full test
suite green, clippy clean. Coyote's rmcp API surface (14 items) dodges
all 2.0/3.0 breaking changes; the "Auth required" error string matched
by is_auth_required_error is intact in 3.1.2.
Distinguish why an OAuth MCP server was not started: never authenticated
(no stored credentials), stored token expired and refresh failed, or the
server rejected a token that looked valid. McpTokenStatus replaces the
Option<String> return of load_or_refresh_mcp_token, and McpAuthRequired
carries the reason across the error boundary via anyhow context.
Dark-Alex-17
Alex Clarke