Major update from v1.0.0-test-10 — new session continuation workflow, full CLI redesign, recovery command, comprehensive standards compliance, and platform decision corrections across all 5 targets.
Installation
CLI:
npm install -g agentic-pm@1.0.0-test-2Templates (via the new CLI):
apm init -t v1.0.0-test-11The CLI was redesigned alongside these templates. If you're on an older CLI version, update to v1.0.0-test-2 first — the new template commands reference CLI features (apm archive, apm add) that don't exist in earlier versions.
Templates
New: Session Continuation
Closes the APM session loop — when a project finishes (or at any point), you can summarize and archive it, then start a follow-up session with access to previous context.
/apm-8-summarize-session— new command that spawns a non-APM agent to explore the current.apm/directory, source code, and planning artifacts, then produces a session summary document. Not a formal APM role — just an ad-hoc assistant to close the loop.apm-archive-explorer— new agent file that Planners spawn as a subagent to explore archived sessions and extract relevant context without loading full archives into the context window.- Archive detection in Planner context gathering — Planners check
.apm/archives/before starting question rounds and offer to explore relevant previous sessions. - Manager completion flow — Managers recommend running
/apm-8-summarize-sessionin their completion message.
New: Recovery from Auto-Compaction
/apm-9-recover— new troubleshooting command that reconstructs agent context after the platform compacts a conversation mid-session. Supports flexible role detection (arguments, context clues, or ask User). Replaces a non-functional Framework Rule.
Agent Instance Terminology
- "Agent sessions" renamed to "agent instances" (numbered lifetimes within a single APM session). "Session" is now reserved for the overall APM project. "Chat" replaces "session" where referring to platform conversations.
Standards Compliance and Workflow Optimization
- Voice/person distinction codified in WRITING.md: standards use 3rd-person, runtime files use 2nd-person addressing the reading agent. Applied across all commands and guides.
- Per-standard audit (45 findings): em-dashes to hyphens, "follow" to "per", Stage/Memory capitalization, section cross-reference titles, batch constraint softening, stop condition additions.
- Memory term elevation: Memory is now a formal term in TERMINOLOGY.md, scoped to
.apm/memory/contents. - Context gathering: prohibited planning vocabulary during information-gathering rounds, round depth minimum, subagent verification as procedural step.
- Work breakdown: renamed to Per-Stage Task Analysis, Plan Header Format spec added, User involvement in Task Scope reasoning.
- Task execution: natural subagent framing replacing mechanical thresholds.
- Task review: Memory Note filtering (ephemeral vs durable), last-Task shortcut for Stage summary.
- Placeholder rename:
{AGENTS_FILE}renamed to{RULES_FILE}.
Build Pipeline
- Agents directory support added for all 5 targets (flat files; Copilot uses
.agent.mdextension). - New placeholders:
{AGENT_PATH},{AGENTS_DIR},{GUIDES_DIR},{ARCHIVE_EXPLORER_GUIDANCE},{SUBAGENT_GUIDANCE}. - Platform decision fixes across all 5 targets:
- Claude Code: subagent tool
Task→Agent - Gemini CLI:
{RULES_FILE}→GEMINI.md, subagent syntax →@codebase_investigator, config note →experimental.enableAgents - GitHub Copilot:
{ARGS}→${input:args}, agent files use.agent.mdextension - OpenCode: commands directory → plural
.opencode/commands, subagent tool → capitalizedTask
- Claude Code: subagent tool
postInstallNotefield in release manifest — CLI displays per-platform warnings after install (e.g., Gemini gets a subagent config reminder).
CLI (v1.0.0-test-2)
Full restructure of the CLI. The command surface, installation flow, and output have all changed from the version that shipped with test-10.
New Commands
apm add— add assistants to an existing installation without re-initializing.apm remove— remove installed assistants. Destructive action confirmation,--forceflag.apm status— show current installation status (installed assistants, versions, source).apm archive— session archival management. Create archives (snapshots all.apm/contents), list with--list, delete with--delete <name>, clear all with--clear. Supports--name <name>for custom archive names.
Changed Behavior
apm initis now fresh-only — if APM is already initialized, it shows current status and points you toapm add,apm update, orapm archiveinstead of re-initializing.apm updatenow auto-archives before updating, pre-validates assistants against the target release, offers stable/pre-release choice when on a pre-release track, and supports date-based release filtering for custom repos.apm customabsorbed repo management from the deletedapm configcommand (--add-repo,--remove-repo,--list,--clear). Added--forceflag for destructive operations.
Installation Tracking and Cleanup
- Per-assistant file tracking — metadata now records exactly which files APM installed per assistant. Cleanup only removes tracked files, preventing accidental deletion of user files.
UX Overhaul
- Progress spinners replace verbose logging for network operations.
- Clean summary screens — every command clears intermediate output and shows a final summary.
- Post-install notes — per-platform warnings displayed after install/update (from manifest
postInstallNotefield). - Unknown command suggestions via prefix matching.
Removed
apm config— repository management moved toapm customflags.
Infrastructure
- GitHub API: Accept header updated from deprecated
v3format toapplication/vnd.github+json. - GitHub Actions:
checkoutv4 → v6,configure-pagesv4 → v5,upload-pages-artifactv3 → v4. - npm package: test transcripts excluded from published package (2.7 MB → 147 kB).
Thanks for testing. Feedback on the session continuation flow, the new CLI commands, and platform-specific behavior is especially useful before v1.0.0 stable.